Skip to main content
Glama
steveswain14

Grounding Enforcer

by steveswain14
README.md
![Version](https://img.shields.io/badge/version-v1.0.0-blue)
![License](https://img.shields.io/badge/license-Apache--2.0-green)
![Release](https://img.shields.io/github/v/release/steveswain14/mcp-grounding-enforcer)

# Grounding Enforcer (MCP)

A standalone MCP server that validates model output against retrieved sources. It flags any claim, statistic, attribution, quote, or URL that cannot be traced back to a real source.

This repository contains the full implementation, including all grounding checks, violation logic, and output-cleaning modes. It runs independently and does not depend on the full suite.

## Usage

Add this server to your MCP client configuration (Claude Desktop, Cursor, Windsurf, or any MCP‑compatible environment):

{
  "mcpServers": {
    "grounding_enforcer": {
      "command": "python3",
      "args": ["/path/to/mcp-grounding-enforcer/server.py"]
    }
  }
}

## Modes

- strict — removes sentences containing ungrounded spans  
- lenient — rewrites ungrounded spans with hedging  
- all (default) — removes fabricated retrieval claims only  

## Relationship to the full suite

This suppressor is also included in the consolidated mcp-hallucination-suite, which bundles all four suppressors and provides a meta-orchestrator:
https://github.com/steveswain14/mcp-hallucination-suite

## Related repositories
- mcp-prompt-suppressor
- mcp-json-suppressor
- mcp-tool-response-suppressor