MCP.Market

GLM MCP server

by djerok·io.github.djerok/glm-mcp·v1.3.0·3 stars
No reviews yet

GLM (Zhipu/Z.ai) as a ~10x cheaper file-editing subagent for AI coding agents.

C60/100grade C
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
C60/100

full report

Adoption
Growing

3 stars247 downloads/wk

Reviews

Write one

Nobody has reviewed GLM MCP yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

GLM MCP tools (4, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • glm_agentwrite action

    Run GLM as a real coding agent with its OWN file tools (read/write/edit/list/bash); it works

  • glm_delegate

    Text-in/text-out subtask on GLM (~10x cheaper than Opus); returns text only. GLM has no

  • glm_recommend

    Free local advisory (no GLM call): given a task profile, returns GLM-vs-Opus, model,

  • glm_status

    Free local status: peak window, active model, GLM usage ledger (proof of GLM tokens spent), and config health. No GLM call.

Public scan report

scanner v0.1.9 · 2026-09-25 · same rubric, same numbers if you re-run it

1 high
  • Code scan7 source files scanned13/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 73 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Findings (1)

  • highShell command built from a string (injection risk)exec.shell-concat
    src/glmAgent.js: …ction gitCheckpoint(root) { try { execSync(`git -C "${root}" rev-parse --is-inside-work-tree`,…
Overall 60/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How GLM MCP compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
60/100
higher than 15% of 48,255 servers
Tools
4
the typical server has 7
Tools that change things
25%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
3
more than 80% of 28,688 servers
Downloads a week
247
more than 78% of 12,191 servers with a package

What its tools let an agent do: 3 read · 1 change

Install GLM MCP in Claude Code, Cursor or VS Code

Runs npx -y glm-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add glm-mcp -- npx -y glm-mcp
Add to Cursor

What the publisher says

From the GLM MCP repository's README, as published. We do not edit it. Read it on GitHub

glm-mcp — GLM as a cheap delegate for your AI coding agent

GLM (Zhipu / Z.ai) as a ~10x cheaper delegate for your AI coding agent. Your expensive main model — Claude Opus, Copilot's default, or Codex — orchestrates and reviews; GLM does the actual work, billed on cheap GLM tokens. GLM exposes an Anthropic-compatible /v1/messages endpoint, so it drops into anything that already speaks Anthropic. This repo wraps it as an MCP server with four tools, plus one-command installers for Claude Code, GitHub Copilot, and Codex. The same server powers every edition.

   

How it works

flowchart TD
    You["You"]
    Main["Main agent (Claude Opus / Copilot / Codex)<br/>orchestrates + reviews"]
    Srv["glm MCP server (stdio)<br/>4 tools"]
    Rt["Router<br/>peak-aware model pick + cost bias"]
    Zai[/"Z.ai Anthropic endpoint<br/>POST /v1/messages"/]
    Loop["glm_agent tool loop<br/>read_file / write_file / edit_file<br/>list_dir / run_bash — on your repo"]
    Led[("usage.jsonl<br/>every GLM call: model + tokens")]

    Repo[("your repo")]

    You --> Main -->|"glm_agent(task, workdir)"| Srv
    Srv --> Rt --> Zai
    Zai -->|"tool calls"| Loop
    Loop -->|"tool results"| Zai
    Loop -->|"reads / writes / runs"| Repo
    Zai --> Led
    Srv -->|"summary + GLM STATS<br/>(model, tokens, est. cost)"| Main
    Main -->|"review · diff · revert"| You

Plain-English walkthrough:

endpoint; the cost bias keeps GLM the default.

  1. You ask the main agent for work.
  2. The main agent delegates via glm_agent — it passes a goal plus an absolute workdir.
  3. The server's router picks a GLM model (peak-aware) and calls the Z.ai /v1/messages

run_bash) directly against your repo, then stops with a summary.

  1. GLM runs its own agent loop (readfile / writefile / editfile / listdir /

the main agent.

  1. The server returns a concise summary + a GLM STATS block (model, tokens, est. cost) to
  1. The main agent reviews; every GLM call is also appended to the usage.jsonl ledger.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

GLM MCP: common questions

Is GLM MCP server safe?
With care: it is graded C, so read the findings first (60/100). Read the GLM MCP safety report
How do I install GLM MCP?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does GLM MCP need an API key?
Yes. The registry entry asks for GLM_API_KEY.
Is GLM MCP maintained?
The last commit was 112 days ago (2026-07-15). The latest release is v1.3.0.
How does GLM MCP compare with other MCP servers?
safety score 60/100 (higher than 15% of 48,255 servers); tools 4 (the typical server has 7); tools that change things 25% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.