GLM Vision

A Model Context Protocol (MCP) server that integrates GLM-4.5V from Z.AI with Claude Code.

python

7

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "danilofalcao-mcp-server-glm-vision": {
      "command": "/path/to/your/project/env/bin/python",
      "args": [
        "/path/to/your/project/glm-vision.py"
      ],
      "env": {
        "GLM_MODEL": "glm-4.5v",
        "GLM_API_KEY": "your_api_key_here",
        "GLM_API_BASE": "https://api.z.ai/api/paas/v4"
      }
    }
  }
}

You deploy and run an MCP server that bridges GLM-4.5V image analysis from Z.AI with Claude Code, enabling you to analyze images from local files or URLs through a simple MCP interface.

How to use

You run the GLM Vision MCP server locally and connect to it via your MCP client. Once the server is registered, you can invoke the vision tool to analyze images by providing an image path (local file or URL) and a descriptive prompt. The server handles the image analysis using GLM-4.5V and returns a structured response.

How to install

Prerequisites you need before starting:

Python 3.10 or higher is required.

GLM API key from Z.AI is required.

Claude Code must be installed to integrate with MCP.

Step 1: Prepare your project directory

cd /path/to/your/project

Step 2: Create and activate a virtual environment

python3 -m venv env
source env/bin/activate  # On Windows: env\Scripts\activate

Step 3: Install dependencies

pip install -r requirements.txt
# or with uv (recommended)
uv pip install -r requirements.txt

Step 4: Set up environment variables

cp .env.example .env
# Edit .env with your GLM API key from Z.AI

Step 5: Add the server to Claude Code

# Using uv (recommended)
uv run mcp install -e . --name "GLM Vision Server"

# Or manually add to Claude Desktop configuration:
claude mcp add-json --scope user glm-vision '{
  "type": "stdio",
  "command": "/path/to/your/project/env/bin/python",
  "args": ["/path/to/your/project/glm-vision.py"],
  "env": {"GLM_API_KEY": "your_api_key_here"}
}'

Step 6: Verify your setup

Ensure the MCP server is registered and the environment variables are available to the running process.

Available tools

glm-vision

Analyze an image file using GLM-4.5V's vision capabilities. Supports both local files and URLs. Parameters include image_path, prompt, temperature, thinking, and max_tokens.