glm-subagent-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GLM_MODEL | No | Model to use. The Coding Plan supports glm-5.3 and glm-5.3-flash. | glm-5.3 |
| GLM_API_KEY | Yes | Your Coding Plan API key. Required. | |
| GLM_BASE_URL | No | Coding Plan address. Mainland-China accounts should use https://open.bigmodel.cn/api/anthropic | https://api.z.ai/api/anthropic |
| GLM_MAX_TOKENS | No | Output limit per round (this project's choice, not an official cap) | 32768 |
| GLM_MAX_RETRIES | No | Retries on 429, 5xx and concurrency errors | 4 |
| GLM_MAX_CONCURRENT | No | Requests sent to GLM at the same time | 1 |
| GLM_AGENT_MAX_ITERS | No | Maximum rounds per task | 30 |
| GLM_STALL_TIMEOUT_MS | No | How long to wait in silence before retrying | 120000 |
| GLM_AGENT_BASH_TIMEOUT_MS | No | Time limit for one shell command | 120000 |
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| glm_agentA | Delegate a self-contained coding task to a GLM sub-agent (use when the user asks for GLM or glm_agent, or wants to save Claude tokens). GLM works inside |
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 1 tool
Only one tool is exposed, so there is zero risk of selecting the wrong tool. Its purpose—delegating a self-contained coding task to a GLM sub-agent—is clearly stated and distinct.
The single tool uses snake_case (`glm_agent`), which is a standard, predictable convention. With only one tool, consistency is trivially satisfied.
One tool is slightly below the typical 3–15 range, but the server is a focused, single-purpose delegation wrapper. The tool is substantial rather than trivial, so the count is reasonable though thin.
The tool covers the core delegation lifecycle: accept a task, run it in a workdir, return summary and changed files. However, it lacks follow-up operations like status, cancellation, or session continuation, which could be useful for long tasks.