DCL Evaluator MCP Server

1

Add it to Claude Code

Run this in a terminal.

Run in terminal
claude mcp add --transport http -H "x-api-key: your-key" dcl-evaluator https://mcp.fronesislabs.com/sse
Required:x-api-key
README.md

Cryptographic audit trail for AI agents. Powered by Leibniz Layer™

DCL Evaluator

Cryptographic audit trail for AI agents. Powered by Leibniz Layer™

Every decision your AI agent makes — sealed, verified, auditable.

DCL Evaluator is the first implementation of Leibniz Layer™ — a cryptographic verification protocol for AI agent decisions. It brings deterministic, tamper-evident audit trails to any LLM-powered system.


Why DCL Evaluator

AI agents make decisions. Those decisions carry risk — legal, financial, reputational. Yet most AI systems are black boxes: no record of what was decided, why, or whether the decision was tampered with afterward.

DCL Evaluator solves this with a simple principle borrowed from cryptography: commit every decision into a hash chain. Modify any past record and the entire chain invalidates. Mathematical proof of integrity — no trust required.


Core capabilities

  • SHA-256 hash chain — every agent action cryptographically sealed
  • Merkle tree audit trail — tamper-evident by design
  • Deterministic policy engine — identical input = identical decision, 100% reproducible
  • Drift detection — statistical Z-test catches behavioural drift before it becomes a compliance failure
  • Multi-LLM support — Claude, GPT-4, Grok, Gemini, DeepSeek, Ollama (local, air-gapped)
  • MCP server — connect any agent in minutes via Model Context Protocol
  • Compliance reports — tamper-evident PDF export, ready for regulators
  • Offline-capable — runs fully air-gapped, zero data leaves your infrastructure

💳 Pay-per-Audit via x402

DCL Evaluator supports the x402 payment protocol.
AI agents can request audits autonomously — no API keys, just HTTP 402 + USDC on Base.

Endpoint: https://x402.fronesislabs.com
Network: Base Mainnet (eip155:8453)

Tool Price Margin
Quick Scan $1 USDC 99%
Standard Audit (4 models) $5 USDC 99.4%
Deep Audit + PoC $15 USDC 99.3%

Any agent that speaks HTTP can pay for and receive a cryptographic audit — no human required.


Connect via MCP

{
  "mcpServers": {
    "dcl-evaluator": {
      "url": "https://mcp.fronesislabs.com/sse",
      "headers": {
        "x-api-key": "your-key"
      }
    }
  }
}

Four tools available:

Tool Description
dcl_commit Seal an agent action into the hash chain
dcl_verify Verify chain integrity
dcl_get_chain Retrieve full audit trail
dcl_report Generate compliance report

Health check: https://mcp.fronesislabs.com/health


Download

Latest release — v1.2.0

Desktop app (Windows). Wails + Go + React. Works offline.


Compliance coverage

Built-in policy templates:

DEFAULT · EU AI ACT · GDPR · FINANCE · MEDICAL · RED TEAM


Leibniz Layer™

DCL Evaluator is the first product implementing Leibniz Layer™ — the cryptographic verification layer for the AI agent economy.

Named after Gottfried Wilhelm Leibniz — mathematician, logician, pioneer of deterministic reasoning.

"Every decision, every action deterministically sealed, tamper-evident, auditable."

leibniz.fronesislabs.com


Links


© 2026 Fronesis Labs · Leibniz Layer™, DCL Evaluator™ — Patent Pending · Source-Available License

Tools (4)

dcl_commitSeal an agent action into the hash chain
dcl_verifyVerify chain integrity
dcl_get_chainRetrieve full audit trail
dcl_reportGenerate compliance report

Environment Variables

x-api-keyrequiredAPI key for accessing the DCL Evaluator SSE endpoint

Configuration

claude_desktop_config.json
{"mcpServers": {"dcl-evaluator": {"url": "https://mcp.fronesislabs.com/sse", "headers": {"x-api-key": "your-key"}}}}

Try it

Commit the last decision made by the agent to the DCL hash chain.
Verify the integrity of the current audit trail to ensure no tampering has occurred.
Retrieve the full audit trail for the recent agent session.
Generate a compliance report for the latest agent actions in PDF format.

Frequently Asked Questions

What are the key features of DCL Evaluator?

SHA-256 hash chain for cryptographically sealing agent actions. Merkle tree audit trail for tamper-evident logging. Deterministic policy engine for 100% reproducible decisions. Statistical Z-test drift detection for behavioral monitoring. Compliance report generation with tamper-evident PDF export.

What can I use DCL Evaluator for?

Maintaining regulatory compliance for AI agents in finance and medical sectors. Providing verifiable audit trails for autonomous AI decision-making processes. Detecting behavioral drift in AI agents before it leads to compliance failures. Ensuring data integrity in air-gapped or offline AI infrastructure.

How do I install DCL Evaluator?

Install DCL Evaluator by running: https://mcp.fronesislabs.com/sse

What MCP clients work with DCL Evaluator?

DCL Evaluator works with any MCP-compatible client including Claude Desktop, Claude Code, Cursor, and other editors with MCP support.

Turn this server into reusable context

Keep DCL Evaluator docs, env vars, and workflow notes in Conare so your agent carries them across sessions.

Need the old visual installer? Open Conare IDE.
Open Conare