Fact Checker MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Fact Checker MCP ServerIs the capital of France Paris?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Fact Checker MCP Server
This is a Model Context Protocol (MCP) server that verifies simple factual claims by checking them against knowledge sources like Wikidata.
Features
Accepts claims in natural language
Verifies the accuracy of the claim
Returns an MCP-compliant response with the claim, correct answer, and confidence score
Includes an MCP client that integrates with Ollama LLM
Related MCP server: Groundcheck
MCP Payload Format
{
"version": "1.0",
"context": {
"type": "fact_check",
"claim": "The capital of France is London",
"correct_answer": "Incorrect. The capital of France is Paris, not London.",
"confidence": 0.95
}
}Setup and Installation
Clone this repository
Install dependencies:
pip install -r requirements.txtRun the server:
python app.py
Usage
Server API
Send a POST request to the /fact-check endpoint with a JSON payload containing the claim:
curl -X POST http://localhost:5000/fact-check \
-H "Content-Type: application/json" \
-d '{"claim": "The capital of France is London"}'MCP Client with Ollama Integration
The project includes an MCP client that demonstrates integration with Ollama LLM:
Make sure Ollama is installed and running:
ollama serveRun the demo script:
bash run_demo.shOr run the client directly:
python mcp_client.py --model llama3
The client will:
Detect factual claims about capitals in your prompts
Verify these claims using the MCP server
Augment the LLM's knowledge with accurate information
Ensure the LLM provides factually correct responses
Testing
Basic Testing
Run the test client with a specific claim:
python test_client.py "The capital of France is Paris"Or run the default test suite with multiple claims:
python test_client.pyComprehensive Test Suite
Run the comprehensive test suite that includes both correct and incorrect claims:
python test_client.py --test-suiteUnit Tests
Run the unit tests to verify the server's functionality:
python -m unittest test_unit.pySupported Claim Types
Currently, the server can verify:
Capital city claims (e.g., "The capital of [Country] is [City]")
More claim types will be added in future updates.
Extending the Server
To add support for new types of claims:
Add a new pattern matching regex in the
check_fact()functionImplement a corresponding verification function similar to
check_capital_claim()
License
Author
© Anthony Lim
This server cannot be deployed
Maintenance
Related MCP Connectors
Cross-check a factual claim against a verified knowledge graph before you assert it. Never guesses.
Check whether a real-world fact can be verified before an agent acts on it. Free, no auth.
Verify claims with verdict, confidence & cited sources; batch verify, source checks, daily brief.
Hallucination & safety checks for LLM/Agent outputs: claim-level fact-check with citations.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables AI agents to fact-check claims, verify citations, and check source freshness using Wikipedia, Wikidata, Crossref, and Wayback Machine.1-
- AlicenseAqualityBmaintenanceVerifies factual claims against live sources and returns a verdict, confidence score, and citations for any agent to use before stating uncertain facts.6MIT
- AlicenseNot gradedqualityBmaintenanceEnables agents to verify claims with evidence-based truth scores and confidence levels by running a deterministic pipeline of evidence lanes and adversarial checks.26MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to verify claims deterministically by computing arithmetic, ratios, and dates and matching statements against provided sources, returning a confidence ladder of certain, source-backed, or unverifiable.MIT