brain-core
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| brain_recallA | Search the agent's long-term memory: facts, patterns, decisions, corrections, session notes, raw sources, entity relations and the Claude Code session transcripts of this folder, across SQLite, the markdown vault, Hindsight and the graph, returned as one deduplicated list ranked by relevance and recency and capped at about 6k tokens. scope='transcript' searches only what past sessions said and ran. |
| brain_rememberA | Write one memory item to every store in one call, in order: markdown vault, SQLite, Hindsight, and the entity graph (relations only). |
| brain_sessionA | Open or close the agent's working session. Call phase='start' once at the beginning of every conversation, before any other brain tool; call phase='end' once when the user signals they are done. Not for single facts (brain_remember). |
| brain_distillA | Capture an external source into the agent's immutable raw/ folder as a dated markdown file with provenance: source, title, author, published, sha256, word count. This is step 1 of /distill; compiling the knowledge page from the raw file is your job afterwards. |
| brain_statusA | Report the agent's health in one read-only call: reachability of every store (vault,
SQLite, Hindsight, graph), knowledge-wiki lint (pages missing from _index, index links
to missing pages, pages without sources, raw files never compiled), always-loaded
context size in tokens per file, the last session start and close ids with an
|
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 5 tools
Each tool occupies a distinct slot: search (brain_recall), ingest (brain_distill), write a fact (brain_remember), session lifecycle (brain_session), and health/diagnostics (brain_status). Every description ends with an explicit 'Not for X (brain_Y)' boundary statement, so an agent has no path to confuse one with another.
All five tools share a strict `brain_` prefix followed by a single lowercase token, which reads as a coherent namespace. Minor deviation: recall/remember/distill are verbs while session/status are nouns, so the pattern is prefix-consistent but not uniformly verb_noun.
Five tools is tight and each earns its place: with the memory domain you need read, write, ingest, session boundary, and diagnostics, and nothing is redundant. brain_session reasonably bundles start/end into one phase-parameterised tool rather than splitting into two.
The read/write/ingest/lifecycle/diagnostic loop is fully closed, including partial-failure reporting and duplicate/contradiction handling. The gap is that memory is strictly append-only: there is no forget/prune/retract or explicit edit path, so a user cannot remove an obsolete item, and brain_status hints at 'maintenance' for which no tool exists.