
Agent Manifest Protocol (AMP)
com.agent-manifestv0.1.5Updated Oct 3, 2026
Fetch, validate, and permission-check Agent Manifest Protocol (AMP) manifests for API discovery.
Overview
Lets an assistant fetch, validate, and permission-check Agent Manifest Protocol manifests so it can discover and evaluate agent-ready APIs.
- What it does
- The official MCP server for the Agent Manifest Protocol. It provides tools to fetch AMP manifests from API origins, validate manifest JSON against the spec schema, and check proposed actions against the constraints a manifest declares. It can run over stdio for desktop clients or as a hosted SSE endpoint.
- When to use it
- Useful when an assistant needs to discover or vet agent-accessible APIs at runtime rather than relying on hardcoded endpoints, or when a developer wants manifest validation and permission checks inside an MCP client.
- Requirements
- Node.js 18+ for the npm package @agentmanifest/mcp-server over stdio, or a connection to the remote SSE endpoint at mcp.agent-manifest.com. Network access to fetch manifests from API origins. Optional environment variable AMP_FETCH_TIMEOUT_MS sets the HTTP fetch timeout in milliseconds. No authentication is declared.
Installation
In SourceWeft
- Open Agent Manifest Protocol (AMP) in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Web executable via SSE. Remote servers run from the web runtime once configured in a workspace.
Other MCP clients
Add this to your client's mcpServers config.
{
"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.
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
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:
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:
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:
Make sure:
- Your
descriptionis at least 100 characters and explains what your API does for agents - Your
agent_notesis 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: trueif you want to be publicly listed
Step 2: Validate Locally
Fix any errors reported by the validator.
Step 3: Submit to the Registry
You'll receive a submission_id. Check its status:
If validation passes, your API is now publicly listed and discoverable by agents.
Project Structure
Local Development
Prerequisites
- Node.js 18+
- PostgreSQL 15+
- Docker & Docker Compose (optional but recommended)
Option 1: Docker Compose (Recommended)
Option 2: Manual Setup
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.
Source: README.md at commit ec59868
Tools
0Version history
1- v0.1.5LatestOct 3, 2026

