ZAI MCP Server

A Model Context Protocol (MCP) server that provides web search, content fetching, and AI-powered summarization capabilities using ZAI's GLM-4.7-Flash model.

Features

Web Search: Search the web using DuckDuckGo
Content Fetching: Clean and extract text from any website
AI Summarization: Summarize web content using GLM-4.7-Flash
Combined Workflows: Search, fetch, and summarize in one operation
Fast & Efficient: Uses flash model for quick responses

Tools

`search_web`

Search the web for information.

Parameters:

query (string, required): Search query
num_results (number, optional): Number of results (1-10, default: 5)

Returns:

{
  "query": "search term",
  "count": 5,
  "results": [
    {
      "title": "Result Title",
      "url": "https://example.com",
      "snippet": "Brief snippet of the content..."
    }
  ]
}

`fetch_and_summarize`

Fetch a website URL and summarize its content.

Parameters:

url (string, required): Website URL to fetch
max_content_length (number, optional): Max content length to process (default: 10000)

Returns:

{
  "url": "https://example.com/article",
  "title": "Article Title",
  "summary": "AI-generated summary of the content...",
  "content_length": 5000
}

`search_and_summarize`

Search the web, fetch the top result, and summarize it.

Parameters:

query (string, required): Search query
result_index (number, optional): Which search result to fetch (1-10, default: 1)

Returns:

{
  "query": "search term",
  "result_index": 1,
  "url": "https://example.com/article",
  "title": "Article Title",
  "summary": "AI-generated summary...",
  "total_results": 10
}

Installation

Prerequisites

Python 3.8 or higher
ZAI API key (get one at https://z.ai/model-api)
pip package manager

Install from source

# Clone the repository
git clone https://github.com/yourusername/zai-mcp-server.git
cd zai-mcp-server

# Install dependencies
pip install -r requirements.txt

# Make server executable
chmod +x src/server.py

Quick Start

# Set your API key
export ZAI_API_KEY="your-zai-api-key"

# Run the server
python src/server.py

Configuration

Environment Variables

Variable	Description	Required	Default
`ZAI_API_KEY`	Your ZAI API key	Yes	-

API Configuration

The server uses the following ZAI API configuration:

Base URL: https://api.z.ai/api/paas/v4
Model: glm-4.7-flash
Max Tokens: 1000
Temperature: 0.7

Usage

Standalone Testing

# Test initialization
echo '{"jsonrpc": "2.0", "id": 1, "method": "initialize", "params": {}}' | python src/server.py

# List available tools
echo '{"jsonrpc": "2.0", "id": 2, "method": "tools/list", "params": {}}' | python src/server.py

# Search the web
echo '{"jsonrpc": "2.0", "id": 3, "method": "tools/call", "params": {"name": "search_web", "arguments": {"query": "AI news", "num_results": 3}}}' | python src/server.py

Integration with Claude Desktop

Add to Claude Desktop configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json Linux: ~/.config/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "zai": {
      "command": "python3",
      "args": ["/absolute/path/to/zai-mcp-server/src/server.py"],
      "env": {
        "ZAI_API_KEY": "your-zai-api-key"
      }
    }
  }
}

Integration with Cursor

Add to Cursor settings file (~/.cursor/mcp_config.json):

{
  "mcpServers": {
    "zai": {
      "command": "python3",
      "args": ["/absolute/path/to/zai-mcp-server/src/server.py"],
      "env": {
        "ZAI_API_KEY": "your-zai-api-key"
      }
    }
  }
}

Integration with Cline (VS Code)

Add to your MCP settings in VS Code:

{
  "mcpServers": [
    {
      "name": "zai",
      "command": "python3",
      "args": ["/absolute/path/to/zai-mcp-server/src/server.py"],
      "env": {
        "ZAI_API_KEY": "${env:ZAI_API_KEY}"
      }
    }
  ]
}

Integration with Continue

Add to ~/.continue/config.json:

{
  "mcpServers": {
    "zai": {
      "command": "python3",
      "args": ["/absolute/path/to/zai-mcp-server/src/server.py"],
      "env": {
        "ZAI_API_KEY": "your-zai-api-key"
      }
    }
  }
}

Integration with Roo Code

Add to Roo Code's MCP configuration:

{
  "mcpServers": {
    "zai": {
      "command": "python3",
      "args": ["/absolute/path/to/zai-mcp-server/src/server.py"],
      "env": {
        "ZAI_API_KEY": "your-zai-api-key"
      }
    }
  }
}

OpenCode Native Integration

Setup

OpenCode supports MCP servers natively. To configure:

Create/Update the MCP configuration file:

# Default location: ~/.config/opencode/mcp_servers.json
mkdir -p ~/.config/opencode
nano ~/.config/opencode/mcp_servers.json

Add ZAI MCP Server configuration:

{
  "mcpServers": {
    "zai": {
      "name": "ZAI Web Search & Summarization",
      "description": "Search web and summarize content using GLM-4.7-Flash",
      "command": "python3",
      "args": ["/home/op/zai-mcp-server/src/server.py"],
      "env": {
        "ZAI_API_KEY": "your-zai-api-key"
      },
      "enabled": true
    }
  }
}

Restart OpenCode to load the new MCP server

Usage in OpenCode

Once configured, you can use the MCP server in OpenCode conversations:

User: Search for recent developments in AI and summarize the top result

Assistant: I'll use the ZAI MCP server to search and summarize for you.

[Calls search_and_summarize tool]

The ZAI MCP server found an article about recent AI developments. Here's a summary:
- Main point 1
- Main point 2
- Main point 3

Full article available at: https://example.com/ai-developments

Examples

Example 1: Web Search

# Request
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "search_web",
    "arguments": {
      "query": "machine learning trends 2024",
      "num_results": 5
    }
  }
}

# Response
{
  "jsonrpc": "2.0",
  "id": 1,
  "result": {
    "content": [
      {
        "type": "text",
        "text": JSON.stringify({
          "query": "machine learning trends 2024",
          "count": 5,
          "results": [...]
        })
      }
    ]
  }
}

Example 2: Fetch and Summarize

# Request
{
  "jsonrpc": "2.0",
  "id": 2,
  "method": "tools/call",
  "params": {
    "name": "fetch_and_summarize",
    "arguments": {
      "url": "https://www.example.com/article"
    }
  }
}

# Response
{
  "jsonrpc": "2.0",
  "id": 2,
  "result": {
    "content": [
      {
        "type": "text",
        "text": JSON.stringify({
          "url": "https://www.example.com/article",
          "title": "Article Title",
          "summary": "Key points:\n• Point 1\n• Point 2\n• Point 3",
          "content_length": 5000
        })
      }
    ]
  }
}

Example 3: Search and Summarize (Combined)

# Request
{
  "jsonrpc": "2.0",
  "id": 3,
  "method": "tools/call",
  "params": {
    "name": "search_and_summarize",
    "arguments": {
      "query": "quantum computing breakthrough",
      "result_index": 1
    }
  }
}

# Response
{
  "jsonrpc": "2.0",
  "id": 3,
  "result": {
    "content": [
      {
        "type": "text",
        "text": JSON.stringify({
          "query": "quantum computing breakthrough",
          "result_index": 1,
          "url": "https://example.com/quantum-news",
          "title": "Major Quantum Computing Breakthrough",
          "summary": "Researchers have achieved a significant milestone...",
          "total_results": 10
        })
      }
    ]
  }
}

Testing

Run the test suite to verify the server is working correctly:

python examples/test_server.py

Expected output:

============================================================
ZAI MCP Server Test Suite
============================================================

Testing initialization...
✓ Initialize: mcp-zai-server v1.0.0

Testing tools list...
✓ Available tools (3):
  - search_web: Search the web for information using DuckDuckGo
  - fetch_and_summarize: Fetch a website URL and summarize its content using GLM-4.7-Flash
  - search_and_summarize: Search the web, fetch top result, and summarize using GLM-4.7-Flash

Testing resources list...
✓ Available resources (1):
  - zai://status: Current status of ZAI MCP server

Testing resource read...
✓ Server status:
  Status: online
  Model: glm-4.7-flash
  API Endpoint: https://api.z.ai/api/paas/v4
  Tools: search_web, fetch_and_summarize, search_and_summarize

============================================================
✓ All tests passed!
============================================================

Development

Project Structure

zai-mcp-server/
├── src/
│   └── server.py          # Main MCP server implementation
├── docs/
│   ├── ARCHITECTURE.md     # Architecture documentation
│   └── API_REFERENCE.md    # Detailed API reference
├── examples/
│   └── test_server.py      # Test suite and examples
├── requirements.txt           # Python dependencies
├── README.md                # This file
└── .env.example             # Environment variables template

Dependencies

aiohttp - Async HTTP client
beautifulsoup4 - HTML parsing
openai - OpenAI-compatible client for ZAI API

Troubleshooting

Common Issues

Server won't start

Ensure Python 3.8+ is installed: python --version
Check dependencies are installed: pip install -r requirements.txt
Verify API key is set: echo $ZAI_API_KEY

Search returns no results

DuckDuckGo API may have rate limits
Try with a different query
Check internet connectivity

Summarization fails

Verify API key is valid at https://z.ai/model-api
Check API credits/balance
Ensure URL is accessible

MCP client can't connect

Verify server path in configuration is correct
Ensure Python3 is in system PATH
Check file permissions: chmod +x src/server.py

Debug Mode

Enable debug logging by setting environment variable:

export ZAI_DEBUG=1
python src/server.py

License

MIT License - see LICENSE file for details

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Support

Issues: Report bugs and feature requests on GitHub Issues
ZAI API Documentation: https://docs.z.ai
MCP Specification: https://modelcontextprotocol.io

Acknowledgments

ZAI for providing the GLM-4.7-Flash API
DuckDuckGo for the search API
Model Context Protocol team for the specification

zai-mcp-server

ZAI MCP Server

Features

Tools

search_web

fetch_and_summarize

search_and_summarize

Installation

Prerequisites

Install from source

Quick Start

Configuration

Environment Variables

API Configuration

Usage

Standalone Testing

Integration with Claude Desktop

Integration with Cursor

Integration with Cline (VS Code)

Integration with Continue

Integration with Roo Code

OpenCode Native Integration

Setup

Usage in OpenCode

Examples

Example 1: Web Search

Example 2: Fetch and Summarize

Example 3: Search and Summarize (Combined)

Testing

Development

Project Structure

Dependencies

Troubleshooting

Common Issues

Debug Mode

License

Contributing

Support

Acknowledgments

Reviews

`search_web`

`fetch_and_summarize`

`search_and_summarize`