RAPPMCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RAPPMCP_CACHE | No | Cache directory for the fetched kernel file. Defaults to ~/.cache/rappmcp (or $XDG_CACHE_HOME/rappmcp). |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| chatA | Send one message to the AI Brainstem and return its answer as JSON: response, session_id, model, agent_logs (the agents it used). A failure is returned as a tool error with a plain explanation. Pass the returned session_id to continue the conversation. wait=false: for work that may take minutes. Returns {status: running, session_id} at once; poll job_status(session_id) for the answer. One message at a time per session. |
| job_statusA | Status of a chat started with wait=false: running (with seconds so far), done (with the
answer in |
| capabilitiesA | What this AI Brainstem can do right now: status, version, model and loaded agents. |
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 3 tools
Each tool has a clearly distinct role: chat sends a message, job_status polls an asynchronous chat job, and capabilities reports server/model/agent information. There is no overlapping purpose, and the descriptions explain exactly when to use each.
Names are all lowercase but follow different conventions: 'chat' is a bare noun, 'job_status' is a snake_case noun phrase, and 'capabilities' is a plural noun. The set is readable, but there is no consistent verb_noun or resource_action pattern.
Three tools are reasonable for a focused AI chat server: send a message, poll long-running work, and inspect capabilities. It is slightly thin but each tool earns its place.
The surface covers the core lifecycle: starting a chat, handling long-running chats asynchronously, polling their status, and discovering capabilities. Minor gaps exist around explicit session management or cancellation, but normal workflows are covered.