Slander

Finds humorous roasts and memes about any character by querying Twitter/X and ranking results by engagement.

javascript

0

GitHub Stars

javascript

Language

5 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": {
    "ebop14-slander_mcp": {
      "command": "node",
      "args": [
        "/path/to/slander_mcp/dist/index.js"
      ],
      "env": {
        "OPENAI_API_KEY": "YOUR_OPENAI_API_KEY",
        "ANTHROPIC_API_KEY": "YOUR_ANTHROPIC_API_KEY",
        "TWITTER_BEARER_TOKEN": "YOUR_TWITTER_BEARER_TOKEN"
      }
    }
  }
}

You run this MCP server to find humorous roasts, jokes, and memes about any character by querying Twitter/X and ranking results by engagement. It helps you automate content discovery, filter for quality, and provide targeted nicknames for in-platform discussions or prompts.

How to use

You use an MCP client to connect to the Slander MCP Server and issue high-level actions like generating search queries, fetching posts, and ranking results. Your goal is to surface top text and media posts about a target, along with nickname ideas, using engagement-based scoring. You can run the local server, supply your API keys, and then query the server for curated content around a character you specify.

How to install

Prerequisites: you need Node.js installed on your machine. You also need API keys for Twitter/X and an LLM provider (Anthropic or OpenAI). Ensure you have a working network connection to reach the Twitter/X API.

Additional configuration and usage notes

Configure environment variables to enable the MCP to access the necessary services. Create a .env file in the project root and include your credentials for the Twitter/X API and an LLM provider. The key names you will use are TWITTER_BEARER_TOKEN, ANTHROPIC_API_KEY, and OPENAI_API_KEY. You can supply at least one LLM API key.

Example workflow

Start the MCP server locally using the provided runtime command and environment variables. 2) Use your MCP client to request content for a target, for example “LeBron James.” 3) The server will generate search queries, fetch posts, and return top text and media posts along with nicknames.

Security and maintenance notes

Keep your API keys secure and do not share them publicly. Rotate keys periodically and monitor usage to avoid unexpected charges. If the Twitter/X API rate limits you, adjust fetch parameters or the number of queries you run.

Available tools

generate_search_query

Generate effective Twitter search queries for finding slander about a target. Input: target name. Output: array of query strings.

fetch_posts

Fetch posts from Twitter for a given query, looping until quality threshold is met. Input: query, loop_limit, count, target. Output: posts with engagement metrics, iterations, stopped_reason.

rank_posts

Rank fetched posts by engagement, separate text from media, extract nicknames. Input: posts, top_n, target. Output: top text posts, top media posts, nicknames.