GLM MCP

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. It runs locally over stdio via the published package.

People connecting coding agent tools to Claude, Cursor, VS Code, or another MCP client. The project is written in JavaScript.

VERIFIED ACTIVE

LAST COMMIT 2026-07-15 · ★ 2 · #92 OF 194 MAINTAINED CODING AGENT · VERIFIED 2026-08-25

MIT · JavaScript servers · how we verify → /methodology

01 · Install GLM MCP

before you install - you'll need

GLM_API_KEY

Environment variables documented in the project's README - it lists which are required and which have defaults.

Claude Code

claude mcp add djerok-glm-mcp -- npx -y glm-mcp

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "djerok-glm-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "glm-mcp"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

repo age created 2026-06-30 - young repo, little track record yet

license MIT - declared in the repository

npm package glm-mcp - unscoped; check the name against the project README before installing

registry namespace io.github.djerok is GitHub-verified and matches the repo owner

03 · What GLM MCP can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

Latest releases

copilot-v1.3.0 · 2026-07-02

Full parity with the Claude Code edition. Copilot (VS Code) has agent hooks too - including a PreToolUse event - so this release adds the third and final primitive: an auto-routing hook. · New - PreToolUse auto-routing…

copilot-v1.2.0 · 2026-07-02

Near-parity with the Claude Code edition. Copilot has custom agents (subagents) after all, so this release adds one. · New · GLM custom agent (subagent) - restricted to the glm MCP tools (tools: ['glm/']), the Copilot…

copilot-v1.1.0 · 2026-07-02

Adds global setup for GitHub Copilot: npx glm-mcp-copilot --global --key YOUR_ZAI_KEY registers the GLM server in VS Code's user mcp.json (all workspaces) and adds the delegation policy to user settings.json…

04 · Who maintains GLM MCP

GLM MCP is maintained by djerok. It's the only MCP server we track from this author; the repo dates to Jun 2026.

05 · Facts

category
coding agent - ranked #92 of 194 actively-maintained coding agent servers as of 2026-08-25.
release cadence
4 releases in the last 90 days (latest 2026-07-02)
registry
io.github.djerok/glm-mcp (active, first published 2026-07-06 · 3 versions)
packages
npm:glm-mcp

06 · GLM MCP FAQ

What is GLM MCP?

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. It runs locally over stdio via the published package.

Is GLM MCP still maintained?

Yes - as of 2026-08-25, its last commit was 2026-07-15 and it shipped 4 releases in the last 90 days. We re-verify nightly.

How do I install GLM MCP?

Run `npx -y glm-mcp`. The README documents one environment variable (GLM_API_KEY) to set first. You can also paste the ready-made client config above.

Does GLM MCP run locally?

Yes - it's a stdio server: it runs on your machine (via npx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to GLM MCP

More coding agent MCP servers · Codecanvas · Agentmako · Talkthru · Calm MCP · Code Context Engine

More JavaScript MCP servers · Guesty MCP Server · Twitterapi Docs MCP · Twitterapi Io MCP · Conta Azul MCP · Megalinter · see all