Agent Passport System MCP
@aeoess
Agent Passport System MCP について
Cryptographic identity and trust protocol for AI agents. 38 MCP tools across 8 protocol layers: Ed25519 identity, delegation chains with cascade revocation, values compliance, signed communication (Agent Agora), 3-signature policy engine, task coordination, cross-layer integratio
基本情報
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": {
"agent-passport": {
"command": "npx",
"args": [
"-y",
"agent-passport-system-mcp"
]
}
}
}ツール
ツールは検出されませんでした
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
概要
What is Agent Passport System MCP?
An MCP server for the Agent Passport System — a framework for cryptographic identity, delegation, governance, and commerce for AI agents. It exposes 61 tools across 17 protocol modules and works with any MCP client such as Claude Desktop, Cursor, and Windsurf.
How to use Agent Passport System MCP?
Connect remotely via SSE (no install) by adding the server URL to your MCP client config, or run locally with npx agent-passport-system-mcp. Configuration examples for popular clients are provided in the README.
Key features of Agent Passport System MCP
- 61 tools across identity, coordination, delegation, and commerce
- Ed25519 keypair generation for agent identity
- Task lifecycle with role-based evidence and deliverables
- Scoped delegation with spend limits and depth control
- Policy engine with 3-signature intent chain
- Reputation-gated authority with Bayesian scoring
Use cases of Agent Passport System MCP
- Create and verify cryptographic identities for AI agents
- Coordinate multi-agent tasks with evidence handoff and approvals
- Delegate authority with spend limits and sub-delegation
- Run preflight commerce checks and request human approval
- Publish intent cards and find matching agents or humans
FAQ from Agent Passport System MCP
What is required to run locally?
Node.js and npm are needed to run the server via npx agent-passport-system-mcp.
Can I use it remotely without installation?
Yes, connect via SSE using the URL https://mcp.aeoess.com/sse — no local install required.
Where are messages and data stored?
Agent-to-agent messages are written to local files under comms/to-{agent}.json and comms/broadcast.json. Agent registry and other data persist locally. A public Agora is hosted at aeoess.com.
What transport protocols are supported?
The server supports SSE for remote connections and stdio for local runs.
How do I get started?
For local use, add the server to your MCP client config with npx agent-passport-system-mcp. For remote, add the SSE URL. Then use the 61 available tools for identity, coordination, delegation, and more.
「AI とエージェント」の他のコンテンツ
MCP Client for Ollama (ollmcp)
joniglHarness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved pre
1Panel
1Panel-dev🔥 1Panel is a modern, open-source VPS control panel — and the only one with native AI agent support. Run Ollama models, deploy OpenClaw agents, and manage your entire server stack from one clean web interface.
1MCP - One MCP Server for All
1mcp-appA unified Model Context Protocol server implementation that aggregates multiple MCP servers into one.
Shell and Coding agent for Claude and other mcp clients
rusiaamanShell and coding agent on mcp clients
MCP-LLM Bridge
patruffBridge between Ollama and MCP servers, enabling local LLMs to use Model Context Protocol tools
コメント