Malloy MCP Server

@namabile

About Malloy MCP Server

An MCP Server for interacting with Malloy data models through the Malloy Publisher

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "malloy-mcp-server": {
      "command": "uv",
      "args": [
        "pip",
        "install",
        "malloy-mcp-server"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Malloy MCP Server?

An MCP server implementation for executing Malloy queries and managing Malloy resources. It integrates with the Malloy Publisher API and is intended for developers who need to run Malloy queries via the Model Context Protocol.

How to use Malloy MCP Server?

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.

Key features of Malloy MCP Server

Execute Malloy queries via MCP
Access Malloy project, package, and model metadata
Robust error handling with detailed context
Comprehensive test coverage
Type-safe implementation

Use cases of Malloy MCP Server

Execute ad‑hoc Malloy queries through MCP tools
Programmatically inspect project, package, or model metadata
Integrate Malloy querying into AI‑powered workflows
Debug queries with detailed error context

FAQ from Malloy MCP Server

How do I install Malloy MCP Server?

Install with uv pip install malloy-mcp-server or pip install malloy-mcp-server. For development, use uv pip install -e ".[dev]".

How do I configure the Malloy Publisher URL?

Set the MALLOY_PUBLISHER_ROOT_URL environment variable; it defaults to http://localhost:4000.

What dependencies does the server use?

The server is built on FastMCP, the Malloy Publisher Client, and Pydantic for data validation.

How does error handling work?

The server raises a QueryExecutionError with message and context attributes for detailed error context.

Can I run tests?

Yes, run pytest or pytest --cov=malloy_mcp_server for test coverage.

Frequently asked questions

How do I install Malloy MCP Server?

Install with `uv pip install malloy-mcp-server` or `pip install malloy-mcp-server`. For development, use `uv pip install -e ".[dev]"`.

How do I configure the Malloy Publisher URL?

Set the `MALLOY_PUBLISHER_ROOT_URL` environment variable; it defaults to `http://localhost:4000`.

What dependencies does the server use?

The server is built on FastMCP, the Malloy Publisher Client, and Pydantic for data validation.

How does error handling work?

The server raises a `QueryExecutionError` with `message` and `context` attributes for detailed error context.

Can I run tests?

Yes, run `pytest` or `pytest --cov=malloy_mcp_server` for test coverage.

Comments

Basic information

More Other MCP servers

Mcp

browsermcp

Browser MCP is a Model Context Provider (MCP) server that allows AI applications to control your browser

6.8K

ghidraMCP

LaurieWired

MCP Server for Ghidra

9.4K

AutoBrowser MCP

autobrowser-ai

Browser MCP is a Model Context Provider (MCP) server that allows AI applications to control your browser

6.8K

MCP Go 🚀

mark3labs

A Go implementation of the Model Context Protocol (MCP), enabling seamless integration between LLM applications and external data sources and tools.

8.9K

MCP Registry

modelcontextprotocol

A community driven registry service for Model Context Protocol (MCP) servers.

7.0K