Skip to main content
Glama
https://github.com/jkingsman/qanon-mcp-server

https://github.com/jkingsman/qanon-mcp-server

by jkingsman

QAnon is a dangerous cult. This archive is for research purposes only, and I do not endorse any material in this repo.

Q-Anon Posts/Drops MCP Server

An MCP (Model Context Protocol) server that provides access to a dataset of Q-Anon posts for anthropological/sociological research. This server allows AI assistants like Claude to search, filter, and analyze the Q-Anon drops.

Posts are drawn from https://github.com/jkingsman/JSON-QAnon. You can learn more about how the source data was composed there, as well as find alternate formats, schemas, etc.

Warning: This tool was entirely vibe coded. Use at your own risk.

Related MCP server: China PolicySignal

Prerequisites

  • Python 3.10 or higher

  • uv package manager

  • Claude Desktop (for Claude integration)

Installation

This tool is compatible with uvx and doesn't need to be cloned/installed.

Installing via Smithery

To install qanon-mcp-server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @jkingsman/qanon-mcp-server --client claude

Manual

  1. Clone or download this repository to your local machine

  2. Install the required packages using uv:

uv pip install -e .

Usage

You can run the server directly with uvx:

uvx qanon_mcp

Claude Desktop Integration

To use this MCP server with Claude Desktop:

  1. Make sure you have Claude Desktop installed

  2. Open the Claude menu and select "Settings..."

  3. Click on "Developer" in the left-hand bar and then "Edit Config"

  4. Add the following configuration to the claude_desktop_config.json file:

{
  "mcpServers": {
    "qanon_mcp": {
      "command": "uvx",
      "args": [
        "qanon_mcp"
      ]
    }
  }
}

or, if you don't have uvx installed:

{
  "mcpServers": {
    "qanon_mcp": {
      "command": "uv",
      "args": [
        "tool",
        "run",
        "qanon_mcp"
      ]
    }
  }
}
  1. Save the file and restart Claude Desktop

  2. Start a new conversation in Claude Desktop

  3. You should see a hammer icon in the input box, indicating that tools are available

Features

Resources

  • qanon://posts/count - Get the total number of posts

  • qanon://posts/{post_id} - Access a specific post by ID

  • qanon://posts/raw/{post_id} - Get the raw JSON data for a specific post

  • qanon://authors - List all unique authors

  • qanon://stats - Get dataset statistics

Tools

  • get_post_by_id_tool - Retrieve a specific post by its ID

  • search_posts - Find posts containing specific keywords or phrases

  • get_posts_by_date - Retrieve posts from a specific date range

  • get_posts_by_author_id - Find posts by a specific author ID

  • analyze_post - Get detailed analysis of a specific post including references and context

  • get_timeline_summary - Generate a chronological timeline, optionally within a date range

  • word_cloud_by_post_ids - Generate a word frequency analysis for posts within a specified ID range

  • word_cloud_by_date_range - Generate a word frequency analysis for posts within a specified date range

Example Queries for Claude

Once the MCP server is connected to Claude Desktop, you can ask questions like:

  • "How many Q-Anon posts are in the dataset?"

  • "Search for posts that mention 'storm'"

  • "Show me posts from October 2020"

  • "Analyze post #3725"

  • "Create a timeline of Q-Anon posts from 2018"

  • "Generate a word cloud for Q-Anon posts between January and March 2019"

  • "Get the raw data for post #4500"

  • "What are the most common words used in posts #1000-2000?"

Troubleshooting

  • If Claude Desktop doesn't show the hammer icon, check your configuration and restart Claude Desktop

  • Ensure the posts.json file is in the same directory as the script

  • Check the output in the terminal for any error messages

  • Make sure you're using the absolute path to the script in your Claude Desktop configuration

Available Tools

8 tools
analyze_postB
Get detailed analysis of a specific post/drop including references and context.

Args:
    post_id: The ID of the post to analyze

Inputs: post_id (required).

get_post_by_id_toolB
Retrieve a specific post by its ID.

Args:
    post_id: The ID of the post to retrieve

Inputs: post_id (required).

get_posts_by_author_idB
Get posts/drops by a specific author ID.

Args:
    author_id: The author ID to search for
    limit: Maximum number of results to return (default: 10)

Inputs: author_id (required), limit.

get_posts_by_dateB
Get posts/drops within a specific date range.

Args:
    start_date: Start date in YYYY-MM-DD format
    end_date: End date in YYYY-MM-DD format (defaults to start_date if not provided)
    limit: Maximum number of results to return (default: 10)

Inputs: start_date (required), end_date, limit.

get_timeline_summaryB
Get a timeline summary of posts/drops, optionally within a date range.

Args:
    start_date: Optional start date in YYYY-MM-DD format
    end_date: Optional end date in YYYY-MM-DD format

Inputs: start_date, end_date.

search_postsB
Search for posts/drops containing a specific keyword or phrase.

Args:
    query: The keyword or phrase to search for
    limit: Maximum number of results to return (default: 10)

Inputs: query (required), limit.

word_cloud_by_date_rangeB
Generate a word cloud analysis showing the most common words used in posts within a specified date range.

Args:
    start_date: Start date in YYYY-MM-DD format
    end_date: End date in YYYY-MM-DD format
    min_word_length: Minimum length of words to include (default: 3)
    max_words: Maximum number of words to return (default: 100)

Inputs: start_date (required), end_date (required), min_word_length, max_words.

word_cloud_by_post_idsA
Generate a word cloud analysis showing the most common words used in posts within a specified ID range.

Args:
    start_id: Starting post ID
    end_id: Ending post ID
    min_word_length: Minimum length of words to include (default: 3)
    max_words: Maximum number of words to return (default: 100)

Inputs: start_id (required), end_id (required), min_word_length, max_words.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.4/5.0

    Scored across 8 tools

    Disambiguation4/5

    Most tools have distinct purposes: retrieval by ID, author, date, search, timeline summary, and word cloud generation. However, 'analyze_post' and 'get_post_by_id_tool' could cause confusion as both target specific posts, with 'analyze_post' implying deeper analysis but overlapping in core retrieval functionality. The word cloud tools are clearly differentiated by date vs. ID range.

    Naming Consistency3/5

    The naming is mixed: some tools use verb_noun patterns like 'search_posts' and 'analyze_post', while others use noun_verb patterns like 'get_post_by_id_tool' and 'get_posts_by_author_id'. There's inconsistency in verb usage ('get', 'analyze', 'search') and structure, but names remain readable and descriptive overall.

    Tool Count5/5

    With 8 tools, this server is well-scoped for analyzing and retrieving posts/drops in a QAnon context. The count is reasonable, covering key operations like retrieval, search, timeline summary, and word cloud analysis without being overwhelming or too sparse.

    Completeness4/5

    The tool surface is largely complete for a read-only analysis server, covering retrieval by various criteria, search, timeline summaries, and word cloud generation. A minor gap is the lack of update or delete operations, but given the domain (likely analyzing historical data), this is acceptable, and agents can work around it effectively.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      Enables search and discourse analysis over Xi Jinping's publicly available speeches and official statements, including full-text retrieval, phrase-trend tracking, and verbatim quotes with source-linked citations.
      9
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables assistants to directly query a large community archive, including user activity, thread development, and front-page history over decades. It provides read-only access to answer questions about who is most active and how the community has changed.
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Enables AI clients to search, read, and analyze a local SQLite knowledge base built from the full public archives of people you follow, bookmark, or subscribe to, with tools for onboarding, querying, and topic tracking.
      12
      8
      MIT