glm-mcp

MCP server for ZhipuAI GLM — exposes chat, text embeddings, translation, vision, and OCR to Claude Code (and any MCP-compatible client) via the OpenAI-compatible API.

Tools

Tool	Description
`glm_chat`	Text completion — default model `glm-4-flash`, pass `model=` to use any GLM chat model (e.g. `glm-5`). Supports single-turn and multi-turn (`messages=` parameter). Sampling: `temperature=0.7`, `top_p=0.95` (pass `top_p=None` to omit). Auto-fallback on transient errors (429/503/timeout/connection) via `auto_fallback=True` (default). Use `avoid_peak_hours=True` to pre-emptively switch during peak hours (UTC+8 14:00–18:00).
`glm_embed`	Text embeddings — default model `embedding-3`, pass `model=` to override
`glm_usage_summary`	Query token usage from `~/.glm-mcp/usage.jsonl`. Parameters: `days` (default 7), `model` (optional filter). Returns period, total tokens, by_tool, by_model.
`glm_translate`	Pure single-language translation — default model `glm-4.7`. Parameters: `text`, `target_lang` (`"ja"`, `"zh"`, `"en"`), `source_lang` (default `"auto"`), `style` (`"formal"` or `"casual"`, default `"formal"`). Sampling: `temperature=1.0`, `top_p=0.8` (GLM-4.7 Plan B: top_p as primary control; pass `top_p=None` to omit). Outputs ONLY the target language, solving the mixed Chinese–Japanese output problem common with general LLMs.
`glm_vision`	Multimodal image analysis — default model `glm-4.6v`. Parameters: `image_url` (HTTP/HTTPS URL or Base64 string), `prompt`, `detail` (`"auto"`, `"low"`, `"high"`), `max_tokens` (default 2048). Sampling: `temperature=0.2`, `top_p=0.9` (focused stable analysis; pass `top_p=None` to omit). Auto-fallback to `glm-4.6v-flash` on 429/503/timeout. Bare Base64 strings are automatically prefixed with `data:image/png;base64,`.
`glm_ocr`	Document and image OCR — default model `glm-ocr`. Parameters: `file` (HTTP/HTTPS URL, Base64 string, `data:` URI, or local file path), `model`, `start_page_id`, `end_page_id`. Returns extracted text as Markdown. Local files are auto-encoded as Base64; bare Base64 strings are prefixed with `data:application/pdf;base64,`.

Quick Start

Install via uvx (recommended)

uvx glm-mcp

Add to Claude Code

Add to ~/.claude.json:

{
  "mcpServers": {
    "glm-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": ["glm-mcp"],
      "env": {
        "GLM_API_KEY": "your_api_key_here"
      }
    }
  }
}

Get your API key at https://open.bigmodel.cn/.

Run from source

git clone https://github.com/sky-zhang01/glm-mcp
cd glm-mcp
uv sync
GLM_API_KEY=your_key uv run glm-mcp

Environment Variables

Variable	Required	Default	Description
`GLM_API_KEY`	Yes	—	ZhipuAI API key
`GLM_BASE_URL`	No	`https://open.bigmodel.cn/api/paas/v4/`	API endpoint override
`GLM_MCP_LOG_DIR`	No	`~/.glm-mcp/`	Directory for `usage.jsonl` token log

Token Usage Logging

Each tool call appends a JSON line to ~/.glm-mcp/usage.jsonl:

{"timestamp": "...", "tool": "glm_chat", "model": "glm-4-flash", "input_tokens": 13, "output_tokens": 15, "fallback_used": false, "original_model": null, "fallback_reason": null}

When fallback is triggered:

{"timestamp": "...", "tool": "glm_chat", "model": "glm-4.7", "input_tokens": 13, "output_tokens": 15, "fallback_used": true, "original_model": "GLM-5", "fallback_reason": "429"}

Development

uv sync --dev
uv run pytest --cov=glm_mcp --cov-report=term-missing

License

MIT

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

glm_mcp-0.8.1.tar.gz (10.0 kB view details)

Uploaded Mar 1, 2026 Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

glm_mcp-0.8.1-py3-none-any.whl (15.5 kB view details)

Uploaded Mar 1, 2026 Python 3

File details

Details for the file glm_mcp-0.8.1.tar.gz.

File metadata

Download URL: glm_mcp-0.8.1.tar.gz
Upload date: Mar 1, 2026
Size: 10.0 kB
Tags: Source
Uploaded using Trusted Publishing? Yes
Uploaded via: uv/0.10.7 {"installer":{"name":"uv","version":"0.10.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

File hashes

Hashes for glm_mcp-0.8.1.tar.gz
Algorithm	Hash digest
SHA256	`f03f56cf21cc31997d9a1ac0c3ca4b222335fca31bcd545612a6489f55735be3`
MD5	`3764eeb7121e507b0d234a747ea70344`
BLAKE2b-256	`d4037c0debc299ba05f3d5a2ed4254dd60ee9bbbc6c11db6909236105dd72ff3`

See more details on using hashes here.

File details

Details for the file glm_mcp-0.8.1-py3-none-any.whl.

File metadata

Download URL: glm_mcp-0.8.1-py3-none-any.whl
Upload date: Mar 1, 2026
Size: 15.5 kB
Tags: Python 3
Uploaded using Trusted Publishing? Yes
Uploaded via: uv/0.10.7 {"installer":{"name":"uv","version":"0.10.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

File hashes

Hashes for glm_mcp-0.8.1-py3-none-any.whl
Algorithm	Hash digest
SHA256	`e015d4a4fc2dad568e6a35f5a847b6e6ba4bbc7e7affd3be30e6e146f574f8b8`
MD5	`c02fe25b3d7284ee782395323e952bce`
BLAKE2b-256	`d725a7d252e96e454db82ee2058320c844096e5c143052690dcb7de5c72a51e4`