Summary
A cloud-hosted MCP server that gives agents full CRUD control over an organizational knowledge base. You get 179 tools across documents, diagrams (Mermaid, BPMM, D2, PlantUML), plans, tasks, and a self-learning knowledge graph. Agents can provision workspaces, invite members, set RBAC permissions, create folders, edit Markdown documents, insert visualizations, and query the knowledge graph for entity relationships. Supports both Bearer token auth and OAuth 2.1 with dynamic client registration. Works over streamable HTTP, so no local process to manage. Useful when you want Claude or Cursor to not just read your company brain but actively build and maintain it end to end, from billing setup through diagram generation.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Tools
Public tool metadata for what this MCP can expose to an agent.
80 tools
searchToolsSearch available tools by keyword or category. Returns matching tool names and descriptions.2 params
Search available tools by keyword or category. Returns matching tool names and descriptions.
Parameters* required
categorystringCategory filter.one of
navigation · folders · documents · diagrams · images · dataquerystringNatural language description of what you want to do.
listDiagramTypesList supported diagram types. Use the returned `type` field when calling insertDiagramInDocument.5 params
List supported diagram types. Use the returned `type` field when calling insertDiagramInDocument.
Parameters* required
enabledOnlybooleanfieldsarrayField projection. Valid fields: type, label, description, whenToUse, dslLanguage, dslInstructions, exampleDsl, enabled, availableOnFree, sortOrder, updatedAt.
limitnumberoffsetnumberquerystringgetDiagramTypeGuideGet DSL writing instructions for a diagram type. Call before writing diagramCode.2 params
Get DSL writing instructions for a diagram type. Call before writing diagramCode.
Parameters* required
fieldsarrayField projection. Valid fields: type, label, description, whenToUse, dslLanguage, dslInstructions, exampleDsl, enabled, sortOrder, updatedAt.
typestringlistArchitectureIconsList icons for systemsarchitecture diagrams. Use returned iconPath as-is in D2 code (e.g. icon: dev/docker.svg).5 params
List icons for systemsarchitecture diagrams. Use returned iconPath as-is in D2 code (e.g. icon: dev/docker.svg).
Parameters* required
categorystringFilter by category (e.g. AWS, Azure, GCP, dev, essentials).
fieldsarrayField projection. Valid fields: id, iconPath, iconName, category, subcategory, vendor, description, searchTerms, tags, useCases, aliases, isFeatured, displayOrder.
limitnumberoffsetnumberquerystringSearch by name, category, vendor, or description.
getCdmdLanguageGuideGet the CDMD markdown language specification. Call before createDocument if unfamiliar with syntax.
Get the CDMD markdown language specification. Call before createDocument if unfamiliar with syntax.
No parameter schema in public metadata yet.
getCurrentUserReturn the calling user's identity (user_id, display_name, full_name, email, avatar_url). Use this when the user says 'me' / 'mine' / 'I' so you can resolve to their UUID before passing it to tools like updateImprovement(owner_id=…) or filtering by owner. Read-only.
Return the calling user's identity (user_id, display_name, full_name, email, avatar_url). Use this when the user says 'me' / 'mine' / 'I' so you can resolve to their UUID before passing it to tools like updateImprovement(owner_id=…) or filtering by owner. Read-only.
No parameter schema in public metadata yet.
listAssignablePrincipalsServer-side searchable, paginated list of USERS and TEAMS that can be assigned as the owner of an improvement/task in a project. Returns two arrays — `users` (with user_id, display_name, email, avatar_url, has_explicit_permission) and `teams` (with team_id, name, member_count,...6 params
Server-side searchable, paginated list of USERS and TEAMS that can be assigned as the owner of an improvement/task in a project. Returns two arrays — `users` (with user_id, display_name, email, avatar_url, has_explicit_permission) and `teams` (with team_id, name, member_count,...
Parameters* required
kindstringFilter to one principal kind. Default 'all' returns users first then teams.one of
all · user · teamlimitnumberMax results per page (1-100, default 20).
offsetnumberPagination offset.
projectIdstringProject to scope assignees to. Required.
qstringOptional ILIKE search filter — matched against display_name + email (users) and team name (teams).
workspaceIdstringWorkspace UUID. Optional but recommended — when present, the result includes ALL org members; when omitted, only direct project grants + team-expanded users are returned.
listTeamsList teams in an organization, with optional search filter and an `includeMembers` flag that fans out to v_team_members in a single round-trip. Supply EITHER organizationId OR workspaceId (the workspace's parent org is resolved automatically). Use this when the user asks about...6 params
List teams in an organization, with optional search filter and an `includeMembers` flag that fans out to v_team_members in a single round-trip. Supply EITHER organizationId OR workspaceId (the workspace's parent org is resolved automatically). Use this when the user asks about...
Parameters* required
includeMembersbooleanWhen true, each team gets a `members` array (user_id, role, joined_at). Capped at 500 total members across the page. Default false.
limitnumberMax teams per page (1-200, default 50).
offsetnumberPagination offset.
organizationIdstringOrganization UUID. Either this OR workspaceId is required.
qstringOptional ILIKE search on team name/slug.
workspaceIdstringWorkspace UUID. The parent organization is resolved from v_workspaces.
getTeamGet a single team by ID with profile-enriched member list (display_name, email, avatar_url, role, joined_at). Set `includeMembers=false` to skip the member fan-out and just return team metadata. Read-only.2 params
Get a single team by ID with profile-enriched member list (display_name, email, avatar_url, role, joined_at). Set `includeMembers=false` to skip the member fan-out and just return team metadata. Read-only.
Parameters* required
includeMembersbooleanInclude the team's members enriched with user profile info. Default true.
teamIdstringTeam UUID.
listOrganisationsList organisations you have access to. Supports query filtering by name/slug.4 params
List organisations you have access to. Supports query filtering by name/slug.
Parameters* required
fieldsarrayField projection. Valid fields: id, name, slug, subscription_tier, created_at.
limitnumberoffsetnumberquerystringlistWorkspacesList workspaces you have access to. Supports query filtering by name/slug.7 params
List workspaces you have access to. Supports query filtering by name/slug.
Parameters* required
dateFieldstringDate field to filter. Default: updated_at.
fieldsarrayField projection. Valid fields: id, name, slug, organization_id, created_at, updated_at.
fromDatestringISO 8601 date filter (from).
limitnumberoffsetnumberquerystringtoDatestringISO 8601 date filter (to).
listProjectsList projects in a workspace. Supports query filtering by project name.8 params
List projects in a workspace. Supports query filtering by project name.
Parameters* required
dateFieldstringDate field to filter. Default: updated_at.
fieldsarrayField projection. Valid fields: id, name, description, workspace_id, created_at, updated_at.
fromDatestringISO 8601 date filter (from).
limitnumberoffsetnumberquerystringtoDatestringISO 8601 date filter (to).
workspaceIdstringlistFoldersList folders in a project. Use parentId for nested folders. For full tree, use getProjectHierarchy instead.9 params
List folders in a project. Use parentId for nested folders. For full tree, use getProjectHierarchy instead.
Parameters* required
dateFieldstringDate field to filter. Default: updated_at.
fieldsarrayField projection. Valid fields: id, projectId, parentId, name, position, createdAt, updatedAt.
fromDatestringISO 8601 date filter (from).
limitnumberoffsetnumberparentIdstringprojectIdstringquerystringtoDatestringISO 8601 date filter (to).
createFolderCreate a folder in a project. Supports nesting via parentId.4 params
Create a folder in a project. Supports nesting via parentId.
Parameters* required
namestringparentIdstringpositionnumberprojectIdstringupdateFolderUpdate a folder (rename/move/reorder). Supports nesting changes via parentId.4 params
Update a folder (rename/move/reorder). Supports nesting changes via parentId.
Parameters* required
folderIdstringnamestringparentIdstringpositionnumberdeleteFolderDelete a folder recursively, including all nested folders and documents.1 params
Delete a folder recursively, including all nested folders and documents.
Parameters* required
folderIdstringlistDocumentsList documents in a project, workspace, or folder. Supports query search and date filtering.10 params
List documents in a project, workspace, or folder. Supports query search and date filtering.
Parameters* required
dateFieldstringDate field to filter. Default: updated_at.
fieldsarrayField projection. Valid fields: id, title, friendlyId, friendlyIdNumber, projectId, folderId, createdAt, updatedAt, href.
folderIdstringfromDatestringISO 8601 date filter (from).
limitnumberoffsetnumberprojectIdstringquerystringtoDatestringISO 8601 date filter (to).
workspaceIdstringgetProjectHierarchyGet the complete folder and document tree for a project in one call. Recommended first call for navigation.8 params
Get the complete folder and document tree for a project in one call. Recommended first call for navigation.
Parameters* required
dateFieldstringDate field to filter. Default: updated_at.
folderIdstringStart from this folder instead of project root.
fromDatestringISO 8601 date filter (from).
includeDocumentsbooleanInclude documents. Default: true.
maxDepthnumberMax nesting depth. Default: 10, max: 20.
projectIdstringProject ID. Required if folderId not provided.
querystringFilter by name/title (case-insensitive).
toDatestringISO 8601 date filter (to).
getFolderHierarchyGet the folder and document tree starting from a specific folder. Alias for getProjectHierarchy with folderId.7 params
Get the folder and document tree starting from a specific folder. Alias for getProjectHierarchy with folderId.
Parameters* required
dateFieldstringDate field to filter. Default: updated_at.
folderIdstringThe folder ID to start from.
fromDatestringISO 8601 date filter (from).
includeDocumentsbooleanInclude documents. Default: true.
maxDepthnumberMax nesting depth. Default: 10, max: 20.
querystringFilter by name/title (case-insensitive).
toDatestringISO 8601 date filter (to).
getDocumentRead a document's content with line numbers. Returns numbered lines for use with editDocument. Diagrams/images appear as OMITTED markers with metadata (type, diagramId, nlDescription) — use getDiagramInDocument(diagramId) for full DSL code, or dedicated diagram/image tools to...5 params
Read a document's content with line numbers. Returns numbered lines for use with editDocument. Diagrams/images appear as OMITTED markers with metadata (type, diagramId, nlDescription) — use getDiagramInDocument(diagramId) for full DSL code, or dedicated diagram/image tools to...
Parameters* required
contentFieldsarrayContent field projection. Valid fields: offset, limit, totalLines, nextOffset, metadata, text.
documentIdstringThe document ID to read.
fieldsarrayField projection. Valid fields: id, title, friendlyId, friendlyIdNumber, projectId, folderId, createdAt, updatedAt, versionTimestamp.
limitnumberMax lines to return. Default: 200.
offsetnumberLines to skip from start. Default: 0.
createDocumentCreate a document from CDMD markdown. Call getCdmdLanguageGuide first if unfamiliar with syntax. Do not include DIAGRAM/IMAGE markers — insert them after with dedicated tools.5 params
Create a document from CDMD markdown. Call getCdmdLanguageGuide first if unfamiliar with syntax. Do not include DIAGRAM/IMAGE markers — insert them after with dedicated tools.
Parameters* required
cdmdstringchangeSummarystringVersion history summary.
folderIdstringprojectIdstringtitlestringeditDocumentEdit a document with line-based patches. Call getDocument first for line numbers and versionTimestamp. Call getCdmdLanguageGuide if unfamiliar with CDMD syntax. Do not edit DIAGRAM/IMAGE markers manually — use dedicated diagram/image tools.6 params
Edit a document with line-based patches. Call getDocument first for line numbers and versionTimestamp. Call getCdmdLanguageGuide if unfamiliar with CDMD syntax. Do not edit DIAGRAM/IMAGE markers manually — use dedicated diagram/image tools.
Parameters* required
changeSummarystringVersion history summary.
documentIdstringfolderIdstringMove to this folder.
patchesarrayLine-based patches. Can be empty if only updating title or folderId.
titlestringNew title.
versionTimestampnumberVersion timestamp from getDocument() for optimistic locking.
findAndReplaceTextInDocumentFind and replace text in a document. Searches for all occurrences and replaces them. Case-sensitive by default. Diagrams/images are automatically protected — only document text is affected.5 params
Find and replace text in a document. Searches for all occurrences and replaces them. Case-sensitive by default. Diagrams/images are automatically protected — only document text is affected.
Parameters* required
caseSensitivebooleanCase-sensitive matching. Default: true.
changeSummarystringVersion history summary.
documentIdstringfindstringText to search for.
replacestringReplacement text. Empty string to delete occurrences.
getDiagramInDocumentGet a diagram's full details including raw DSL source code. Use diagramId from DIAGRAM_OMITTED markers in getDocument output. Returns diagramCode, type, name, nlDescription, and versionTimestamp.2 params
Get a diagram's full details including raw DSL source code. Use diagramId from DIAGRAM_OMITTED markers in getDocument output. Returns diagramCode, type, name, nlDescription, and versionTimestamp.
Parameters* required
diagramIdstringDiagram ID from DIAGRAM_OMITTED markers.
fieldsarrayField projection. Valid fields: diagramId, documentId, type, name, diagramCode, nlDescription, colorPlan, renderStatus, renderError, createdAt, updatedAt, versionTimestamp.
insertDiagramInDocumentInsert a new diagram into a document. Call listDiagramTypes to find your type, then getDiagramTypeGuide for DSL syntax before writing diagramCode.10 params
Insert a new diagram into a document. Call listDiagramTypes to find your type, then getDiagramTypeGuide for DSL syntax before writing diagramCode.
Parameters* required
afterLinenumberInsert after this line number (1-based).
alignstringAlignment.one of
left · center · rightcaptionstringCaption below the diagram.
colorPlanobjectBPMN only. Color plan: { byElementId: { ElementId: SwatchName } }.
diagramCodestringDiagram DSL code. Call getDiagramTypeGuide for syntax.
documentIdstringdocumentVersionTimestampnumberVersion timestamp from getDocument() for optimistic locking.
nlDescriptionstringExtended description of the diagram (2-4 sentences).
promptstringShort description of what the diagram shows (1-2 sentences).
typestringDiagram type (e.g. mermaid, plantuml, bpmn, d2). Call listDiagramTypes for all types.
updateDiagramInDocumentUpdate a diagram's code, description, or properties. Call getDiagramTypeGuide for DSL syntax. Requires documentVersionTimestamp from getDocument. IMPORTANT: To change what the diagram visually shows, you MUST provide diagramCode with the full updated DSL source. The prompt and...8 params
Update a diagram's code, description, or properties. Call getDiagramTypeGuide for DSL syntax. Requires documentVersionTimestamp from getDocument. IMPORTANT: To change what the diagram visually shows, you MUST provide diagramCode with the full updated DSL source. The prompt and...
Parameters* required
alignstringAlignment.one of
left · center · rightcaptionstringNew caption.
colorPlanobjectBPMN only. Updated color plan. Set to null to remove.
diagramCodestringNew diagram DSL source code. REQUIRED to change what the diagram visually renders. Call getDiagramTypeGuide for syntax. Must provide the COMPLETE updated DSL, not just the changed parts.
diagramIdstringDiagram ID from DIAGRAM_OMITTED markers.
documentVersionTimestampnumberVersion timestamp from getDocument() for optimistic locking.
nlDescriptionstringNew extended description (metadata only — does NOT change the rendered diagram).
promptstringNew short description (metadata only — does NOT change the rendered diagram).
deleteDiagramInDocumentDelete a diagram from a document.1 params
Delete a diagram from a document.
Parameters* required
diagramIdstringDiagram ID from DIAGRAM_OMITTED markers.
deleteDocumentDelete a document.1 params
Delete a document.
Parameters* required
documentIdstringlistDocumentVersionsList version history for a document. Returns timestamps, creator, change summary, and content.8 params
List version history for a document. Returns timestamps, creator, change summary, and content.
Parameters* required
documentIdstringfieldsarrayField projection. Valid fields: id, documentId, versionNumber, title, contentMarkdown, changeSummary, createdBy, createdAt.
fromDatestringISO 8601 date filter (from).
limitnumberMax versions. Default: 50, max: 200.
offsetnumberPagination offset.
sortAscendingbooleanSort oldest first. Default: false.
toDatestringISO 8601 date filter (to).
versionNumbernumberFilter to a specific version.
getImageInDocumentGet image details including a fresh signed URL (expires after 1 hour). Use storagePath from IMAGE_OMITTED markers in getDocument output.2 params
Get image details including a fresh signed URL (expires after 1 hour). Use storagePath from IMAGE_OMITTED markers in getDocument output.
Parameters* required
documentIdstringstoragePathstringStorage path from IMAGE_OMITTED marker.
createImageUploadSessionCreate a PUT upload URL for a document image (max 10MB). Use the returned assetUrl with insertImageInDocument.4 params
Create a PUT upload URL for a document image (max 10MB). Use the returned assetUrl with insertImageInDocument.
Parameters* required
documentIdstringfileNamestringOriginal filename (e.g. screenshot.png).
mimeTypestringImage MIME type (e.g. image/png).
sha256stringOptional SHA-256 hex digest.
insertImageInDocumentInsert an image into a document (max 10MB). Provide imageBase64, imageBinary, or imageUrl. For large files, call createImageUploadSession first then use the returned assetUrl.13 params
Insert an image into a document (max 10MB). Provide imageBase64, imageBinary, or imageUrl. For large files, call createImageUploadSession first then use the returned assetUrl.
Parameters* required
afterLinenumberInsert after this line (0 = beginning, omit = end).
alignstringAlignment. Default: center.one of
left · center · rightaltstringAlt text. Defaults to caption.
captionstringCaption below the image.
documentIdstringdocumentVersionTimestampnumberVersion timestamp from getDocument() for optimistic locking.
fileNamestringOriginal filename.
heightnumberHeight in pixels.
imageBase64stringBase64-encoded image data. Mutually exclusive with imageBinary/imageUrl.
imageBinaryarrayRaw binary as byte array. Mutually exclusive with imageBase64/imageUrl.
imageUrlstringURL to fetch image from, or assetUrl from createImageUploadSession.
nlDescriptionstringDescription of image content for semantic search.
widthnumberWidth in pixels.
updateImageInDocumentUpdate image metadata (alt, caption, dimensions, alignment). Requires documentVersionTimestamp from getDocument for optimistic locking.8 params
Update image metadata (alt, caption, dimensions, alignment). Requires documentVersionTimestamp from getDocument for optimistic locking.
Parameters* required
alignstringAlignment.one of
left · center · rightaltstringNew alt text.
captionstringNew caption.
documentVersionTimestampnumberVersion timestamp from getDocument() for optimistic locking.
heightnumberHeight in pixels.
imageIdstringImage ID from IMAGE_OMITTED markers.
nlDescriptionstringNew image description.
widthnumberWidth in pixels.
deleteImageInDocumentDelete an image from a document and storage.1 params
Delete an image from a document and storage.
Parameters* required
imageIdstringImage ID from IMAGE_OMITTED markers.
createVegaDataUploadSessionCreate a PUT upload URL for a Vega/Vega-Lite data file. Use returned assetUrl in your Vega spec.3 params
Create a PUT upload URL for a Vega/Vega-Lite data file. Use returned assetUrl in your Vega spec.
Parameters* required
contentTypestringMIME type override. Auto-detected from extension if omitted.
documentIdstringfileNamestringOriginal filename (e.g. sales-data.csv). Extension auto-detects content type.
deleteVegaDataFileDelete a data file attachment from a document.2 params
Delete a data file attachment from a document.
Parameters* required
attachmentIdstringAttachment ID to delete.
documentIdstringcreateDocumentIngestSessionStep 1 of file ingest. Mint a single-use PUT upload URL for a large file (PDF, DOCX, plain text, or markdown — up to 150 MB). Returns { sessionId, uploadUrl, expiresAt, maxBytes }. Upload the raw bytes to uploadUrl with PUT, then call createDocumentFromUpload({ sessionId, proj...5 params
Step 1 of file ingest. Mint a single-use PUT upload URL for a large file (PDF, DOCX, plain text, or markdown — up to 150 MB). Returns { sessionId, uploadUrl, expiresAt, maxBytes }. Upload the raw bytes to uploadUrl with PUT, then call createDocumentFromUpload({ sessionId, proj...
Parameters* required
fileNamestringOriginal filename, e.g. report.pdf.
folderIdstringOptional folder to drop the document into. Must belong to projectId.
mimeTypestringOne of: application/pdf, application/vnd.openxmlformats-officedocument.wordprocessingml.document (DOCX), text/plain, text/markdown.
projectIdstringTarget project for the resulting document.
sizeBytesnumberOptional file size hint in bytes. Rejected up-front if it exceeds 150 MB.
createDocumentFromUploadStep 2 of file ingest. After the file is uploaded via the PUT URL from createDocumentIngestSession, call this to start the async conversion. Returns { jobId, documentId } immediately — the document is created as a draft and progressively populated as the worker processes the f...5 params
Step 2 of file ingest. After the file is uploaded via the PUT URL from createDocumentIngestSession, call this to start the async conversion. Returns { jobId, documentId } immediately — the document is created as a draft and progressively populated as the worker processes the f...
Parameters* required
changeSummarystringOptional changelog message for the version snapshot taken when the ingest finalises.
folderIdstringOptional folder. Must belong to projectId.
projectIdstringMust match the project the session was created for.
sessionIdstringFrom createDocumentIngestSession.
titlestringOptional document title. Defaults to the upload's filename without extension.
getDocumentIngestJobRead the current status of an ingest job. Returns { status, stage, processedImages, totalImages, documentId, error?, lastHeartbeatAt }. Stages: pending → downloaded → extracted → draft_saved → images_processing → finalized → cleaned_up. Status: queued, running, succeeded, fail...1 params
Read the current status of an ingest job. Returns { status, stage, processedImages, totalImages, documentId, error?, lastHeartbeatAt }. Stages: pending → downloaded → extracted → draft_saved → images_processing → finalized → cleaned_up. Status: queued, running, succeeded, fail...
Parameters* required
jobIdstringlistImprovementsList improvements in a project. Supports filtering by status, type, priority, and query.16 params
List improvements in a project. Supports filtering by status, type, priority, and query.
Parameters* required
agentReadybooleanFilter by agent readiness.
categoryIdstringFilter by category ID.
complianceOnlybooleanOnly compliance-linked improvements.
fieldsarrayField projection. Valid fields: id, friendly_id, friendlyId, title, type, status, priority, source, category_id, categoryId, created_at, createdAt, updated_at, updatedAt, href.
frameworkKeystringFilter by framework (e.g. soc2, iso27001).
limitnumberMax results (1-100, default 50).
offsetnumberPagination offset.
prioritystringFilter: low, medium, high, critical.
projectIdstringquerystringSearch title, friendly_id, problem_statement.
scanRunIdstringFilter by compliance scan run.
sortAscendingbooleanSort ascending. Default: true.
sortFieldstringSort field. Default: position.
sourcestringFilter: agent_review, human_manual, doc_comment, feedback, incident, etc.
statusstringFilter: captured, triaging, shaped, approved, ready_for_agent, in_progress, ready_for_review, in_review, blocked, done, rejected, deferred.
typestringFilter: feature, bug, tech_debt, architecture_gap, documentation_gap, risk, enhancement, task. Tasks (is_task=true) always have type='task'.
getImprovementGet full details for an improvement item including evidence, activity log, compliance context, and the `checklist` array (each item: id, text, due_date, completed_at, plus server-stamped attribution). Returns versionTimestamp — pass it to updateImprovement for optimistic locki...1 params
Get full details for an improvement item including evidence, activity log, compliance context, and the `checklist` array (each item: id, text, due_date, completed_at, plus server-stamped attribution). Returns versionTimestamp — pass it to updateImprovement for optimistic locki...
Parameters* required
improvementIdstringcreateImprovementCreate an improvement item in a project. Requires projectId and title. Auto-assigns friendly ID.38 params
Create an improvement item in a project. Requires projectId and title. Auto-assigns friendly ID.
Parameters* required
acceptance_criteriaarrayAcceptance criteria — ordered list of pass/fail statements that define "done" for this item. Each row is `{ id, text }` with server-stamped `updated_at / updated_by / updated_by_credential_name`. R...
agent_briefstringagent_complexitystringlow, medium, high, very_high.
agent_confidencenumber0.00 to 1.00.
agent_missing_infoarrayagent_readybooleanagent_recommended_actionstringbusiness_impactstringcategory_idstringCategory ID.
checklistarrayTick-box checklist shown above acceptance_criteria. The full array REPLACES the stored list on update, and array order = display order — to edit, fetch via getTask/getImprovement, modify, and send...
constraintsarraydescriptionstringdesired_outcomestringend_datestringYYYY-MM-DD.
impacted_componentsarrayimpacted_diagramsarrayArray of {id, name}.
impacted_documentsarrayArray of {id, title}.
is_taskbooleanMark as task. Default: false. Prefer setting type='task' instead — is_task is kept in sync from the type enum by a DB trigger, and rows with type='task' get the TAS- friendly_id prefix while all ot...
linked_document_idsarrayDocument IDs to link. Titles resolved automatically.
non_goalsarray+18 more parameters. See the server's own documentation for the full schema.
updateImprovementUpdate an improvement (or a task — tasks share this row, but prefer the symmetric updateTask alias when working from getTask). Supports the full field set including `checklist` (tick-boxes with due dates + completion attribution) and `acceptance_criteria` (objects with per-row...50 params
Update an improvement (or a task — tasks share this row, but prefer the symmetric updateTask alias when working from getTask). Supports the full field set including `checklist` (tick-boxes with due dates + completion attribution) and `acceptance_criteria` (objects with per-row...
Parameters* required
acceptance_criteriaarrayAcceptance criteria — ordered list of pass/fail statements that define "done" for this item. Each row is `{ id, text }` with server-stamped `updated_at / updated_by / updated_by_credential_name`. R...
agent_briefstringagent_complexitystringagent_confidencenumberagent_missing_infoarrayagent_readybooleanagent_recommended_actionstringblocked_commentstringRequired when status=blocked.
business_impactstringcategory_idstringCategory ID. Null to unassign.
checklistarrayTick-box checklist shown above acceptance_criteria. The full array REPLACES the stored list on update, and array order = display order — to edit, fetch via getTask/getImprovement, modify, and send...
completion_commentstringRequired when status=done.
constraintsarraydescriptionstringdesired_outcomestringdocs_updatedbooleanend_datestringYYYY-MM-DD.
follow_up_neededbooleanimpacted_componentsarrayimpacted_diagramsarray+30 more parameters. See the server's own documentation for the full schema.
deleteImprovementDelete an improvement and all associated evidence and activity.1 params
Delete an improvement and all associated evidence and activity.
Parameters* required
improvementIdstringlistImprovementCategoriesList improvement categories for a project. Returns tree and flat list.1 params
List improvement categories for a project. Returns tree and flat list.
Parameters* required
projectIdstringcreateImprovementCategoryCreate an improvement category or sub-category. Max two levels.8 params
Create an improvement category or sub-category. Max two levels.
Parameters* required
colorstringColor code.
descriptionstringiconstringLucide icon name.
namestringparentIdstringParent category ID for sub-categories.
projectIdstringslugstringURL-friendly slug. Auto-generated if omitted.
sortOrdernumberSort order. Default: 0.
updateImprovementCategoryUpdate an improvement category. Cannot modify system categories.7 params
Update an improvement category. Cannot modify system categories.
Parameters* required
categoryIdstringcolorstringdescriptionstringiconstringnamestringslugstringsortOrdernumberdeleteImprovementCategoryDelete an improvement category. Cannot delete system categories.1 params
Delete an improvement category. Cannot delete system categories.
Parameters* required
categoryIdstringreorderImprovementCategoriesReorder improvement categories by setting sort_order values.1 params
Reorder improvement categories by setting sort_order values.
Parameters* required
itemsarrayArray of {categoryId, sortOrder}.
addImprovementEvidenceAdd evidence to an improvement. Types: document_section, diagram_node, incident_note, feedback, free_text.7 params
Add evidence to an improvement. Types: document_section, diagram_node, incident_note, feedback, free_text.
Parameters* required
evidenceTypestringEvidence type. Default: free_text.
improvementIdstringpositionnumberOrder in evidence list.
rawContentstringFull original text.
refIdstringReference ID (document, diagram, etc.).
refUrlstringReference URL.
summarystringSummary of the evidence.
addImprovementActivityAdd a comment or activity entry to an improvement.7 params
Add a comment or activity entry to an improvement.
Parameters* required
activityTypestringType: comment, agent_update, field_change. Default: comment.
commentstringComment text.
fieldNamestringFor field_change: field name.
improvementIdstringmetadataobjectAdditional context.
newValuestringFor field_change: new value.
oldValuestringFor field_change: previous value.
updateImprovementCommentUpdate a comment on an improvement. Requires the comment's updated_at as versionTimestamp.3 params
Update a comment on an improvement. Requires the comment's updated_at as versionTimestamp.
Parameters* required
activityIdstringActivity ID from getImprovement activity array.
commentstringNew comment text.
versionTimestampnumberComment's updated_at as Unix ms for optimistic locking.
deleteImprovementCommentDelete a comment from an improvement.1 params
Delete a comment from an improvement.
Parameters* required
activityIdstringActivity ID from getImprovement activity array.
searchImprovementsSearch improvements using hybrid text + semantic search. Returns ranked results.4 params
Search improvements using hybrid text + semantic search. Returns ranked results.
Parameters* required
limitnumberMax results (default 20, max 50).
projectIdstringLimit to a project.
querystringSearch query.
workspaceIdstringLimit to a workspace.
listPlansList plans in a project. Supports filtering by status, priority, and query.9 params
List plans in a project. Supports filtering by status, priority, and query.
Parameters* required
fieldsarrayField projection. Valid fields: id, friendly_id, friendlyId, title, description, status, priority, icon, color, start_date, startDate, end_date, endDate, created_at, createdAt, updated_at, updatedA...
limitnumberMax results (1-100, default 50).
offsetnumberPagination offset.
prioritystringFilter: low, medium, high, critical.
projectIdstringquerystringSearch title, friendly_id, description.
sortAscendingbooleanSort ascending. Default: false.
sortFieldstringSort field. Default: created_at.
statusstringFilter: draft, planning, active, on_hold, completed, cancelled.
getPlanGet full plan details including phases, items, and activity. Returns versionTimestamp — pass it to updatePlan for optimistic locking. Items include percent_complete for progress tracking.1 params
Get full plan details including phases, items, and activity. Returns versionTimestamp — pass it to updatePlan for optimistic locking. Items include percent_complete for progress tracking.
Parameters* required
planIdstringcreatePlanCreate a plan in a project. Requires projectId and title.11 params
Create a plan in a project. Requires projectId and title.
Parameters* required
colorstringColor code.
descriptionstringend_datestringYYYY-MM-DD.
iconstringLucide icon name.
linked_document_idsarrayDocument IDs to link.
linked_documentsarrayArray of {id, title}.
prioritystringPriority. Default: medium.
projectIdstringstart_datestringYYYY-MM-DD.
statusstringStatus. Default: draft.
titlestringupdatePlanUpdate a plan. Requires versionTimestamp from getPlan.13 params
Update a plan. Requires versionTimestamp from getPlan.
Parameters* required
colorstringdescriptionstringend_datestringYYYY-MM-DD.
iconstringlinked_document_idsarrayDocument IDs to link.
linked_documentsarraymetadataobjectplanIdstringprioritystringPriority: low, medium, high, critical.
start_datestringYYYY-MM-DD.
statusstringStatus: draft, planning, active, on_hold, completed, cancelled.
titlestringversionTimestampnumberVersion timestamp from getPlan() for optimistic locking.
deletePlanDelete a plan, all its phases, and all tasks/improvements within it. This is a destructive operation that cannot be undone.1 params
Delete a plan, all its phases, and all tasks/improvements within it. This is a destructive operation that cannot be undone.
Parameters* required
planIdstringlistPlanPhasesList phases for a plan ordered by position.1 params
List phases for a plan ordered by position.
Parameters* required
planIdstringgetPlanPhaseGet a plan phase by ID with full details. Returns versionTimestamp — pass it to updatePlanPhase for optimistic locking.1 params
Get a plan phase by ID with full details. Returns versionTimestamp — pass it to updatePlanPhase for optimistic locking.
Parameters* required
phaseIdstringcreatePlanPhaseCreate a phase in a plan. Position and wbs_code are auto-computed.10 params
Create a phase in a plan. Position and wbs_code are auto-computed.
Parameters* required
colorstringPhase color. Must be one of: #3b82f6 (Blue), #f59e0b (Amber), #8b5cf6 (Purple), #ec4899 (Pink), #06b6d4 (Cyan), #14b8a6 (Teal), #6366f1 (Indigo), #6b7280 (Gray). Red and green are reserved for bloc...one of
#3b82f6 · #f59e0b · #8b5cf6 · #ec4899 · #06b6d4 · #14b8a6descriptionstringend_datestringYYYY-MM-DD.
namestringplanIdstringpositionnumberPosition. Auto-computed if omitted.
prioritystringPriority. Default: medium.
start_datestringYYYY-MM-DD.
statusstringStatus: not_started, in_progress, completed, on_hold, cancelled. Default: not_started.
wbs_codestringWBS code. Auto-computed if omitted.
updatePlanPhaseUpdate a plan phase. Requires versionTimestamp from getPlanPhase (not getPlan).11 params
Update a plan phase. Requires versionTimestamp from getPlanPhase (not getPlan).
Parameters* required
colorstringPhase color. Must be one of: #3b82f6 (Blue), #f59e0b (Amber), #8b5cf6 (Purple), #ec4899 (Pink), #06b6d4 (Cyan), #14b8a6 (Teal), #6366f1 (Indigo), #6b7280 (Gray). Red and green are reserved for bloc...one of
#3b82f6 · #f59e0b · #8b5cf6 · #ec4899 · #06b6d4 · #14b8a6descriptionstringend_datestringnamestringphaseIdstringpositionnumberprioritystringPriority: low, medium, high, critical.
start_datestringstatusstringStatus: not_started, in_progress, completed, on_hold, cancelled.
versionTimestampnumberVersion timestamp from getPlanPhase() for optimistic locking.
wbs_codestringdeletePlanPhaseDelete a plan phase and all tasks/improvements within it. This is a destructive operation that cannot be undone.1 params
Delete a plan phase and all tasks/improvements within it. This is a destructive operation that cannot be undone.
Parameters* required
phaseIdstringreorderPlanPhasesReorder plan phases by setting position values. WBS codes are recalculated.1 params
Reorder plan phases by setting position values. WBS codes are recalculated.
Parameters* required
itemsarrayArray of {phaseId, position}.
addPlanActivityAdd a comment or activity entry to a plan.7 params
Add a comment or activity entry to a plan.
Parameters* required
activityTypestringType: comment, agent_update, field_change. Default: comment.
commentstringComment text.
fieldNamestringFor field_change: field name.
metadataobjectAdditional context.
newValuestringFor field_change: new value.
oldValuestringFor field_change: previous value.
planIdstringupdatePlanCommentUpdate a comment on a plan. Requires the comment's updated_at as versionTimestamp.3 params
Update a comment on a plan. Requires the comment's updated_at as versionTimestamp.
Parameters* required
activityIdstringActivity ID from getPlan activity array.
commentstringNew comment text.
versionTimestampnumberComment's updated_at as Unix ms for optimistic locking.
deletePlanCommentDelete a comment from a plan.1 params
Delete a comment from a plan.
Parameters* required
activityIdstringActivity ID from getPlan activity array.
createTaskCreate a task in a plan. Requires planId and title.17 params
Create a task in a plan. Requires planId and title.
Parameters* required
acceptance_criteriaarrayAcceptance criteria — ordered list of pass/fail statements that define "done" for this item. Each row is `{ id, text }` with server-stamped `updated_at / updated_by / updated_by_credential_name`. R...
checklistarrayTick-box checklist shown above acceptance_criteria. The full array REPLACES the stored list on update, and array order = display order — to edit, fetch via getTask/getImprovement, modify, and send...
descriptionstringend_datestringYYYY-MM-DD.
owner_idstringUser UUID to assign as owner. MUTUALLY EXCLUSIVE with owner_team_id. Use listAssignablePrincipals(projectId, kind='user') to look up valid UUIDs.
owner_team_idstringTeam UUID to assign as owner (assigns the whole team). MUTUALLY EXCLUSIVE with owner_id. Use listTeams or listAssignablePrincipals(kind='team') to look up valid UUIDs.
percent_completenumberProgress percentage (0-100). Null means not tracked.
phaseIdstringPhase to assign to.
planIdstringpositionnumberprioritystringPriority. Default: medium.
start_datestringYYYY-MM-DD.
statusstringInitial status. Default: captured.
target_datestringYYYY-MM-DD.
titlestringtypestringType. Default: task. Tasks created in plans are typed 'task' (friendly_id prefix TAS-). Override only if you want the row to appear as a non-task improvement (IMP- prefix).
wbs_codestringlistTasksList tasks in a plan. Supports filtering by status, priority, phaseId, and query.9 params
List tasks in a plan. Supports filtering by status, priority, phaseId, and query.
Parameters* required
limitnumberMax results (1-100, default 50).
offsetnumberPagination offset.
phaseIdstringFilter by phase.
planIdstringprioritystringFilter by priority.
querystringSearch title and friendly_id.
sortAscendingbooleanSort ascending. Default: true.
sortFieldstringSort field. Default: position.
statusstringFilter by status.
getTaskGet a task by ID with full details, evidence, activity, and the `checklist` array (each item: id, text, due_date, completed_at, plus server-stamped attribution). Returns versionTimestamp; pass it to updateTask to modify. Includes percent_complete for progress tracking.1 params
Get a task by ID with full details, evidence, activity, and the `checklist` array (each item: id, text, due_date, completed_at, plus server-stamped attribution). Returns versionTimestamp; pass it to updateTask to modify. Includes percent_complete for progress tracking.
Parameters* required
taskIdstringupdateTaskUpdate a task. Tasks share a row with improvements (`improvement_items` with `is_task=true`), so this is a thin alias over updateImprovement — every field on updateImprovement is supported, including `checklist`, `acceptance_criteria`, status transitions (blocked/rejected/done...48 params
Update a task. Tasks share a row with improvements (`improvement_items` with `is_task=true`), so this is a thin alias over updateImprovement — every field on updateImprovement is supported, including `checklist`, `acceptance_criteria`, status transitions (blocked/rejected/done...
Parameters* required
acceptance_criteriaarrayAcceptance criteria — ordered list of pass/fail statements that define "done" for this item. Each row is `{ id, text }` with server-stamped `updated_at / updated_by / updated_by_credential_name`. R...
agent_briefstringagent_complexitystringagent_confidencenumberagent_missing_infoarrayagent_readybooleanagent_recommended_actionstringblocked_commentstringRequired when status=blocked.
business_impactstringchecklistarrayTick-box checklist shown above acceptance_criteria. The full array REPLACES the stored list on update, and array order = display order — to edit, fetch via getTask/getImprovement, modify, and send...
completion_commentstringRequired when status=done.
constraintsarraydescriptionstringdesired_outcomestringdocs_updatedbooleanend_datestringYYYY-MM-DD.
follow_up_neededbooleanimpacted_componentsarrayimpacted_diagramsarrayimpacted_documentsarray+28 more parameters. See the server's own documentation for the full schema.
getPlanHierarchyGet the complete plan hierarchy (phases, tasks, improvements) in one call. Recommended first call for plan navigation.1 params
Get the complete plan hierarchy (phases, tasks, improvements) in one call. Recommended first call for plan navigation.
Parameters* required
planIdstringsetPlanItemParentSet or clear the WBS parent-child nesting of a task/improvement (outline hierarchy, no scheduling effect). Same plan and phase required. Max depth: 5.2 params
Set or clear the WBS parent-child nesting of a task/improvement (outline hierarchy, no scheduling effect). Same plan and phase required. Max depth: 5.
Parameters* required
itemIdstringItem ID to re-parent.
parentIdstringNew parent ID. Null to un-indent.
listTaskDependenciesList FS/SS/FF task-dependency edges in a plan (the Gantt arrows). Scope by planId, projectId, or itemId. `direction`: 'predecessors' | 'successors' | 'both' (default, only with itemId).4 params
List FS/SS/FF task-dependency edges in a plan (the Gantt arrows). Scope by planId, projectId, or itemId. `direction`: 'predecessors' | 'successors' | 'both' (default, only with itemId).
Parameters* required
directionstringOnly meaningful with itemId. Default: both.one of
predecessors · successors · bothitemIdstringLimit to one item's edges.
planIdstringLimit to one plan.
projectIdstringLimit to one project (all plans).
createTaskDependencyCreate an FS/SS/FF scheduling edge with lag/lead between two items in the same plan (rendered as a Gantt arrow). FS = Finish-to-Start, SS = Start-to-Start, FF = Finish-to-Finish. `lagDays`: positive = lag, negative = lead/overlap. Rejects self-loops, duplicate (pred+succ+type)...4 params
Create an FS/SS/FF scheduling edge with lag/lead between two items in the same plan (rendered as a Gantt arrow). FS = Finish-to-Start, SS = Start-to-Start, FF = Finish-to-Finish. `lagDays`: positive = lag, negative = lead/overlap. Rejects self-loops, duplicate (pred+succ+type)...
Parameters* required
dependencyTypestringFS = Finish-to-Start, SS = Start-to-Start, FF = Finish-to-Finish.one of
FS · SS · FFlagDaysintegerLag (positive) or lead (negative) in days. Default 0.
predecessorIdstringID of the upstream item (the driver).
successorIdstringID of the downstream item (the dependent).
updateTaskDependencyChange the type (FS/SS/FF) or lag/lead of an existing task-dependency. Doesn't move dates directly; flags the successor with `needs_dependency_review=true` and fills `suggested_start_date`/`suggested_end_date` if the change implies a different schedule.3 params
Change the type (FS/SS/FF) or lag/lead of an existing task-dependency. Doesn't move dates directly; flags the successor with `needs_dependency_review=true` and fills `suggested_start_date`/`suggested_end_date` if the change implies a different schedule.
Parameters* required
dependencyIdstringdependencyTypestringone of
FS · SS · FFlagDaysintegerPositive = lag, negative = lead.
deleteTaskDependencyRemove a task-dependency edge. Neither item's dates are changed.1 params
Remove a task-dependency edge. Neither item's dates are changed.
Parameters* required
dependencyIdstringacceptTaskDependencyReviewPer-item: apply a successor's `suggested_start_date`/`suggested_end_date` to its real dates and clear `needs_dependency_review`. For a whole-plan cascade use `applyTaskDependencyCascade`.1 params
Per-item: apply a successor's `suggested_start_date`/`suggested_end_date` to its real dates and clear `needs_dependency_review`. For a whole-plan cascade use `applyTaskDependencyCascade`.
Parameters* required
improvementIdstringThe successor item whose suggestion to apply.
dismissTaskDependencyReviewPer-item: clear `needs_dependency_review` without changing dates — keeps the edge, ignores the suggestion. Use when the successor should stay put despite the predecessor shifting.1 params
Per-item: clear `needs_dependency_review` without changing dates — keeps the edge, ignores the suggestion. Use when the successor should stay put despite the predecessor shifting.
Parameters* required
improvementIdstring
Stable Baseline — MCP Server
The simplest, most complete, end-to-end agent-managed company brain.
Website · Sign up free · Docs · Tool catalogue · llms.txt
How to use Stable Baseline
Pick the surface that matches how you work — every option talks to the same handlers, the same auth, the same data:
| Surface | What it's for | Install |
|---|---|---|
| MCP server | AI agents (Claude Code, Cursor, Windsurf, ChatGPT, Gemini, Smithery, …). Native protocol with prompts and resources. | Endpoint: api.stablebaseline.io/functions/v1/cloud-serve/mcp. See Quick start below. |
| REST API | Any HTTP client, Postman, OpenAPI codegen, Zapier-style integrators. Tool-RPC + idiomatic resource routes. | Live spec: /api/v1/openapi.json · Interactive docs: /api/v1/docs |
| TypeScript SDK | Node, browsers, Deno, Bun. Typed client.tools.<toolName>(...) surface. | npm i @stablebaseline/sdk — see packages/sdk-typescript |
CLI (sb) | Shells, scripts, CI/CD. sb tool call <name> --json '{...}'. | npm i -g @stablebaseline/cli — see packages/cli |
| Python SDK | Python apps, data work. Sync + async clients. | pip install stablebaseline — see packages/sdk-python |
196 tools across 18 categories. Same brain, same Knowledge Graph, same RBAC — every surface.
One workspace where humans and any MCP-compatible AI agent — Claude Code, Cursor, Windsurf, VS Code, Warp, OpenCode, Antigravity, OpenAI Codex, ChatGPT Developer Mode, Gemini CLI/Extensions, and more — co-author living documents (Markdown-native with a rich superset on top), 40+ visual diagrams (Mermaid, BPMN 2.0, D2, PlantUML, GraphViz, ELK architecture, sequence, state, ERD, Gantt, Excalidraw freehand), plans, timelines, tasks, improvements, and a self-learning Knowledge Graph that IS the company brain.
Lean, fast, secure, and affordable — flexible enough for one person organising a personal mind, through to small businesses, growing businesses, and enterprise.
196 MCP tools across 18 categories let an agent drive end-to-end: sign-up → billing → org/workspace/project → members → teams → permissions → brain scope → docs → diagrams → whiteboards → plans, all without a human touching the UI.
Endpoint
https://api.stablebaseline.io/functions/v1/cloud-serve/mcp
Transport: Streamable HTTP (with SSE fallback)
Auth: OAuth 2.1 with Dynamic Client Registration, or Bearer API key (sta_*)
Discovery manifest: https://stablebaseline.io/.well-known/mcp.json
Quick start
Mint an API key (skip OAuth)
- Sign up free — no credit card
- Go to Settings → MCP keys and click Generate
- Copy the
sta_...key
(Or skip this — every client below also supports interactive OAuth on first call.)
Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"stable-baseline": {
"url": "https://api.stablebaseline.io/functions/v1/cloud-serve/mcp",
"headers": {
"Authorization": "Bearer sta_YOUR_KEY"
}
}
}
}
Or use the Claude Desktop OAuth flow — set just url and Claude will prompt you to authorize on first call.
Claude Code
claude mcp add --transport http stable-baseline \
https://api.stablebaseline.io/functions/v1/cloud-serve/mcp \
--header "Authorization: Bearer sta_YOUR_KEY"
Or via OAuth:
claude mcp add --transport http stable-baseline \
https://api.stablebaseline.io/functions/v1/cloud-serve/mcp
Cursor
~/.cursor/mcp.json:
{
"mcpServers": {
"stable-baseline": {
"url": "https://api.stablebaseline.io/functions/v1/cloud-serve/mcp",
"headers": { "Authorization": "Bearer sta_YOUR_KEY" }
}
}
}
Windsurf
~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"stable-baseline": {
"serverUrl": "https://api.stablebaseline.io/functions/v1/cloud-serve/mcp",
"headers": { "Authorization": "Bearer sta_YOUR_KEY" }
}
}
}
VS Code (Copilot Chat)
.vscode/mcp.json (workspace) or user settings:
{
"servers": {
"stable-baseline": {
"type": "http",
"url": "https://api.stablebaseline.io/functions/v1/cloud-serve/mcp",
"headers": { "Authorization": "Bearer ${input:sta_key}" }
}
}
}
Other clients
Recipes for Warp, OpenCode, Antigravity, OpenAI Codex, ChatGPT Developer Mode, Gemini CLI/Extensions, and a generic recipe are at stablebaseline.io/docs/mcp/setup.
What you get
| Category | Sample tools | Docs |
|---|---|---|
| navigation | listOrganisations, getProjectHierarchy, searchTools | → |
| folders | createFolder, listFolders, setPlanItemParent | → |
| documents | createDocument, editDocument, findAndReplaceTextInDocument | → |
| diagrams | insertDiagramInDocument, listDiagramTypes, getCdmdLanguageGuide | → |
| whiteboards | createWhiteboard, addWhiteboardElements, designDeckInWhiteboard | → |
| images | createImageUploadSession, insertImageInDocument | → |
| data | createVegaDataUploadSession (CSV/JSON/TSV → Vega charts) | → |
| improvements | createImprovement, searchImprovements, addImprovementEvidence | → |
| plans | createPlan, createPlanPhase, previewTaskDependencyCascade | → |
| knowledge_graph | kg_search, kg_get_entity, kg_related_documents | → |
| organization | createOrganisation, createWorkspace, createProject | → |
| members | inviteMember, updateMemberRole, setMemberActive | → |
| teams | createTeam, grantTeamWorkspaceAccess | → |
| permissions | upsertResourcePermission, setResourcePermissionOverride | → |
| billing | previewSubscriptionChange, applySubscriptionChange, purchaseCreditPackage | → |
| kg_admin | setKgWorkspaceScope, triggerKgRebuild, previewKgRebuild | → |
| settings | getOrgSettings, updateOrgFeatureFlags, createBrandKit | → |
| signup | startSignup, pollSignupStatus | → |
Full live catalogue: stablebaseline.io/docs/mcp/tools
Highlights
- End-to-end agent-managed: agents drive sign-up → billing → org/workspace/project lifecycle → members → teams → permissions → Knowledge Graph scope. No human touching the UI.
- Living documents: AI-native rich-text editor (CDMD = Markdown + inline diagrams, data tables, media, version history, real-time multi-author edits).
- Visual diagram creation & editing: 40+ types — AI-generated, diagram-as-code, or freehand.
- Plans, timelines, tasks, improvements & bugs: Day/Week/Month/Quarter/Year zoom Gantt, drag-to-reschedule, dependency cascades.
- Self-learning Knowledge Graph (Enterprise): auto-built from every doc/plan/improvement; read by every connected agent. Stops hallucinations around gaps. Run one brain workspace-wide, one per department, or one per project — RBAC end-to-end.
- Compliance Readiness (Enterprise): scans against OWASP ASVS, NIST SSDF, CIS Controls, ISO 27001, SOC 2, TISAX. Readiness only — not legal advice, not an attestation.
- Bring-your-own-agent — no lock-in: any MCP-compatible client.
- Credit-cost preview ritual for every spending operation:
previewX→ confirm token →applyX.
Auth
| Method | When to use |
|---|---|
| OAuth 2.1 + Dynamic Client Registration | Default for desktop apps and IDE extensions. Smithery handles it automatically. |
Bearer API key (sta_...) | CI/CD, headless agents, server-to-server. Mint at app.stablebaseline.io/settings/mcp-setup. Project-scoped or global. |
OAuth endpoints:
authorize:https://api.stablebaseline.io/functions/v1/cloud-serve/oauth/authorizetoken:https://api.stablebaseline.io/functions/v1/cloud-serve/oauth/tokenregister(DCR):https://api.stablebaseline.io/functions/v1/cloud-serve/oauth/register- Scopes:
openid,profile,email,phone. These identify the signed-in user and do NOT decide what an agent may do: authorisation comes from the read/write/delete permissions per content type and the organisation capability toggles chosen on the consent screen. - Authoritative metadata (always prefer this over the list above):
https://api.stablebaseline.io/functions/v1/cloud-serve/.well-known/oauth-authorization-server
Discovery
| Surface | URL |
|---|---|
.well-known/mcp.json (manifest) | https://stablebaseline.io/.well-known/mcp.json |
| Official MCP Registry | https://registry.modelcontextprotocol.io/v0/servers?search=io.stablebaseline |
| Smithery | https://smithery.ai/servers/stablebaseline/sb-mcp |
llms.txt | https://stablebaseline.io/llms.txt |
robots.txt | https://stablebaseline.io/robots.txt |
sitemap.xml | https://stablebaseline.io/sitemap.xml |
security.txt | https://stablebaseline.io/.well-known/security.txt |
Pricing
- Free: 100 one-off credits, no credit card.
- Pro: A$79 / user / month, 500 credits / user / month.
- Enterprise: custom — Knowledge Graph, Compliance Readiness, audit logs, SSO. Contact.
Status
- 🟢 MCP Registry:
io.stablebaseline/sb—active,isLatest. Listed. - 🟢 Smithery: published with
configSchema(Quick Setup). 196 tools / 11 prompts / 8 resources discovered. - 🟢
.well-known/mcp.json: live, schema 2024-11-05. - 🟢 Endpoint:
api.stablebaseline.io/functions/v1/cloud-serve/mcp— accepts POST withmcp-protocol-version: 2025-06-18.
Issues & support
- Bug or feature request: open an issue here.
- Security report: see
.well-known/security.txt— RFC 9116 contact. - General support: https://stablebaseline.io/contact
License
This repository (README, llms-install.md, brand assets, and any documentation) is licensed under the MIT License — see LICENSE. You can copy, fork, and adapt these docs freely.
The Stable Baseline product itself — the SaaS application, the MCP server implementation, and the company brain Knowledge Graph — is proprietary, closed-source, and provided as a service at https://stablebaseline.io under the Stable Baseline Terms of Service.
Built by Orixian Solutions Pty Ltd, Sydney, Australia.
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Registryactive
TransportHTTP
AuthRequired
UpdatedMay 8, 2026
