45
/ 100
1 month ago
npm

thegoodguysla/myco-brain

Self-hosted memory layer for AI agents — MCP server backed by Postgres + pgvector + knowledge graph

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find.

Install from

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings
🚨
Secret credentials may flow to a network call
1 flow detected: ELEVENLABS_API_KEY. We can’t prove the destination matches the brand the credential belongs to.
🔐
You'll be asked for 10 credentials: ANTHROPIC_API_KEY, BRAIN_ANTHROPIC_API_KEY, BRAIN_API_KEY, BRAIN_OPENAI_API_KEY, BRAIN_REQUIRE_API_KEY_SECRET, BRAIN_SERVICE_ROLE_KEY, COHERE_API_KEY, ELEVENLABS_API_KEY, GITHUB_TOKEN, OPENAI_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// required environment variables
This server reads these from process.env. You'll be asked to provide them before it can run.
🔐 secretANTHROPIC_API_KEY
configBRAIN_AGENT_IDfrom key Agent identity for service-role auth; derived from BRAIN_API_KEY otherwise.
🔐 secretBRAIN_ANTHROPIC_API_KEYKnowledge graph needs an extractor [Ollama locally](#build-the-knowledge-graph--locally-no-api-keys) (keyless) or (most accurate)
🔐 secretBRAIN_API_KEYenv =brain_00000000-0000-0000-0000-000000000001_00000000-0000-0000-0000-0000000000a1_localdev \
configBRAIN_EMBED_PROVIDERSemantic search needs embeddings =ollama (local, keyless)
configBRAIN_EVAL_BAR
configBRAIN_EVAL_MODEL
configBRAIN_EXTRACTION_BATCH_SIZE
configBRAIN_EXTRACTION_FAKE
configBRAIN_EXTRACTION_LEASE_MSTuning thresholds (BRAIN_SCHEMA_PROMOTE_MIN_SEEN, , BRAIN_FUNCTIONAL_PREDICATES, …) live in [.env.example](./.env.example).
configBRAIN_EXTRACTION_MAX_ATTEMPTS
configBRAIN_EXTRACTION_MAX_TEXT_CHARS
configBRAIN_EXTRACTION_MODEL
configBRAIN_EXTRACTION_POLL_MS
configBRAIN_EXTRACTION_PROVIDERforce a choice with =ollamaanthropic.
configBRAIN_FUNCTIONAL_PREDICATESTuning thresholds (BRAIN_SCHEMA_PROMOTE_MIN_SEEN, BRAIN_EXTRACTION_LEASE_MS, , …) live in [.env.example](./.env.example).
configBRAIN_HEALTH_PORT8080 Health-check port.
configBRAIN_MODE
configBRAIN_OLLAMA_BASE_URLecho "=http://host.docker.internal:11434" >> .env
configBRAIN_OLLAMA_EMBED_MODELnomic-embed-text Local embedding model (no key, nothing leaves your machine).
configBRAIN_OLLAMA_MODELllama3.2:3b Local extraction model.
configBRAIN_OLLAMA_TIMEOUT_MS
🔐 secretBRAIN_OPENAI_API_KEYUse OpenAI embeddings instead of local.
🔐 secretBRAIN_REQUIRE_API_KEY_SECRETacts as a bearer token; set =1 to require a
configBRAIN_REQUIRE_HUMAN_REVIEWhuman review of every fact (=1).
configBRAIN_REST_HOSTBinding: loopback by default — set =0.0.0.0 behind your own
configBRAIN_REST_PORT8787 Read-only REST port.
configBRAIN_SCHEMA_AUTO_PROMOTE(=1), counted per document, not per mention, so two
configBRAIN_SCHEMA_PROMOTE_MIN_CONFIDENCE
configBRAIN_SCHEMA_PROMOTE_MIN_SEENTuning thresholds (, BRAIN_EXTRACTION_LEASE_MS, BRAIN_FUNCTIONAL_PREDICATES, …) live in [.env.example](./.env.example).
configBRAIN_SCHEMA_PROPOSAL_MIN_CONFIDENCE
🔐 secretBRAIN_SERVICE_ROLE_KEYmust equal , not merely look like one). Single-tenant
configBRAIN_TRUST_REQUEST_IDENTITYsummary><strong>Advanced — multi-tenant gateways: who is the caller? (<code></code>)</strong></summary>
configBRAIN_WATCH_DIRwith (needs unzip on your PATH).
configBRAIN_WORKSPACE_ID"": "00000000-0000-0000-0000-000000000001",
🔐 secretCOHERE_API_KEY
configDATABASE_SSL
configDATABASE_URLenv =postgresql://brain:brain@localhost:5432/brain \
🔐 secretELEVENLABS_API_KEY
configELEVENLABS_VOICE_ID
🔐 secretGITHUB_TOKEN"show my Myco memory stats". Set for private repos.
configHOST
configPORT
configSUPABASE_DB_URL
configLONGMEMEVAL_ALLOW_SYNTHETIC
configPAPERCLIP_AGENT_ID
🔐 secretOPENAI_API_KEYsk-... DATABASE_URL=postgresql://brain:brain@localhost:5432/brain \
configLONGMEMEVAL_QA_MODEL
configLONGMEMEVAL_JUDGE_MODEL
// full audit trail
The full breakdown of what we checked, the deductions that landed, the network hosts, the dependency advisories, and concrete fix guidance is available to verified publishers.
// improvement guidance — verified publishers only
We have 1 concrete improvement we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Score](https://m8ven.ai/badge/mcp/mycobrain-mcp-server-1bwzj2)](https://m8ven.ai/mcp/mycobrain-mcp-server-1bwzj2)
commit: d55c4f2f4c6fe3213adf5345d624c20c4c3d4866
code hash: 5073f31040f47efafebc4ce044bdb52745def86d19fbbd40cf7acce46d2be3a8
verified: 7/1/2026, 10:01:18 AM
view raw JSON →