TFT MCP Server

What does “TFT” MCP Server do?

The TFT MCP Server is a Model Context Protocol (MCP) server designed for Team Fight Tactics (TFT). It connects AI assistants with the official Riot Games API, enabling access to TFT game data such as player match history and detailed match information. By exposing these functionalities through standardized MCP tools, the server allows AI agents and developers to programmatically query for a player’s recent games or delve into specifics of any TFT match. This integration streamlines workflows for developers who want to build tools or assistants that interact with TFT data, making tasks like analyzing gameplay, tracking performance, or fetching match records more accessible and automated.

List of Prompts

No prompt templates were mentioned in the repository or documentation.

List of Resources

No explicit resources were listed in the repository or documentation.

List of Tools

• tft_match_history
  Retrieves TFT match history for the current player. Supports optional parameters for the number of matches (count, defaults to 20) and pagination (start, defaults to 0).

• tft_match_details
  Fetches detailed information about a specific TFT match, given a required matchId parameter.

Use Cases of this MCP Server

• Player Match History Retrieval
  Developers can build assistants that fetch a user’s recent TFT games, enabling automated stat tracking or game log analysis.
• Match Analytics Tools
  By obtaining detailed match data, developers can create tools that analyze strategies, champion selection, or placement trends for educational or coaching purposes.
• Performance Monitoring
  Assistants can periodically check and summarize a player’s performance over time by aggregating data from multiple matches.
• Event or Tournament Analysis
  Organizers can use the server to analyze player histories and match details for tournament participants, supporting fair play and in-depth event commentary.

How to set it up

Windsurf

No specific installation instructions for Windsurf were found.

Claude

1. Ensure Node.js (v14+) and npm/yarn are installed.
2. Acquire a Riot Games API key from Riot Games Developer Portal.
3. Find your Claude Desktop config file at:
   • MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
   • Windows: %APPDATA%/Claude/claude_desktop_config.json
4. Add the following configuration:

   {
     "mcpServers": {
       "tft-mcp": {
         "command": "npx",
         "args": [
           "mcp-server-tft",
           "--apiKey",
           "<YOUR_RIOT_API_KEY>",
           "--gameName",
           "<YOUR_GAME_NAME>",
           "--tagLine",
           "<YOUR_TAG_LINE>"
         ]
       }
     }
   }
   

5. Save the file and restart Claude.

Securing API Keys:
Use environment variables to keep your API key secure:

{
  "mcpServers": {
    "tft-mcp": {
      "command": "npx",
      "args": [
        "mcp-server-tft"
      ],
      "env": {
        "RIOT_API_KEY": "<YOUR_RIOT_API_KEY>",
        "GAME_NAME": "<YOUR_GAME_NAME>",
        "TAG_LINE": "<YOUR_TAG_LINE>"
      }
    }
  }
}

Cursor

No specific installation instructions for Cursor were found.

Cline

No specific installation instructions for Cline were found.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "tft-mcp": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “tft-mcp” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

| Supports Roots | ⛔ | Not mentioned | | Supports Sampling | ⛔ | Not mentioned |

Our opinion

The TFT MCP Server provides two essential tools for interacting with TFT data, with clear setup instructions for Claude. However, it lacks explicit prompt templates and resources, and platform support details are limited. Sampling and roots support are not mentioned. The project is open source with an MIT license, but documentation could be expanded to cover more platforms and features.

MCP Score

Score: 5/10
This MCP server is functional and open source, but lacks broader documentation, prompt/resource definitions, and explicit support for sampling/roots or multiple platforms.