Sub-Agents MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AGENTS_DIR | Yes | Absolute path to the folder containing agent definition files (.md or .txt). | |
| AGENT_TYPE | Yes | The backend to use. One of: codex, claude, cursor, command-code, glm, kimi, grok, antigravity, gemini, opencode. | |
| AGENT_MODEL | No | Model to use for every agent. Omit to use the backend's default model. | |
| CLI_API_KEY | No | API key for GLM (Z.ai) or Kimi backends. Required when AGENT_TYPE is 'glm' or 'kimi'. | |
| SESSION_ENABLED | No | Set to "true" to enable session continuation across calls. The assistant must reuse the returned session_id. | |
| AGENT_PERMISSION | No | Controls what agents may do: 'read-only' (review/investigation), 'safe-edit' (edits allowed without approval, default), 'yolo' (unrestricted execution). | safe-edit |
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
ActivityActive
ResponsivenessResponsive