mcp-medic — MCP Diagnostics & Quality Gate
Diagnose trusted MCP configs, triage handshake and schema failures, plan focused repairs, and establish evidence-led CI quality gates.
$1
Works with the AI Agents you already use
mcp-medic — MCP Diagnostics & Quality Gate
Example session with this skill installed
Check one reviewed local stdio MCP config with a bounded timeout, explain its diagnostics, and distinguish protocol quality from runtime security.
- Read your context and instructions
- Compiled the mcp-medic
A source-built mcp-medic 1.3.0 run against one reviewed local token-budget MCP server returned servers=1, connected=1, failed=0, errors=0, warnings=0. It enumerated 14 tools. Quality coverage was 100% for the built-in passive checks, and the resulting quality score was 100. These fixture-specific observations do not establish tool business correctness or dependency safety: the tool itself states that its score is not a security or correctness certification. No server tool calls were made by the passive diagnostic. Next steps for a real project: confirm the intended tools were listed, add independent behavior tests where needed, and preserve this evidence without publishing credentials or private config.
Connects securely to your tools. The creator never sees your data.
About this skill
Original agent workflows for mcp-medic: inspect configuration execution scope, diagnose connection and schema failures, interpret quality coverage, plan minimal fixes, and verify the same scope after repair. Includes CLI setup, bounded CI playbooks, failure handling and privacy-aware evidence templates.
Requires separately installed mcp-medic 1.3.0 and Node.js >=18. This is a terminal workflow, not an MCP server. Real checks start configured processes or contact endpoints: trusted configs only. Passive MCP enumeration does not call server tools, but server startup can execute code.
Verified source baseline: 320 tests passed; real stdio inspection connected to one server and enumerated 14 tools with zero diagnostics. Its deterministic score is not security certification or a guarantee of runtime behavior. Production dependency audit reported zero advisories for the tested source lockfile.
The MIT runtime remains free at https://github.com/shivam039/mcp-doctor. Install npm package mcp-medic, not the unrelated mcp-doctor package. This MIT workflow package provides original curation; no exclusive runtime rights or performance promises.
Normal checks enumerate protocol metadata, not tool behavior. Scores/security checks are heuristics, not certification. Configured startup commands and remote connections are real. Experimental extension and planned plugins are not bundled.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 19 days ago
Requires
Permissions
Allowed Hosts
Install only in an authorized project; review commands/config and endpoints before execution. Read task-authorized files and write only authorized project changes/reports. Runtime and source packages remain free and open-source under MIT; this purchase is for original curated instructions.