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 your agent definitions. Must contain at least one .md or .txt file. The filename becomes the agent name. | |
| AGENT_TYPE | Yes | The coding CLI backend to use. One of: codex, claude, cursor, command-code, glm, kimi, grok, antigravity, gemini, opencode. The selected CLI must be installed and configured before the MCP server starts. | |
| AGENT_MODEL | No | Use one model for every agent. Omit it to use the backend's default. | |
| CLI_API_KEY | No | API key required when AGENT_TYPE is glm or kimi. Other backends use the CLI's existing authentication. | |
| SESSION_ENABLED | No | Set to "true" to let an agent remember earlier calls and continue a longer task. Your assistant must reuse the returned session_id on the next call to continue that session. | |
| AGENT_PERMISSION | No | Controls what agents may do: read-only (review and investigation), safe-edit (edits allowed without approval, default), or 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