Agent Manifest Protocol (AMP)
Fetch, validate, and permission-check Agent Manifest Protocol (AMP) manifests for API discovery.
Open the source (opens github.com) https://github.com/amprotocol/amp
Before you use it
- Runs on someone else's server: what you send it leaves your machine.
- Runs on your computer with your permissions. Read what it can do before connecting it to an agent.
What it is
MCP servers from com.agent-manifest.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
npm package (stdio)
@agentmanifest/mcp-server@0.1.5
From the server's entry in the official MCP Registry
Remote endpoint (sse)
https://mcp.agent-manifest.com/mcp
From the server's entry in the official MCP Registry
Settings it asks for
AMP_FETCH_TIMEOUT_MS· HTTP timeout (ms) when fetching manifests from API origins.
Related
-
NDP — Music Rights & Track Identification
MCP serversMusic rights for AI: track identification by fingerprint, rights manifests, artist verification.
@aendykachess/ndp-mcp@1.0.1 -
manifestlens
MCP serversAgent Manifest Protocol: fetch, validate and permission-check API manifests; registry submissions.
@reneturcios/manifestlens@0.1.0 -
Google Workspace
MCP serversGive AI agents access to Gmail, Calendar, Drive, and more — multi-account, manifest-driven
@aaronsb/google-workspace-mcp@4.9.1 -
agent-guard-mcp
MCP serversVerify-before-act safety checks for AI agents: packages, lockfiles, manifests, CI workflows.
@liminallablibs/agent-guard-mcp@0.2.1 -
AGT agent names
MCP serversResolve, verify and discover .agt agent names: owner, records, signed manifest, endpoints.
@agtnames/mcp@1.5.2 -
MCP Agent Health Reporter
MCP serversAdvisory AOS agent health scan before deployment (manifest, services, immune loop, evidence).
mcp-agent-health@0.3.1