company-brain-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@company-brain-mcpWhat are the key facts and health signals for account 'GlobalTech'?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
company-brain-mcp
MCP server exposing the Company Brain (Supabase GraphRAG knowledge store) to AI agents.
Runs three transports simultaneously:
Streamable HTTP (
POST /mcp) — Claude web (claude.ai) and Claude Code HTTP entriesLegacy SSE (
GET /sse+POST /messages) — n8nmcpClientTool(v2.15)stdio (
dist/index.js) — local Claude Code via.mcp.json
Tools (16)
Account-centric:
get_account_summarylist_account_meetingsget_account_factsget_account_health_signalsget_account_context_graphfind_accounts_by_tagfind_similar_accountsfind_similar_accounts_by_description
Retrieval / graph:
search_meeting_chunks(hybrid HNSW + FTS + tag)search_peopleget_meeting_transcriptget_person_meetingsget_org_hierarchyquery_tag_trendssearch_product_docssearch_call_log(RingCentral calls by phone/person/direction)
Related MCP server: Supabase MCP Server
Setup
npm install
npm run buildEnvironment
Create /etc/brain-mcp/env (chmod 600) or an .env:
SUPABASE_URL=https://<project>.supabase.co
SUPABASE_SERVICE_ROLE_KEY=<service role key>
GEMINI_API_KEY=<gemini key>
MCP_API_KEY=<openssl rand -hex 32>
MCP_PORT=3100
ALLOWED_ORIGINS=https://claude.ai,https://<n8n-host>
GOFLEET_ORG_ID=<org uuid>
brainmust be listed in Supabase Dashboard → Settings → API → Exposed Schemas.
Run
npm run start # stdio (local Claude Code)
npm run start:http # HTTP + SSE server on MCP_PORTProduction (PM2):
pm2 start ecosystem.config.cjs
pm2 save && pm2 startupThis server cannot be deployed
Maintenance
Related MCP Connectors
Company brain for AI agents — temporal knowledge graph search, exploration, and durable memory.
Your company's brain for AI agents. Cited, permission-aware knowledge across every system.
Shared memory for AI agents, as a graph in your own Postgres. Writes never call an LLM.
- EvermuseOAuthcom.evermuse
Search your customer interviews, calls, feedback, competitor intel and roadmap from any AI agent.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceIntegrates CRM data with AI agents to manage leads, track pipeline statistics, and search price catalogs via Supabase. It enables automated lead creation, stage updates, and history tracking through natural language commands.-
- FlicenseNot gradedqualityDmaintenanceEnables AI agents to access and manage Supabase projects through the Model Context Protocol, supporting database operations, edge functions, storage, and documentation search. It provides a complete toolset for SQL execution, migration management, and real-time project debugging.-
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to query a personal knowledge vault with hybrid search, entity relationships, user highlights, and vault statistics over a Supabase/Postgres schema.MIT
- AlicenseAqualityDmaintenanceConnects AI agents to AgentData's company intelligence platform, enabling natural language queries for structured company data like tech stacks, emails, people, and signals.68 npmMIT