Yelp Fusion

MCP server for exposing tools powered by Yelp's data

python

23

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": {
    "yelp-yelp-mcp": {
      "command": "uv",
      "args": [
        "--directory",
        "<PATH_TO_YOUR_CLONED_PROJECT_DIRECTORY>",
        "run",
        "mcp-yelp-agent"
      ],
      "env": {
        "YELP_API_KEY": "<YOUR_YELP_FUSION_API_KEY>"
      }
    }
  }
}

You can run the Yelp Fusion AI MCP Server locally or in a container to enable natural language queries and real-time business data access in your applications. This server exposes a yelp_agent tool that handles conversational requests and returns both natural language responses and structured business data. Use it to perform searches, answer questions about businesses, and manage multi-turn conversations.

How to use

You interact with the Yelp Fusion AI MCP Server through an MCP client that supports stdio transport. Start the server in your environment, then connect your MCP client to the provided stdio endpoint. Use the yelp_agent tool to ask questions like finding restaurants, checking if a business allows pets, or planning an itinerary. Conversations can span multiple turns using a chat_id to maintain context.

How to install

Prerequisites: ensure you have Python 3.10 or higher and the uv package manager installed.

Step 1. Install dependencies and prepare the environment.

Step 2. Install the MCP server locally.

Additional setup and configuration

Two methods are supported for running the Yelp MCP Server: running without Docker using uv and running with Docker. In both cases you must provide your Yelp Fusion API key for authentication.

Available tools

yelp_agent

Agent tool for natural language requests about local businesses. Supports search, detailed questions, comparisons, itinerary planning, and follow-up queries using chat_id. Returns both natural language responses and structured business data.