CCM
/MCP
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Claude Code Marketplaces

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Skill index
  • MCP index
  • Marketplace index
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by mertbuilds.com

Independent project, not affiliated with Anthropic
maindexapp avatar

Maindex Expert Memory Service

maindexapp/maindex
14 toolsauthHTTPregistry active
Summary

If you're building agents that need to remember things across sessions and tools, this gives you a full CRUD layer over Maindex's memory infrastructure. You get collections, typed memories with metadata, links between facts, semantic search, and bulk operations all through MCP. It connects to their hosted graph at expert.maindex.io, which means your agent's memories sync across Claude, Cursor, ChatGPT, or whatever else you hook up via their OAuth flow. Useful when you want structured, traceable memory instead of dumping context into a vector DB or rewriting the same facts into every chat. The Expert tier exposes the full API, including collection locking and revision history.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
inference shell
inference shell
create and run specialised agents in minutes
build now →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
inference shell
inference shell
create and run specialised agents in minutes
build now →

Tools

Public tool metadata for what this MCP can expose to an agent.

14 tools
collection_unlockUnlock locked memory collections using a passphrase. When collections are locked, their contents are invisible. Provide the passphrase (e.g. 'bright-coral-drift') to unlock them for this session. Mutates session unlock state. Idempotent.1 params

Unlock locked memory collections using a passphrase. When collections are locked, their contents are invisible. Provide the passphrase (e.g. 'bright-coral-drift') to unlock them for this session. Mutates session unlock state. Idempotent.

Parameters* required
passphrasestring
The unlock passphrase (e.g. 'bright-coral-drift')
memory_keepCreate a new memory. Mutates. Not idempotent — calling twice creates two distinct memories. Returns the created memory with id (UUID) and shortId (e.g. mem-1a). Tip: include conversation identifiers in `conversations` to group related memories. CONTENT POLICY: NEVER store pass...18 params

Create a new memory. Mutates. Not idempotent — calling twice creates two distinct memories. Returns the created memory with id (UUID) and shortId (e.g. mem-1a). Tip: include conversation identifiers in `conversations` to group related memories. CONTENT POLICY: NEVER store pass...

Parameters* required
bodystring
Supporting detail. Omit if the headline is self-contained.default:
canon_statusstring
Canonicality: draft, proposed, accepted, deprecated, alternative, metaone of draft · proposed · accepted · deprecated · alternative · metadefault: draft
collectionsarray
Collection slugs or IDs to add this memory to
confidenceinteger
Confidence as an integer percentage from 0 to 100 (e.g. 85 means 85% confident)
conversationsarray
Conversation contexts this memory belongs to. If you are acting within a named conversation, chat session, or task context, pass its identifier here to enable cross-memory grouping.
headlinestring
Title or core assertion of the memory (required)
human_collaboratorobject
Human collaborator context (name, email, timezone, etc.)
kindstring
Memory type: note, fact, idea, summary, artifact, task_context, constraint, question, decisionone of note · fact · idea · summary · artifact · task_contextdefault: note
linksarray
Typed links to create from this memory
metadataobject
Arbitrary key-value metadata stored as JSON. Opaque to search and ranking.
parent_memory_idvalue
Parent memory ID -- creates a belongs_to link
related_memory_idsarray
Related memory IDs -- creates related_to links
signerobject
Agent identity -- who wrote this. Required fields: agent_id, run_id.
sourceobject
Source metadata: origin platform, URI, author, capture time
source_memory_idsarray
IDs of memories this was derived from (provenance tracking)
stale_atstring
ISO 8601 datetime when this memory becomes stale
tagsarray
Tags for categorization. Use facet:name format for structured tags (e.g. domain:cosmology, project:brox).
verification_statusstring
Verification status: unverified, verified, disputed, supersededone of unverified · verified · disputed · supersededdefault: unverified
memory_updateUpdate an existing memory by creating a new revision (full history is preserved). Supports changing kind, canon_status, confidence, and verification_status in-place. Mutates. Tags and conversations are additive. Retryable — duplicate calls create extra revisions but do not cor...16 params

Update an existing memory by creating a new revision (full history is preserved). Supports changing kind, canon_status, confidence, and verification_status in-place. Mutates. Tags and conversations are additive. Retryable — duplicate calls create extra revisions but do not cor...

Parameters* required
bodystring
New body text
canon_statusstring
Set canon status: draft, proposed, accepted, deprecated, alternative, metaone of draft · proposed · accepted · deprecated · alternative · meta
confidenceinteger
Confidence as an integer percentage from 0 to 100 (e.g. 85 means 85% confident)
conversationsarray
Conversation contexts to add (additive)
headlinestring
New headline text
human_collaboratorobject
Human collaborator context (name, email, timezone, etc.)
kindstring
Change the memory kindone of note · fact · idea · summary · artifact · task_context
memory_idstring
ID of the memory to update
metadataobject
Arbitrary key-value metadata stored on the revision (not merged into the memory). Opaque to search and ranking.
modestring
How to apply the updateone of body_append · body_replace · headline_replace · headline_and_body_replace · revision_only
replacesvalue
Mark this memory as replacing another
signerobject
Agent identity -- who wrote this. Required fields: agent_id, run_id.
source_memory_idsarray
IDs of memories this revision was derived from
superseded_bystring
Mark this memory as superseded by another
tagsarray
Tags to add (additive)
verification_statusstring
Verification status: unverified, verified, disputed, supersededone of unverified · verified · disputed · superseded
memory_forgetSoft-delete a memory (sets status to 'deleted'; restorable). Mutates. Idempotent — safe to retry. Returns the deletion result with the memory's id and shortId.2 params

Soft-delete a memory (sets status to 'deleted'; restorable). Mutates. Idempotent — safe to retry. Returns the deletion result with the memory's id and shortId.

Parameters* required
memory_idstring
ID of the memory to delete
signerobject
Agent identity -- who wrote this. Required fields: agent_id, run_id.
memory_recallRetrieve a single memory by ID (UUID or short_id like mem-1a). Read-only. Returns the memory object, or null if not found.4 params

Retrieve a single memory by ID (UUID or short_id like mem-1a). Read-only. Returns the memory object, or null if not found.

Parameters* required
include_deletedboolean
Include soft-deleted memoriesdefault: false
include_linksboolean
Include linked memoriesdefault: true
include_revisionsboolean
Include full revision historydefault: false
memory_idstring
ID of the memory to retrieve
memory_listList memories with filters (tags, kind, canon_status, collection, session, confidence range, tag facets). Read-only. Returns { items, total }.19 params

List memories with filters (tags, kind, canon_status, collection, session, confidence range, tag facets). Read-only. Returns { items, total }.

Parameters* required
canon_statusstring
Filter by canon statusone of draft · proposed · accepted · deprecated · alternative · meta
collectionstring
Filter by collection slug or ID
conversation_keystring
Filter by conversation key
conversation_typestring
Filter by conversation type
kindstring
Filter by memory kindone of note · fact · idea · summary · artifact · task_context
limitinteger
Maximum number of results to return
max_confidenceinteger
Maximum confidence as an integer percentage from 0 to 100
min_confidenceinteger
Minimum confidence as an integer percentage from 0 to 100
offsetinteger
Number of results to skip for paginationdefault: 0
orderstring
Sort order: ascending or descendingone of asc · descdefault: desc
session_idstring
Filter by interaction session
sortstring
Sort fieldone of updated_at · created_at · headline · stale_atdefault: updated_at
statusstring
Filter by status: active, stale, deletedone of active · stale · deleted
tag_facetstring
Filter by tag facet: domain, project, function, status, topicone of domain · project · function · status · topic
tag_modestring
Tag matching mode: all (AND) or any (OR)one of all · anydefault: all
tagsarray
Filter by tags (AND semantics by default)
updated_afterstring
Only memories updated after this ISO 8601 datetime
updated_beforestring
Only memories updated before this ISO 8601 datetime
verification_statusstring
Filter by verification statusone of unverified · verified · disputed · superseded
memory_searchFull-text and semantic search across memories. Multi-tier retrieval: exact match, relaxed OR fallback with synonym expansion, fuzzy trigram, and optional semantic/hybrid search. Read-only. Returns { items, total, search_mode, retrieval_sources, degraded_components }.23 params

Full-text and semantic search across memories. Multi-tier retrieval: exact match, relaxed OR fallback with synonym expansion, fuzzy trigram, and optional semantic/hybrid search. Read-only. Returns { items, total, search_mode, retrieval_sources, degraded_components }.

Parameters* required
allow_relaxedboolean
Allow AND-to-OR relaxed fallback when strict search returns nothingdefault: true
canon_statusstring
Filter by canon statusone of draft · proposed · accepted · deprecated · alternative · meta
collectionstring
Filter by collection slug or ID
include_graph_neighborsboolean
Include graph-linked neighbor memories in resultsdefault: false
include_match_contextboolean
Include highlighted match context snippetsdefault: true
include_score_breakdownboolean
Include per-signal score breakdown for each resultdefault: false
kindstring
Filter by memory kindone of note · fact · idea · summary · artifact · task_context
limitinteger
Maximum number of results to return
max_confidenceinteger
Maximum confidence as an integer percentage from 0 to 100
min_confidenceinteger
Minimum confidence as an integer percentage from 0 to 100
offsetinteger
Number of results to skip for paginationdefault: 0
orderstring
Sort order: ascending or descendingone of asc · descdefault: desc
qstring
Search query
search_fieldsarray
Restrict search to specific fields
search_strategystring
Search strategy: auto (best available), lexical (text only), semantic (vector only), hybrid (both with fusion)one of auto · lexical · semantic · hybriddefault: auto
session_idstring
Filter by interaction session
sortstring
Sort fieldone of relevance · updated_at · created_at · confidencedefault: relevance
stale_penaltynumber
How much to penalize stale memories in ranking. 0 = no penalty, 1 = fully suppress. Default 0.5.default: 0.5
statusstring
Filter by status: active, stale, deletedone of active · stale · deleted
tag_facetstring
Filter by tag facetone of domain · project · function · status · topic

+3 more parameters. See the server's own documentation for the full schema.

memory_associateCreate typed links between memories (inverse links auto-created for known types). Mutates. Not idempotent — calling twice creates duplicate links. Returns the created link objects with id and shortId. Common relation types: belongs_to, supports, depends_on, contradicts, altern...3 params

Create typed links between memories (inverse links auto-created for known types). Mutates. Not idempotent — calling twice creates duplicate links. Returns the created link objects with id and shortId. Common relation types: belongs_to, supports, depends_on, contradicts, altern...

Parameters* required
from_memory_idstring
Source memory ID
signerobject
Agent identity -- who wrote this. Required fields: agent_id, run_id.
targetsarray
Target memories to link to
memory_get_relatedDiscover related memories via links, shared tags, or collection membership. Read-only. At least one of memory_id, tags, or collection is required. Returns an array of related memory objects.5 params

Discover related memories via links, shared tags, or collection membership. Read-only. At least one of memory_id, tags, or collection is required. Returns an array of related memory objects.

Parameters* required
collectionstring
Filter by collection slug or ID
limitinteger
Maximum number of related memories to returndefault: 20
memory_idstring
ID of the memory to find relations for
relation_typestring
Filter by relation type (e.g. supports, contradicts, depends_on)
tagsarray
Find memories sharing these tags
collection_manageCreate, update, delete collections, or manage their members. Actions 'list' and 'get' are read-only; all others mutate. 'create' is not idempotent; 'delete' is idempotent. The 'id' param is required for update/delete/add_members/remove_members/get. Returns the collection objec...11 params

Create, update, delete collections, or manage their members. Actions 'list' and 'get' are read-only; all others mutate. 'create' is not idempotent; 'delete' is idempotent. The 'id' param is required for update/delete/add_members/remove_members/get. Returns the collection objec...

Parameters* required
actionstring
Action to performone of create · update · delete · add_members · remove_members · list
colorstring
Hex color for UI display
descriptionstring
Collection description
iconstring
Emoji or icon identifier
idstring
Collection ID, short_id, or slug (required for update/delete/add_members/remove_members/get)
memory_idsarray
Memory IDs (for add_members/remove_members)
metadataobject
Arbitrary key-value metadata for the collection. Opaque to search and ranking.
namestring
Collection name (for create/update)
parent_idstring
Parent collection ID for nesting
slugstring
URL-friendly slug (auto-generated from name if omitted)
summary_headlinestring
Short summary for browsing
memory_supersedeReplace an existing memory with a new one. Creates the replacement, marks the old memory as deprecated (superseded_by → new), and creates a supersedes link. Tags from the old memory are automatically inherited by the new one (merged with any caller-provided tags). Mutates. Not...10 params

Replace an existing memory with a new one. Creates the replacement, marks the old memory as deprecated (superseded_by → new), and creates a supersedes link. Tags from the old memory are automatically inherited by the new one (merged with any caller-provided tags). Mutates. Not...

Parameters* required
bodystring
Body text of the new replacement memorydefault:
canon_statusstring
Canon status for the replacement (defaults to accepted)one of draft · proposed · accepted · deprecated · alternative · metadefault: accepted
collectionsarray
Collection slugs or IDs for the replacement
headlinestring
Headline of the new replacement memory
kindstring
Memory type for the replacementone of note · fact · idea · summary · artifact · task_contextdefault: note
metadataobject
Arbitrary key-value metadata for the replacement
old_memory_idstring
ID of the memory being superseded
signerobject
Agent identity -- who wrote this. Required fields: agent_id, run_id.
sourceobject
Source metadata for the replacement memory
tagsarray
Tags for the replacement memory (merged with inherited tags from the old memory)
memory_bulk_keepCreate multiple memories in one call (max 100) with shared defaults. Tags and collections are merged per-item. Mutates. Not idempotent — calling twice creates duplicates. Auto-links batch members with mentioned_with links unless auto_link is false. Returns { created, memories...3 params

Create multiple memories in one call (max 100) with shared defaults. Tags and collections are merged per-item. Mutates. Not idempotent — calling twice creates duplicates. Auto-links batch members with mentioned_with links unless auto_link is false. Returns { created, memories...

Parameters* required
auto_linkboolean
Auto-create mentioned_with links between batch membersdefault: true
defaultsobject
Shared defaults applied to all memories in the batch
memoriesarray
Array of memories to create (1-100)
memory_bulk_updateBatch update multiple memories (max 100). Supports add/remove tags, set kind, set canon_status, set verification_status, add/remove collections, merge metadata, add links, forget (soft-delete). Does NOT support headline/body replacement. Mutates. Idempotent for set_* and tag o...3 params

Batch update multiple memories (max 100). Supports add/remove tags, set kind, set canon_status, set verification_status, add/remove collections, merge metadata, add links, forget (soft-delete). Does NOT support headline/body replacement. Mutates. Idempotent for set_* and tag o...

Parameters* required
memory_idsarray
Memory IDs to update
operationsobject
Operations to apply to all specified memories
signerobject
Agent identity -- who wrote this. Required fields: agent_id, run_id.
system_report_bugReport a bug to the Maindex maintainers. Provide a clear title, description, severity, and category. Include reproduction steps, error messages, and context when available. Do not include sensitive information. Reports are not public and are delivered to the team's internal bu...14 params

Report a bug to the Maindex maintainers. Provide a clear title, description, severity, and category. Include reproduction steps, error messages, and context when available. Do not include sensitive information. Reports are not public and are delivered to the team's internal bu...

Parameters* required
action_calledstring
MCP tool or API action that triggered the bug
actual_behaviorstring
What actually happened
agent_idstring
Identifier of the reporting agent
categorystring
Bug category: data_integrity, api_error, performance, auth, mcp_protocol, search, ui, otherone of data_integrity · api_error · performance · auth · mcp_protocol · search
descriptionstring
Detailed description of the bug
environmentstring
Environment: development, staging, productionone of development · staging · production
error_messagestring
Raw error message or stack trace
expected_behaviorstring
What should have happened
hostnamestring
Hostname of the reporting machine
metadataobject
Arbitrary key-value context
session_idstring
MCP session ID
severitystring
Bug severity: critical, high, medium, lowone of critical · high · medium · low
steps_to_reproducestring
Step-by-step reproduction instructions
titlestring
Short bug title
Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
inference shell
inference shell
create and run specialised agents in minutes
build now →
Categories
Search & Web Crawling
Registryactive
TransportHTTP
AuthRequired
UpdatedMay 3, 2026
View on GitHub

More from maindexapp

  • Maindex Smart Memory Service

Related Search & Web Crawling MCP Servers

View all →
mcpcentral-io avatar
Jsoncanvas

io.mcpcentral/jsoncanvas

Create, validate, edit, export (markdown/svg/png/mermaid), and search JSON Canvas files.
io.qt.qt-docs-mcp avatar
Qt Documentation

io.qt.qt-docs-mcp/qt-documentation

Search Qt 6 API and product docs (Qt Core, Qt Quick, Qt Creator, Boot to Qt, MCUs).
scispot-repo avatar
Mcp

io.scispot/mcp

Turn any LLM into your lab assistant: search samples, track experiments, analyze data with AI.
searchapi avatar
Mcp

io.searchapi/mcp

Give AI assistants access to real-time search data through SearchApi.
io.speedvault avatar
Mcp

io.speedvault/mcp

Run web performance audits, get code-level fixes, crawl for SEO, and read real-user Core Web Vitals.
io.studiomeyer avatar
StudioMeyer Memory

io.studiomeyer/memory

AI memory with 56 tools. Knowledge Graph, semantic search, OAuth 2.1 + Magic Link. Free tier.