Malloy MCP Server
About
An MCP Server for interacting with Malloy data models through the Malloy Publisher
Details
- Author
- namabile
- GitHub stars
- 2
- Downloads
- 189
- Categories
- Other
Jump to
- Execute Malloy queries via MCP
- Access Malloy project, package, and model metadata
- Robust error handling with detailed context
- Comprehensive test coverage
- Type-safe implementation
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
Malloy 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 using uv pip install malloy-mcp-server or pip install malloy-mcp-server. Configure the MALLOY_PUBLISHER_ROOT_URL environment variable (default http://localhost:4000). Start the server with mcp.serve() or by running python -m malloy_mcp_server. Use the ExecuteMalloyQueryTool to run queries and access resource endpoints such as malloy://project/home/metadata.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"malloy mcp server": {
"malloy-mcp-server": {
"command": "uv",
"args": [
"pip",
"install",
"malloy-mcp-server"
]
}
}
}
}
McpServers
{
"malloy-mcp-server": {
"command": "uv",
"args": [
"pip",
"install",
"malloy-mcp-server"
]
}
}
Malloy MCP Server
An MCP server implementation for executing Malloy queries and managing Malloy resources.
Features
- Execute Malloy queries via MCP
- Access Malloy project, package, and model metadata
- Robust error handling with detailed context
- Comprehensive test coverage
- Type-safe implementation
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.



