Back to Browse

Proof Layer MCP Server

Developer ToolsModerate5.0MCP RegistryLocal
Free

Server data from the Official MCP Registry

Signed, hash-chained provenance receipts for AI agent actions.

About

Signed, hash-chained provenance receipts for AI agent actions.

Security Report

5.0
Moderate5.0Moderate Risk

This is a well-architected MCP server for cryptographic governance receipts with solid security practices. Authentication via API key is properly enforced, code is clean and input-validated, and permissions align with the server's purpose (network access for API calls, file I/O for install tracking). The telemetry implementation is transparent with a clear opt-out mechanism. Minor code quality notes around error handling and logging do not materially impact security. Supply chain analysis found 3 known vulnerabilities in dependencies (0 critical, 2 high severity). Package verification found 1 issue.

6 files analyzed · 8 issues found

Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.

Permissions Required

This plugin requests these system permissions. Most are normal for its category.

env_vars

Check that this permission is expected for this type of plugin.

file_system

Check that this permission is expected for this type of plugin.

HTTP Network Access

Connects to external APIs or services over the internet.

What You'll Need

Set these up before or after installing:

Your Proof Layer API key from https://prooflayer.world999labs.com/dashboard/keysRequired

Environment variable: PROOF_LAYER_API_KEY

Override the default API endpoint (default: https://prooflayer.world999labs.com)Optional

Environment variable: PROOF_LAYER_API_URL

Set to 'off' to disable anonymous usage telemetry (default: on)Optional

Environment variable: PROOF_LAYER_TELEMETRY

How to Install

Add this to your MCP configuration file:

{
  "mcpServers": {
    "io-github-world-999-labs-proof-layer": {
      "env": {
        "PROOF_LAYER_API_KEY": "your-proof-layer-api-key-here",
        "PROOF_LAYER_API_URL": "your-proof-layer-api-url-here",
        "PROOF_LAYER_TELEMETRY": "your-proof-layer-telemetry-here"
      },
      "args": [
        "-y",
        "@proof-layer/mcp"
      ],
      "command": "npx"
    }
  }
}

Documentation

View on GitHub

From the project's GitHub README.

Proof Layer

@proof-layer/mcp @proof-layer/verify License: MIT MCP compatible Live deployment

Cryptographic governance receipts for AI agents. Issued before the agent acts. Ed25519-signed. Hash-chained. Verifiable offline.

Built by WORLD999_LABS. Published on npm under @proof-layer/*. The legacy @veridocs/* package names continue to resolve and forward to the new ones.


What this repo contains

This is the public half of Proof Layer — the parts you install and run on your own machine:

PackageWhat it doesnpm
@proof-layer/mcpMCP server for Claude Desktop, Cursor, Cline, and any MCP-aware hostnpm
@proof-layer/verifyStandalone offline verifier — zero dependencies, audits any receipt bundle with just our public keynpm

The kernel (governance engine, Gauntlet adversary/judge pipeline, billing, dashboard) is closed-source and runs at prooflayer.world999labs.com. Open-source clients + closed-source server is the same pattern Stripe, Resend, and Vercel use — you get full transparency on what runs locally and what data leaves your machine, while the proprietary server logic stays protected.


Quick start

npx -y @proof-layer/mcp@latest

Drop into Claude Desktop's claude_desktop_config.json:

{
  "mcpServers": {
    "proof-layer": {
      "command": "npx",
      "args": ["-y", "@proof-layer/mcp@latest"],
      "env": {
        "PROOF_LAYER_API_KEY": "pl_live_...",
        "PROOF_LAYER_API_URL": "https://prooflayer.world999labs.com"
      }
    }
  }
}

Restart Claude. Eight pl_* tools appear in the picker. Get an API key at prooflayer.world999labs.com.

Migrating from @veridocs/mcp? No code changes required. The legacy package name continues to resolve, the legacy vd_* tool names continue to work alongside pl_*, and existing VERIDOCS_API_KEY / VERIDOCS_API_URL environment variables are still accepted. You can switch the package name and env-var names on your own schedule.


Why pre-execution governance?

Most "AI safety" tools run after the model has acted — toxicity filters, output classifiers, post-hoc audit logs. By the time the alarm fires, the agent has already sent the email, merged the PR, or executed the trade.

Proof Layer flips this:

  1. Agent proposes an action (e.g. "send wire transfer for $50,000")
  2. Proof Layer evaluates → returns signed verdict: EXECUTE / BLOCK / REVIEW / SHADOW
  3. Receipt is written to a hash-chained, Ed25519-signed audit trail
  4. Anyone with our public key can verify the entire chain offline — no trust in our infra required

A broken hash chain = tampering, immediately visible. A missing receipt = the agent acted without permission.


Verifying receipts offline

Receipts are designed to outlive us. Here's how to verify a bundle without ever calling our API:

import { verifyBundle } from "@proof-layer/verify";
import fs from "fs";

const bundle = fs.readFileSync("./receipts.ndjson", "utf8");
const publicKey = fs.readFileSync("./prooflayer-public-key.pem", "utf8");

const result = verifyBundle(bundle, publicKey);
console.log(result);
// { pass: 147, fail: 0, total: 147, chainBroken: false }

Public key is published at prooflayer.world999labs.com/v1/public-key and rotates on a published schedule.


Resources


License

MIT — see LICENSE.

The kernel and dashboard are proprietary and not included in this repo. The MCP server, verifier, and all client SDKs published under @proof-layer/* (and the legacy @veridocs/* names) are MIT-licensed.


Contributing

Pull requests, issues, and feedback welcome. See CONTRIBUTING.md.

Reviews

No reviews yet

Be the first to review this server!