Tavily

Provides Tavily-based web search capabilities via MCP with AI-assisted results and links.

other

0

GitHub Stars

other

Language

7 months ago

First Indexed

3 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": {
    "mcp-mirror-tomatio13_mcp-server-tavily": {
      "command": "uv",
      "args": [
        "--directory",
        "C:\\\\your_path\\\\mcp-server-tavily",
        "run",
        "tavily-search"
      ],
      "env": {
        "TAVILY_API_KEY": "YOUR_TAVILY_API_KEY",
        "PYTHONIOENCODING": "utf-8"
      }
    }
  }
}

You run an MCP server that uses the Tavily API to perform searches and return results in text form. This enables you to query broad sources and receive AI-assisted responses, including titles and URIs, all orchestrated through a dedicated MCP endpoint that your client can call to perform searches.

How to use

Use your MCP client to list available tools on the Tavily search server, then call the search tool with your query. You can control the depth of the search by choosing the basic or advanced mode if your client exposes that option. The server returns a structured response that includes AI-generated content and relevant links to search results.

Typical usage pattern:

Discover tools provided by the Tavily search server.
Invoke the search tool with a natural language query, optionally specifying a depth level.
Parse the text output to extract the AI response and the list of search results with titles and URLs.

How to install

mcpServers:
  tavily_search:
    type: stdio
    command: uv
    args:
      - "--directory"
      - "C:\\your_path\\mcp-server-tavily"
      - "run"
      - "tavily-search"
    env:
      - name: TAVILY_API_KEY
        value: "YOUR_TAVILY_API_KEY"
      - name: PYTHONIOENCODING
        value: "utf-8"

Configuration and notes

Prerequisites: ensure you have a runtime capable of running the MCP server as shown. You will need a local copy of the server project and access to configure environment variables for API access.

Steps you will follow:

Clone the server repository.
Create or edit the configuration to specify how to start the Tavily search server.
Provide your Tavily API key in the environment so the server can authenticate with Tavily.
Restart the runtime to apply the configuration.

Available tools

search

Performs searches using the Tavily API and returns results in text form, including AI responses, URIs, and titles.