Schema | GLM Subagent MCP

GLM Subagent MCP

Describes the environment variables required to run the server.

Name	Required	Description	Default
`GLM_CAP`	No	Output-token cap. Off by default = generous (up to 131072 per call). Set on to enforce GLM_MAX_TOKENS. Default: off	off
`GLM_API_KEY`	Yes	Your Z.ai API key with GLM Coding Plan access. Required.
`GLM_BASE_URL`	No	Anthropic-compatible endpoint. Default: https://api.z.ai/api/anthropic	https://api.z.ai/api/anthropic
`GLM_COST_BIAS`	No	How hard to favor GLM (it's ~10x cheaper). Higher = more GLM; 0 = decide on capability only. Default: 1.5	1.5
`GLM_MAX_TOKENS`	No	The hard per-call limit applied only when GLM_CAP=on. Default: 32768	32768
`GLM_PEAK_MODEL`	No	Model used during China peak. Default: glm-5.2	glm-5.2
`GLM_PEAK_END_CN`	No	Peak window end (China hour, UTC+8). Default: 18	18
`GLM_OFFPEAK_MODEL`	No	Model used off-peak. Default: glm-5.2	glm-5.2
`GLM_PEAK_START_CN`	No	Peak window start (China hour, UTC+8). Default: 14	14
`GLM_MAX_CONCURRENT`	No	GLM caps in-flight requests; keep at 1. Default: 1	1
`GLM_AGENT_MAX_ITERS`	No	Max tool-loop turns for glm_agent. Default: 30	30
`GLM_MAX_TOKENS_CEILING`	No	The generous default used when the cap is off. Default: 131072	131072

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.

Features and capabilities supported by this server

Protocol revision2025-11-25

Capability	Details
`tools`	{ "listChanged": true }

Functions exposed to the LLM to take actions

Name	Description
glm_delegateA	Text-in/text-out subtask on GLM (~10x cheaper than Opus); returns text only. GLM has no file/tool access -- put everything in task+context. For file edits use glm_agent instead. Not for sensitive, long-debugging, large-refactor, or parallel work.
glm_agentA	Run GLM as a real coding agent with its OWN file tools (read/write/edit/list/bash); it works your repo end-to-end on GLM tokens (~10x cheaper than Opus). Prefer this over doing repo work yourself. Pass task + absolute workdir. Returns a concise summary+stats (use dry_run to preview a diff first). Not for sensitive, huge-context, or heavy dependent-tool-loop work.
glm_recommendA	Free local advisory (no GLM call): given a task profile, returns GLM-vs-Opus, model, confidence, and reasons. Call when unsure which engine to use.
glm_statusA	Free local status: peak window, active model, GLM usage ledger (proof of GLM tokens spent), and config health. No GLM call.

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/djerok/glm-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server