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 | Coding CLI backend to use. Supported values: 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 required in the MCP server environment when AGENT_TYPE is glm or kimi. Optional for other backends, which use the CLI's existing authentication. | |
| SESSION_ENABLED | No | Set to "true" to enable continuing an agent's work across multiple calls using the returned session_id. | false |
| AGENT_PERMISSION | No | Controls what agents may do: read-only, safe-edit (default), or yolo. | 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
ResponsivenessNo issues