mcp-contradiction-check
Scans markdown vaults to detect contradictory claims (quantitative and negation) between notes with high concept overlap, and provides tools for analysis and reconciliation.
README
<!-- mcp-name: io.github.onetrueclaude-creator/mcp-contradiction-check -->
mcp-contradiction-check
Find where your notes disagree — contradiction detection for markdown vaults.
Find pairs of notes in your markdown knowledge base that have high concept overlap but disagree — quantitative conflicts (different numbers with the same unit on the same concept) and negation conflicts (one note claims "X is not Y", another claims "X is Y"). Prevents knowledge corruption by surfacing disputes before they propagate. Designed to pair with hebbian-vault's usage-weighted retrieval to flag notes that shouldn't be strengthened yet.
Install
pip install mcp-contradiction-check
# or
uvx mcp-contradiction-check
Usage
Claude Code
claude mcp add mcp-contradiction-check -- mcp-contradiction-check
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"contradiction_check": {
"command": "uvx",
"args": ["mcp-contradiction-check"]
}
}
}
MCP Tools
| Tool | Tier | Description |
|---|---|---|
find_contradictions |
Free | Scan the vault for note pairs with high concept overlap but conflicting numerical or qualitative claims. Returns all detected conflicts with the specific issues flagged. |
check_pair |
Free | Run the full contradiction check between two specific notes (by path or filename stem). Returns the detailed conflict analysis — shared concepts, quantitative conflicts, negation conflicts. |
extract_claims |
Pro | Pull all quantitative claims (numbers with units) and negation patterns from a single note. Useful as input to your own verification pipeline. |
generate_reconciliation_prompt |
Pro | For a detected contradiction, produce a structured prompt you can feed to an LLM to reason through the conflict and suggest a resolution. Preserves the exact claims + shared concepts + both notes' context windows. |
Pro tier
Unlocks detailed claim extraction per note and LLM-ready reconciliation prompt generation for resolving disputes.
License activation — any one of these works:
# 1. Environment variable
export CONTRADICTION_CHECK_LICENSE="eyJhbGc..."
# 2. CLI flag
mcp-contradiction-check --license-key "eyJhbGc..."
# 3. Config file
echo "eyJhbGc..." > ~/.mcp-contradiction-check/license.jwt
Licenses are verified fully offline — no phone-home, no activation server. Get a license at https://github.com/onetrueclaude-creator/mcp-contradiction-check#pro-tier.
Requirements
- Python 3.10+
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.