modelcontextprotocol / modelcontextprotocol/registry
Proposal: optional AgentSpec readiness metadata for MCP registry entries
Nobody has claimed this yet.
- Dominant language
- Go
- Stars
- 7.3k
- Forks
- 994
- Avg merge
- 4d 12h
- Merged PRs (30d)
- 19
Description
Hi!
I’m building AgentSpec, a lightweight x402 API that inspects MCP tools and returns a machine-readable readiness signal before an agent connects to or publishes a server.
It can surface:
- risky or overly broad tool permissions
- missing or unclear input schemas
- agent-readiness score
- marketplace metadata gaps
Would an optional readiness signal be useful alongside MCP Registry entries?
The goal would not be to block publishing or replace registry validation. It would be an advisory, machine-readable preflight signal that registries, clients, or maintainers could choose to consume.
I’m looking for honest feedback and would be happy to provide a live demo.
Demo: https://agentspec-one.vercel.app/
OpenAPI: https://agentspec-one.vercel.app/openapi.json
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
No repository files, tests, or entry points are named. Start by reviewing the proposal and the registry's existing validation and entry metadata described in the repository, then determine whether an optional readiness signal fits without blocking publishing. Done would require a maintainer decision and concrete requirements for any accepted integration.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- openapi
- Domain
- api, backend-api-design
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100