Schema | robrain

robrain

Describes the environment variables required to run the server.

Name	Required	Description	Default
`PERCEPTION_API_KEY`	No	Perception API key (generated by `npx robrain up`). Optional — read from ~/.robrain/config.json when present.
`PERCEPTION_API_URL`	No	URL of your self-hosted Perception backend (started with `npx robrain up`). Optional — read from ~/.robrain/config.json when present.	http://localhost:3001

Features and capabilities supported by this server

Capability	Details
`tools`	{ "listChanged": true }

Functions exposed to the LLM to take actions

Name	Description
sensing_start_sessionA	Signal the start of a new Claude Code session. Call this once at the beginning of every session. Returns the always-on project summary to inject into your context. session_id may be omitted or empty — the server generates a unique id and returns it (use that id for sensing_record_turn and sensing_end_session).
sensing_record_turnA	Record a completed conversation turn (user message + Claude reply). Call this after every exchange. Survives server restarts — keep using the same session_id even if the server reconnected mid-conversation. Returns whether a topic shift was detected — if true, call your context injection tool.
sensing_end_sessionA	Signal the end of a Claude Code session. Triggers the flush-on-close hook to ship any unclassified buffered turns to Perception before the session closes.
sensing_get_statusA	Get the current status of the Sensing buffer for a session. Useful for debugging.

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/adelinamart/robrain'

If you have feedback or need assistance with the MCP directory API, please join our Discord server