mcpbeat Sign in

MCP Glm MCP Server

by acedatacloud Your server? Claim it
answering

MCP Glm is answering right now. Last checked moments ago. 327 installs a week from pypi. Last commit 28 Aug 2026.

MCP server for GLM chat completions using Zhipu AI models via AceDataCloud

Installs per day peak 348 · avg 105 · -72% w/w
a month agotoday
Uptime history 47 days of history · worst day 99%
47 days agonow
100.0%
Uptime 24h
92 of 92 checks
—
Tools
hidden behind auth
1673 ms
Response time
average over 24h
327
Installs / week
npm and PyPI

Nothing serious here today

Today is the operative word: we check MCP Glm every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 0 min ago.

run in your terminal
claude mcp add mcp-glm --transport http https://glm.mcp.acedata.cloud/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "mcp-glm": {
      "url": "https://glm.mcp.acedata.cloud/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.mcp-glm]
url = "https://glm.mcp.acedata.cloud/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "mcp-glm": {
      "url": "https://glm.mcp.acedata.cloud/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "mcp-glm": {
      "url": "https://glm.mcp.acedata.cloud/mcp"
    }
  }
}

This one needs environment variables set before it will start: ACEDATACLOUD_API_TOKEN (API token from Ace Data Cloud (https://platform.acedata.cloud)). The author declared them in the registry entry; get the values from the project itself.

This endpoint answered with an authorization challenge. The server is running, and it signs you in through your browser: there is no API key to paste.

Endpoints

URLTransportStateLatencyChecked
https://glm.mcp.acedata.cloud/mcp streamable-http sign-in 1719 ms 0 min ago

Alternatives to MCP Glm

same job, measured the same way
MCP Aichat
by acedatacloud

MCP server for AI dialogue using various LLM models via AceDataCloud

3 038 installs/wk answering
MCP Webextrator
by acedatacloud

MCP server for web extraction and rendering via AceDataCloud WebExtrator

1 026 installs/wk answering
ChipsAI MCP Server
by fgasparetto

MCP server for ChipsAI — manage chatbots, conversations, and AI models

70 installs/wk local only
Kaggle MCP
by seif-sameh

MCP server for the Kaggle API: competitions, datasets, kernels, and models.

84 installs/wk local only
MCP Neo4j Data Modeling
by neo4j-contrib

A simple Neo4j MCP server for creating graph data models.

1 308 installs/wk local only
VDatum MCP Server
by mansurjisan

MCP server for vertical datum conversions using coastalmodeling-vdatum

40 installs/wk local only
DeepSeek MCP Server
by dmontgomery40

Official DeepSeek MCP server for chat, completion, model listing, and balance endpoints.

1 154 installs/wk local only
Perplexity Polza MCP Server
by ivanantigravity-lgtm

Perplexity MCP server backed by the Polza.ai chat completions API.

74 installs/wk local only

MCP Glm — questions

Answers built from our own checks of this server.

Why is there no tool list for MCP Glm?
The server answered our handshake with an authorization challenge, so it is running — but it will not describe its tools to an anonymous client. To see them you need to connect with your own credentials. We record it as alive, not as broken: 100.0% of checks in the last 24 hours got a reply.
Is MCP Glm working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 1673 ms. The bar chart above shows every period we have measured.
How do I connect MCP Glm?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address. You sign in through your browser once and the client keeps the session: no key to copy, and it refuses anonymous clients.
How do you sign in to MCP Glm?
No API key is involved. MCP Glm answers our knock with an OAuth challenge, so you authorise it once in your browser and the client keeps the session. That is also why we see no tool list: it will not describe itself to an anonymous client, and that is the server working as intended, not a fault.
How fast is MCP Glm?
It answers our handshake in 1673 ms on average, which is faster than 1% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.
How many people use MCP Glm?
The pypi package mcp-glm was installed 327 times in the last week. Week over week that is -72%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is MCP Glm open source?
Yes — it is published under the MIT licence, written in Python and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.