ChEMBL-MCP-Server
About
🔍 Enable AI assistants to search, access, and analyze ChEMBL through a simple MCP interface.
Details
- Author
- JackKuo666
- Downloads
- 169
- Categories
- Other
Jump to
- Complete API access to the ChEMBL database
- Asynchronous API calls using the FastMCP framework
- Built-in error handling and timeout mechanisms
- Support for both HTTP and stdio transport methods
- Full type annotations and docstrings
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
ChEMBL-MCP-ServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install dependencies with pip install -r requirements.txt, then start the server by running python chembl_searver.py. You can configure the host, port, transport method, and log level using command-line arguments such as --host, --port, --transport, and --log-level.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"chembl-mcp-server": {
"ChEMBL-MCP-Server": {
"command": "python",
"args": [
"chembl_searver.py"
]
}
}
}
}McpServers
{
"ChEMBL-MCP-Server": {
"command": "python",
"args": [
"chembl_searver.py"
]
}
}ChEMBL-MCP-Server
A FastMCP wrapper server based on the chembl_webresource_client package, providing API access to the ChEMBL database.
Features
- Complete API access to the ChEMBL database
- Asynchronous API calls implemented using FastMCP framework
- Built-in error handling and timeout mechanisms
- Support for both HTTP and stdio transport methods
- Complete type annotations and docstrings
Installation
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
