Agent Manifest Protocol (AMP)

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

Should I use this

Quality & Safety

A
Description quality
100%
Schema completeness
93%
Naming quality
100%
Poisoning risk
100%
Permission match
100%
Protocol compliance
100%

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~513Tokens (tool definitions)
~1.4 KBTypical response size
Minimal attention impact (0.40% of 128k context)

This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.

Install

One-Click Install

Add this to your `claude_desktop_config.json` file:

{
  "mcpServers": {
    "amp-mcp": {
      "command": "npx",
      "args": [
        "@agentmanifest/mcp-server"
      ]
    }
  }
}

Runnable packages

npm@agentmanifest/mcp-server0.1.5stdio

Remote endpoints

https://mcp.agent-manifest.com/mcpsse

What it can do

Tool inventory

Tools (3)

🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
🟢fetch_manifest_by_domain(domain)

Resolve an API origin from a domain (e.g. "bakebase.agent-manifest.com"), try standard AMP discovery URLs, and return parsed manifest JSON plus metadata.

Input Schema

{
  "type": "object",
  "properties": {
    "domain": {
      "type": "string",
      "minLength": 1,
      "description": "API hostname or URL origin without a path, e.g. \"example.com\", \"api.example.com\", or \"https://bakebase.agent-manifest.com\"."
    }
  },
  "required": [
    "domain"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
⚪validate_manifest_syntax(manifest)

Validate a manifest JSON string or object against the official AMP JSON Schema for its spec_version (agentmanifest-0.2 or agentmanifest-0.3). Returns errors or a success_token.

Input Schema

{
  "type": "object",
  "properties": {
    "manifest": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "object",
          "additionalProperties": {},
          "description": "Parsed AMP manifest object (agentmanifest-0.2 or agentmanifest-0.3)."
        }
      ],
      "description": "Either a JSON string of the manifest, or a parsed manifest object with spec_version, name, endpoints, etc."
    }
  },
  "required": [
    "manifest"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢check_agent_permissions(action, manifest, intends_unauthenticated, payment_onboarded)

Given an intended HTTP action (method + path or full URL) and a manifest, determine whether the action aligns with declared endpoints, authentication, payment onboarding, rate limits, and language in agent_notes.

Input Schema

{
  "type": "object",
  "properties": {
    "action": {
      "type": "string",
      "minLength": 1,
      "description": "Intended operation, e.g. \"POST /baking/validate-mix\", \"GET /health\", or \"POST https://api.example.com/v1/search\"."
    },
    "manifest": {
      "type": "object",
      "additionalProperties": {},
      "description": "Parsed AMP manifest object (agentmanifest-0.2 or agentmanifest-0.3)."
    },
    "intends_unauthenticated": {
      "type": "boolean",
      "description": "Set true if the agent plans to call the API without credentials."
    },
    "payment_onboarded": {
      "type": "boolean",
      "description": "Set true if AMP payment onboarding is already complete for this API."
    }
  },
  "required": [
    "action",
    "manifest"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded3 tools