MCP tools
Agent Brain exposes one MCP tool named brain. It uses a required command
field and an optional input object. This unified shape is the current public
contract; older examples that call brain_recall or brain_remember directly
are stale and should be migrated.
Request shape
{
"name": "brain",
"arguments": {
"command": "recall",
"input": {
"query": "deployment approval policy",
"limit": 5
}
}
}
Commands
| Command | Purpose |
|---|---|
remember | Store durable memory with type, importance, project, and tags. |
remember_execution | Store a structured Harness or Terminal execution outcome. |
execution_insights | Aggregate recurring routing, verification, policy, or materialization friction. |
recall | Retrieve relevant memories for a natural-language query. |
search | Browse memories with pagination and filters. |
forget | Archive a memory by ID. |
get_by_id | Fetch one memory by UUID. |
resolve_memory | Resolve a deferred brain://memory/<id> reference. |
status | Return health, memory, cache, and connected-agent status. |
share | Share a memory with selected agents. |
cache_check | Check for a semantically similar cached response. |
project_context | Retrieve project-scoped context and active agents. |
audit | Find conflicts, redundancy, and stale memories. |
audit_apply | Apply approved audit findings. |
export | Export a .brainpack archive. |
import | Restore a .brainpack archive, optionally as a dry run. |
import_foreign | Import Claude, Codex, Gemini, or other supported memory files. |
Common inputs
remember
{
"command": "remember",
"input": {
"content": "Deployments require staging approval before production.",
"type": "decision",
"importance": 0.9,
"project": "example-project",
"tags": ["release", "policy"]
}
}
recall
{
"command": "recall",
"input": {
"query": "What is our production approval policy?",
"limit": 5,
"filter": { "project_id": "example-project" }
}
}
search
Use query, optional filter, page, and page_size for browse-style access.
Filters can include memory type, project, source agent, date range, minimum
importance, tags, and archived status.
export and import
Use a passphrase for encrypted .brainpack archives. Use dry_run: true before
an import that will write records. Keep archive files and passphrases private.
Compatibility notes
- Discover the
braintool and its description at connection time. - Treat command output fields as additive and IDs as opaque.
- The MCP endpoint is local by default; do not expose it publicly without an authentication and network boundary.
- For HTTP clients, use the REST API reference.