Credence — Epistemic Guard

Overview

Credence — Epistemic Guard is a Model Context Protocol (MCP) server: Epistemic guard for AI coding: tracks uncertain values and blocks writes until verified. In practice that means any MCP-compatible AI assistant can call Credence — Epistemic Guard's tools directly — the model decides when to use them in a conversation or agent run.

It runs locally: the Python package credence-guard (via uvx) speaks MCP over stdio on your machine. No credentials are required — it works out of the box. The current release is v1.2.5, with source at Lakshmi-Chakradhar-Vijayarao/credence-ai on GitHub.

Credence — Epistemic Guard is listed under AI & Agents on mcp.site and works with any MCP client — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed and the rest of the ecosystem — using the install snippets below. If you maintain Credence — Epistemic Guard for Lakshmi-Chakradhar-Vijayarao, claim this listing to verify ownership, earn the Verified badge, and keep the details current.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "credence_epistemic_guard": {
      "command": "uvx",
      "args": [
        "credence-guard"
      ]
    }
  }
}