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.
Public tool metadata for what this MCP can expose to an agent.
project.listList all Relay projects you have access to. Returns project IDs, names, slugs, and descriptions.1 paramsList all Relay projects you have access to. Returns project IDs, names, slugs, and descriptions.
limitnumberproject.get_briefFetch a project context brief — decisions, constraints, progress, and memory items formatted for an AI coding session.4 paramsFetch a project context brief — decisions, constraints, progress, and memory items formatted for an AI coding session.
kindstringincludearrayprojectIdstringtargetProfileKeystringproject.get_stateGet full structured project state including overview, objectives, decisions, constraints, and tasks.1 paramsGet full structured project state including overview, objectives, decisions, constraints, and tasks.
projectIdstringmemory.searchSearch memory items by keyword or semantic query. Returns matching decisions, constraints, tasks, notes, and other memory items.5 paramsSearch memory items by keyword or semantic query. Returns matching decisions, constraints, tasks, notes, and other memory items.
tagsarraylimitnumberquerystringtypesarrayprojectIdstringmemory.addAdd a memory item to the project. Use this to persist decisions, constraints, tasks, or notes discovered during the session.5 paramsAdd a memory item to the project. Use this to persist decisions, constraints, tasks, or notes discovered during the session.
tagsarraytypestringtitlestringcontentstringprojectIdstringcontext.saveSave a structured session summary with decisions, progress, next steps, and constraints. Call this at the end of a coding session.7 paramsSave a structured session summary with decisions, progress, next steps, and constraints. Call this at the end of a coding session.
notesarraysummarystringprogressstringdecisionsarraynextStepsarrayprojectIdstringconstraintsarraymemory.manageUpdate, delete, or archive an existing memory item by its ID.5 paramsUpdate, delete, or archive an existing memory item by its ID.
tagsarraytitlestringactionstringcontentstringmemoryIdstringproject.updateUpdate a project's name or description.3 paramsUpdate a project's name or description.
namestringprojectIdstringdescriptionstringmemory.recallSearch memory and retrieve project state in one call. Use before making decisions to check for existing constraints and context.2 paramsSearch memory and retrieve project state in one call. Use before making decisions to check for existing constraints and context.
querystringprojectIdstringio.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage
io.github.mikerawsonnz/llm-orchestration-agent
io.github.mikerawsonnz/authenticated-llm-agent
labforgedev/copilot-memory-mcp
csoai-org/agent-prompt-injection-firewall-mcp
io.github.mikerawsonnz/authenticated-multi-llm-agent