LLM Subagent MCP
by yishutu
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LLM_MODEL | No | Optional default chat model. A model may also be supplied per delegate_task call; priority is tool argument, then environment variable, then TOML default. | |
| LLM_API_KEY | Yes | API key for the OpenAI-compatible Chat Completions provider. This is required and may be set in the environment or in a .env file beside providers.toml. | |
| LLM_BASE_URL | No | Optional API root URL, including /api/v1 or /v1 but without /chat/completions. Defaults to the base URL configured in providers.toml. | |
| MCP_ACCESS_TOKEN | No | Optional separate credential protecting the HTTP MCP endpoint. Token-based clients send it as Authorization: Bearer <MCP_ACCESS_TOKEN>; it is separate from LLM_API_KEY. |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No 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 | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessSyncing