pypi mcp-glmstreamable-httpMITupdated 11d ago
A Model Context Protocol (MCP) server for Zhipu GLM chat completions via the AceDataCloud platform.
What can you do with mcp glm?
MCP GLM Server
A Model Context Protocol (MCP) server for Zhipu GLM chat completions via the AceDataCloud platform.
Features
- GLM chat completions: Call Zhipu GLM models through a uniform MCP tool
- Model discovery: List the GLM models exposed by AceDataCloud
- Usage guide: Inline tool returning the API usage guide
Installation
pip install mcp-glm
Configuration
Set your AceDataCloud API token:
export ACEDATACLOUD_API_TOKEN=your_token_here
Get your token from https://platform.acedata.cloud.
Usage
stdio mode (default)
mcp-glm
HTTP mode
mcp-glm --transport http --port 8000
Available Tools
| Tool | Description |
|---|---|
glm_chat_completions |
Run a GLM chat completion call |
glm_list_models |
List available GLM models |
glm_get_usage_guide |
Get the API usage guide |
Documentation
License
MIT — see LICENSE.
Install
Add mcp glm to your client. Pick the one you use.
{
"servers": {
"mcp-glm": {
"type": "http",
"url": "https://glm.mcp.acedata.cloud/mcp"
}
}
}Add to `.vscode/mcp.json` in your workspace.
claude mcp add mcp-glm -- uvx mcp-glmcodex mcp add mcp-glm -- uvx mcp-glmamp mcp add mcp-glm -- uvx mcp-glm{
"mcpServers": {
"mcp-glm": {
"command": "uvx",
"args": [
"mcp-glm"
]
}
}
}Add to `claude_desktop_config.json`, then restart Claude Desktop.
{
"mcpServers": {
"mcp-glm": {
"command": "uvx",
"args": [
"mcp-glm"
]
}
}
}Add to `~/.cursor/mcp.json`, or `.cursor/mcp.json` for a single project.
{
"mcpServers": {
"mcp-glm": {
"command": "uvx",
"args": [
"mcp-glm"
]
}
}
}Add to `~/.codeium/windsurf/mcp_config.json`.
{
"mcpServers": {
"mcp-glm": {
"command": "uvx",
"args": [
"mcp-glm"
]
}
}
}Add to `cline_mcp_settings.json` via the MCP Servers panel.
{
"mcpServers": {
"mcp-glm": {
"command": "uvx",
"args": [
"mcp-glm"
]
}
}
}Add to `~/.gemini/settings.json`.
{
"mcpServers": {
"mcp-glm": {
"type": "local",
"command": "uvx",
"args": [
"mcp-glm"
],
"tools": [
"*"
]
}
}
}Add to `~/.copilot/mcp-config.json`, or run `/mcp add` inside the CLI.
{
"context_servers": {
"mcp-glm": {
"command": {
"path": "uvx",
"args": [
"mcp-glm"
]
}
}
}
}Add to your Zed `settings.json`.
uvx mcp-glmRun `goose configure`, choose **Add Extension → Command-line Extension**, and paste this command.
3 tools
mcp glm exposes 3 tools to a connected agent.
- glm_chat_completions
- Run a GLM chat completion call
- glm_list_models
- List available GLM models
- glm_get_usage_guide
- Get the API usage guide
Score
79 / 100
Good
- Documentation19/25
- Maintenance25/25
- Trust16/20
- Capability4/15
- Install experience15/15
- Documents what it does and how to connect
- Has a resolvable package or endpoint
- Exposes at least one tool, prompt or resource
- README has substantive content
- Includes a code example
- Documents its configuration
- Mentions credentials or security posture
- Last commit 4 days ago
- Has a release history
- Repository is not archived
- Licensed MIT
- Namespace verified in the official MCP registry
- Claimed by its owner
- Published under an organisation
- 3 tool(s) documented
- Provides prompt templates
- Provides resources
- 18 documented install method(s)
- Published to a package registry
- Offers a hosted endpoint — no local install
Version history
| Versions | Published |
|---|---|
| 2026.8.28.0Latest | Aug 28, 2026 |
| 2026.8.24.0 | Aug 24, 2026 |
| 2026.8.23.0 | Aug 23, 2026 |
| 2026.8.18.0 | Aug 18, 2026 |
| 2026.8.17.0 | Aug 17, 2026 |
| 2026.7.30.0 | Jul 30, 2026 |
| 2026.7.27.0 | Jul 27, 2026 |
| 2026.7.4.0 | Jul 4, 2026 |
| 2026.7.2.0 | Jul 2, 2026 |