Summary
This relay server sits between Claude and RunRelay's agent orchestration platform, giving you threaded AI conversations with human-in-the-loop approval gates. It connects over SSE to their hosted endpoint at mcp.runrelay.io, so there's no local setup. The travel capability discovery piece suggests it can expose dynamic tool sets based on context, though the specifics aren't in the source. You'd reach for this if you're building workflows where AI agents need to pause for human confirmation before taking actions, or if you want persistent conversation threads that survive beyond a single Claude session. Think approval workflows, audit trails, and multi-step tasks where oversight matters.
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.
9 tools
project.listList all Relay projects you have access to. Returns project IDs, names, slugs, and descriptions.1 params
List all Relay projects you have access to. Returns project IDs, names, slugs, and descriptions.
Parameters* required
limitnumberMaximum number of projects to return
project.get_briefFetch a project context brief — decisions, constraints, progress, and memory items formatted for an AI coding session.4 params
Fetch a project context brief — decisions, constraints, progress, and memory items formatted for an AI coding session.
Parameters* required
includearrayExtra sections to include in the brief
kindstringBrief kind: fresh_chat_bootstrap or quick_continuity
projectIdstringProject ID (uses token-scoped project if omitted)
targetProfileKeystringTarget profile key for formatting
project.get_stateGet full structured project state including overview, objectives, decisions, constraints, and tasks.1 params
Get full structured project state including overview, objectives, decisions, constraints, and tasks.
Parameters* required
projectIdstringProject ID (uses token-scoped project if omitted)
memory.searchSearch memory items by keyword or semantic query. Returns matching decisions, constraints, tasks, notes, and other memory items.5 params
Search memory items by keyword or semantic query. Returns matching decisions, constraints, tasks, notes, and other memory items.
Parameters* required
limitnumberMaximum number of results to return
projectIdstringProject ID (uses token-scoped project if omitted)
querystringSearch query to find relevant memory items
tagsarrayFilter by tags attached to memory items
typesarrayFilter by memory types: decision, constraint, task, note, artifact, requirement
memory.addAdd a memory item to the project. Use this to persist decisions, constraints, tasks, or notes discovered during the session.5 params
Add a memory item to the project. Use this to persist decisions, constraints, tasks, or notes discovered during the session.
Parameters* required
contentstringThe memory content to store
projectIdstringProject ID (uses token-scoped project if omitted)
tagsarrayTags for categorizing and searching
titlestringShort title for the memory item
typestringMemory type: decision, constraint, task, note, artifact, or requirement
context.saveSave a structured session summary with decisions, progress, next steps, and constraints. Call this at the end of a coding session.7 params
Save a structured session summary with decisions, progress, next steps, and constraints. Call this at the end of a coding session.
Parameters* required
constraintsarrayConstraints discovered during the session
decisionsarrayDecisions made during the session
nextStepsarrayTasks or next steps identified
notesarrayGeneral notes or observations
progressstringDescription of progress made
projectIdstringProject ID (uses token-scoped project if omitted)
summarystringHigh-level session summary
memory.manageUpdate, delete, or archive an existing memory item by its ID.5 params
Update, delete, or archive an existing memory item by its ID.
Parameters* required
actionstringAction to perform: update, delete, or archive
contentstringNew content (for update action)
memoryIdstringThe ID of the memory item to manage
tagsarrayNew tags (for update action)
titlestringNew title (for update action)
project.updateUpdate a project's name or description.3 params
Update a project's name or description.
Parameters* required
descriptionstringNew project description
namestringNew project name
projectIdstringProject ID (uses token-scoped project if omitted)
memory.recallSearch memory and retrieve project state in one call. Use before making decisions to check for existing constraints and context.2 params
Search memory and retrieve project state in one call. Use before making decisions to check for existing constraints and context.
Parameters* required
projectIdstringProject ID (uses token-scoped project if omitted)
querystringWhat to search for in project memory
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 →
