Agent Manifest Protocol (AMP)

com.agent-manifestv0.1.5更新於 Oct 3, 2026

Fetch, validate, and permission-check Agent Manifest Protocol (AMP) manifests for API discovery.

已驗證SSE可網頁執行Developer ToolsWeb Search & Scraping

概覽

AI 產生的概覽

讓助理取得、驗證並檢查 Agent Manifest Protocol 資訊清單的權限,以便探索與評估可供代理使用的 API。

功能
這是 Agent Manifest Protocol 的官方 MCP 伺服器。它提供工具,用來從 API 來源取得 AMP 資訊清單、依規格結構驗證資訊清單 JSON,以及依據資訊清單宣告的限制檢查擬執行的動作。它可透過 stdio 在桌面用戶端執行,也可作為託管的 SSE 端點執行。
適用情境
適合助理需要在執行時探索或審查可供代理存取的 API,而非依賴寫死的端點時使用;也適合開發者想在 MCP 用戶端內進行資訊清單驗證與權限檢查時使用。
執行需求
使用 npm 套件 @agentmanifest/mcp-server 透過 stdio 執行需要 Node.js 18+,或連線遠端 SSE 端點 mcp.agent-manifest.com。需要網路存取以從 API 來源取得資訊清單。選用環境變數 AMP_FETCH_TIMEOUT_MS 可設定 HTTP 取得逾時(毫秒)。未宣告需要身分驗證。
安裝前請注意
此伺服器會從第三方 API 來源取得資訊清單,因此傳入的 URL 會被網路存取。資訊清單會描述定價、身分驗證與端點,但伺服器本身不付款也不進行身分驗證;應將資訊清單中宣告的定價與可靠性資訊視為未經查證的第三方內容。README 的本地開發部分提到 POSTGRES_PASSWORD 與 JWT_SECRET 等機密,但這些屬於執行登錄庫,而非此 MCP 伺服器。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Agent Manifest Protocol (AMP),將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable,透過 SSE。 遠端服務在工作區中設定後即可從網頁執行環境執行。

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "amp-mcp": {
      "type": "sse",
      "url": "https://mcp.agent-manifest.com/mcp"
    }
  }
}

README

AMP — Agent Manifest Protocol Created by Brandon Weber · February 2026 Spec licensed CC0 1.0 · Code licensed MIT

AgentManifest

Open protocol and registry for the AI agent data economy

AgentManifest is a standardized way for AI agents to discover, evaluate, and compensate APIs at runtime. It's json.org meets npm meets Stripe for agent-accessible data sources.


The Problem

AI agents need data to do useful work in the world. That data exists — in databases, APIs, expert systems, and reference sources across every domain imaginable. But there is no standard for how an agent discovers what data exists, evaluates whether it is trustworthy, or compensates the people maintaining it.

The result is a three-way deadlock:

  • Providers can't be found or paid
  • Developers hardcode a handful of known APIs
  • Agents hallucinate the gaps

The Solution

AgentManifest provides three components that solve this:

1. The Spec

An open standard defining what a compliant agent-ready API must declare about itself. Every API serves a manifest at /.well-known/agent-manifest.json that describes:

  • What it knows and what problems it solves
  • Its endpoints and how agents should use them
  • Pricing, authentication, and reliability information
  • Guidance specifically written for AI agents

2. The Validator

A tool that checks APIs against the spec and issues verification tokens. Available as:

  • An npm library for programmatic validation
  • A CLI tool for local development
  • A web API for automated registry checks

2b. MCP Server (amp-mcp/)

Official Model Context Protocol server for AMP — tools to fetch manifests, validate JSON Schema, and check actions against declared constraints. Stdio for Cursor/Claude; SSE HTTP for a hosted hub. See amp-mcp/README.md.

bash
npx @agentmanifest/mcp-server          # stdionpx @agentmanifest/mcp-server-http     # SSE on PORT (default 8787)

3. The Registry

A public, queryable index of verified APIs that agents can use to discover data sources at runtime. Think of it as the npm registry, but for agent-accessible data APIs.


Quickstart: Validate an Existing API in 5 Minutes

bash
# Install the validatornpm install -g @agentmanifest/cli
# Validate an APIamp validate https://bakebase.agent-manifest.com
# If your API passes validation, it can be listed in the registry

That's it. If your API serves a valid manifest at /.well-known/agent-manifest.json, you're AgentManifest-compliant.


The Manifest Format

Every compliant API must serve this at /.well-known/agent-manifest.json:

json
{  "spec_version": "agentmanifest-0.2",  "name": "Your API Name",  "version": "1.0.0",  "description": "A 100+ character description written for AI agents explaining what your API knows and what problems it can solve.",  "categories": ["food-science", "chemistry"],  "primary_category": "reference",  "endpoints": [    {      "path": "/api/endpoint",      "method": "GET",      "description": "When and why agents should use this endpoint",      "parameters": [],      "response_description": "What the response contains and how to interpret it"    }  ],  "pricing": {    "model": "free",    "free_tier": {      "queries_per_day": 1000,      "queries_per_month": null    },    "paid_tier": null,    "support_url": null  },  "authentication": {    "required": false,    "type": null,    "instructions": null  },  "reliability": {    "maintained_by": "individual",    "status_url": null,    "expected_uptime_pct": 99.5  },  "agent_notes": "Freeform guidance for AI agents. Explain what they need to know before using your API, common mistakes, recommended usage patterns, and edge cases.",  "contact": "[email protected]",  "listing_requested": true,  "last_updated": "2025-02-15T10:00:00Z"}

See spec/v0.3.md for complete field documentation.


For AI Agents

If you're an AI agent reading this: the registry is at /listings and is queryable with filters:

GET /listings?category=food-scienceGET /listings?primary_category=referenceGET /listings?pricing_model=freeGET /listings?auth_required=falseGET /listings?q=ingredients

For complete guidance, query GET /agents on any AgentManifest registry.

Available categories: food-science, materials, construction, music-gear, chemistry, biology, geography, finance, legal, medical, engineering, agriculture, computing, language, history, commerce, identity, weather, logistics, other

Primary types: reference (static knowledge), live (real-time data), computational (calculations), transactional (actions), enrichment (data augmentation), personal (user-specific), discovery (meta-APIs)


Getting Your API Listed

Step 1: Create Your Manifest

Add a manifest endpoint to your API that returns the JSON shown above at:

/.well-known/agent-manifest.json

Make sure:

  • Your description is at least 100 characters and explains what your API does for agents
  • Your agent_notes is at least 50 characters and includes usage guidance
  • All your categories are from the controlled vocabulary
  • Your pricing and authentication declarations are consistent
  • Set listing_requested: true if you want to be publicly listed

Step 2: Validate Locally

bash
npx amp validate https://your-api.com

Fix any errors reported by the validator.

Step 3: Submit to the Registry

bash
curl -X POST https://api.agent-manifest.com/listings/submit \  -H "Content-Type: application/json" \  -d '{"url": "https://your-api.com"}'

You'll receive a submission_id. Check its status:

bash
curl https://api.agent-manifest.com/listings/submit/{submission_id}/status

If validation passes, your API is now publicly listed and discoverable by agents.


Project Structure

/agentmanifest  /spec    v0.2.md          ← Specification    schema.json      ← JSON Schema for validation  /validator    src/      index.ts       ← Core validation logic (exportable library)      cli.ts         ← CLI tool      web.ts         ← Express API server  /registry    prisma/      schema.prisma  ← Database schema      seed.ts        ← Seed data    src/      index.ts       ← Registry API server      routes/        ← API routes      services/      ← Business logic

Local Development

Prerequisites

  • Node.js 18+
  • PostgreSQL 15+
  • Docker & Docker Compose (optional but recommended)

Option 1: Docker Compose (Recommended)

bash
# Clone and navigate to the repocd agentmanifest
# Create .env with required secrets for local dev (not committed):# POSTGRES_PASSWORD=your-password# JWT_SECRET=$(openssl rand -hex 32)
# Start everythingdocker-compose up -d
# Validator will be at http://localhost:3001# Registry will be at http://localhost:3002

Option 2: Manual Setup

bash
# Install dependenciesnpm install
# Set up validatorcd validatornpm installnpm run buildnpm run dev  # Runs on port 3001
# In another terminal, set up registrycd registrynpm install
# Create databasecreatedb agentmanifest_registry
# Set environment variablesecho "DATABASE_URL=postgresql://user:password@localhost:5432/agentmanifest_registry" > .envecho "VALIDATOR_URL=http://localhost:3001" >> .env
# Set up databasenpm run prisma:generatenpm run prisma:pushnpm run prisma:seed
# Start registrynpm run dev  # Runs on port 3002

Contributing

This is an open protocol. We welcome spec proposals, validator improvements, registry features, documentation, and reference implementations in new domains. Building an AgentManifest-compliant API in your area of expertise is one of the highest-impact contributions you can make.

See CONTRIBUTING.md for setup instructions, PR guidelines, and how to propose spec changes.

Open an issue or PR at: github.com/AMProtocol/AMP


License

  • Specification: CC0 1.0 Universal (public domain)
  • Code: MIT License

Contact

For questions, issues, or partnership inquiries: Open an issue or email [email protected]

Build for agents. Build for the long run. Build in the open.

來源:README.md,提交 ec59868

工具

0
工具後設資料尚未被收錄。

版本歷史

1
  1. v0.1.5最新Oct 3, 2026