DCL Trust Oracle MCP Server

Name: DCL Trust Oracle MCP Server
Author: Fronesis Labs

@Fronesis Labs

リポジトリホームページドキュメント

基本情報

カテゴリ

開発者ツール

ライセンス

NOASSERTION

トランスポート

stdio

作者

Fronesis Labs

投稿者

Dari Rinch

DCL Trust Oracle MCP Server について

DCL Evaluator — cryptographic audit trail for AI agents. Powered by Leibniz Layer™

##audit #cryptography #ai-agents #mcp #x402

DCL Trust Oracle MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "dcl-trust-oracle": {
      "url": "https://mcp.fronesislabs.com/mcp"
    }
  }
}

DCL Trust Oracle MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

上のボタンでサーバーのエンドポイントに接続し、ツール一覧を取得できます。

概要

What is DCL Trust Oracle?

DCL Trust Oracle is a hosted MCP server from Fronesis Labs. It evaluates a proposed AI-agent output against policy and appends a hash-chained audit record. Built on the Deterministic Commitment Layer (DCL) and the Leibniz Layer protocol.

How to connect

Add the server to any MCP client that supports Streamable HTTP:

{
  "mcpServers": {
    "dcl-trust-oracle": {
      "url": "https://mcp.fronesislabs.com/mcp"
    }
  }
}

Then call tools/list. Tool names, schemas, prices, and payment requirements come from that response.

Payment

Paid tools settle in USDC on Base through x402, per call. There is no API key and no account. A client that cannot pay receives Payment Required and no verdict.

Verification

Records can be re-checked locally and for free with dcl-core (Python) or @fronesis-labs/dcl-sdk (TypeScript).

Scope

Connecting a client evaluates the calls that client makes. It does not intercept every action in an agent runtime. A clean local check means the supplied records still match their stored hashes. It does not prove that an upstream verdict was the right verdict.

「開発者ツール」の他のコンテンツ

Meticulous

Capgo MCP

Cap-go

Console, Backend and CLI to manage Capgo Instant update and Native build for Capacitor apps Build and upload to app store your mobile app

Collide MCP

Lithometric Inc. | Collide Inc.

Collide is the multiplayer layer for AI coding agents, and it pays for itself. Expert orchestration across every agent on your repo saves teams tens to hundreds of dollars a day in token burn. Run Claude Code, Codex, Cu

Foremerge

naw103

Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git.

SSH MCP Server

hypnosis

SSH MCP server for AI agents: remote commands, file transfer, log search and server audits through OpenSSH.