brain-v42
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LOG_LEVEL | No | Log granularity (e.g. INFO, DEBUG) | INFO |
| POSTGRES_URL | Yes | PostgreSQL connection string (SQLAlchemy async URL) | |
| RERANKER_URL | No | URL of the reranker endpoint | http://localhost:8003 |
| GRAPH_ENABLED | No | Enable the relationship graph (Neo4j) | false |
| MCP_HTTP_TOKEEN | No | Bearer token for MCP HTTP endpoint (stored in private file) | |
| BRAIN_MCP_PROFILE | No | MCP tool catalog profile: 'compact' (default) or 'native' | compact |
| EMBEDDING_DIMENSION | No | Vector dimension for embeddings (<=2000, pgvector HNSW ceiling) | 1536 |
| BRAIN_RERANK_API_KEY | No | API key for external reranker service (stored in private file) | |
| BRAIN_RERANK_BACKEND | No | Reranker backend: 'shim' (default) or 'cohere' | shim |
| BRAIN_EMBEDDING_MODEL | No | Model name sent by the openai backend (e.g. 'qodo') | |
| EMBEDDING_SERVICE_URL | No | URL of the local unified embedding endpoint | http://localhost:8003 |
| MCP_HTTP_DREAM_TOKEENS | No | Bearer tokens for dream-mode HTTP endpoint (stored in private file) | |
| BRAIN_EMBEDDING_API_KEY | No | API key for external embedding service (stored in private file) | |
| BRAIN_EMBEDDING_BACKEND | No | Backend for embeddings: 'shim' (default) or 'openai' | shim |
| GRAPH_LEDGER_WRITE_ENABLED | No | Enable writes to the graph ledger | false |
| BRAIN_EMBEDDING_QUERY_PREFIX | No | Query prefix for asymmetric embedding models (e.g. 'query: ') | |
| BRAIN_EMBEDDING_DOCUMENT_PREFIX | No | Document prefix for asymmetric embedding models; change requires full re-embed |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| brain_session_startA | Start or replay a concurrent session from an explicit user command. An agent tracer is the only session the server opens or closes on its own; no hook and no auto-close may invoke this lifecycle boundary. |
| brain_session_captureA | Attach durable artifacts from an explicit user command — to repair or refine. No longer a compulsory ritual. With derived capture armed, artifacts
created during the session are attributed without this call, and It never steals: an artifact already attributed stays where it is. An agent tracer is the only session the server opens or closes on its own; no hook and no auto-close may invoke this lifecycle boundary. |
| brain_session_heartbeatA | Refresh an open session from an explicit user command. An agent tracer is the only session the server opens or closes on its own; no hook and no auto-close may invoke this lifecycle boundary. |
| brain_session_endA | End a session from an explicit user command, on judgement alone.
What An agent tracer is the only session the server opens or closes on its own; no hook and no auto-close may invoke this lifecycle boundary. |
| brain_session_listA | List sessions only in response to an explicit user command. An agent tracer is the only session the server opens or closes on its own; no hook and no auto-close may invoke this lifecycle boundary. |
| brain_session_resumeB | Resume an open session from an explicit user command. An agent tracer is the only session the server opens or closes on its own; no hook and no auto-close may invoke this lifecycle boundary. |
| brain_session_abandonB | Abandon a session only from an explicit user command. An agent tracer is the only session the server opens or closes on its own; no hook and no auto-close may invoke this lifecycle boundary. |
| brain_find_toolA | Search for tools using natural language. Returns matching tool definitions ranked by relevance, in the same format as list_tools. |
| brain_call_toolA | Call a tool by name with the given arguments. Use this to execute tools discovered via search_tools. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
Most session tools map to distinct lifecycle states, but resume and heartbeat both target an open session with no clear boundary between them, and start's 'replay' capability also blurs with resume. The find_tool/call_tool pair is clearly distinct, which keeps the set usable.
All tools share the brain_ prefix and snake_case, and the seven session tools follow a consistent brain_session_<verb> pattern. The two meta-tools break that pattern with brain_find_tool and brain_call_tool, so the set is mostly consistent but not fully uniform.
Nine tools is well within the ideal range, and each tool maps to a distinct session lifecycle action or a general tool-search/call capability. Nothing feels redundant or bloated.
The session lifecycle is well covered: start, resume, heartbeat, capture, end, abandon, and list, with artifact attribution handled. Adding the meta find/call tools rounds out the surface with no obvious dead ends.