What it does
CoverCraft AI is a Model Context Protocol server written in Python 3.11 that exposes eight tools over stdio and Streamable HTTP SSE transports. The tools include company_research, which runs web search through Tavily and returns source citations; evidence_validator, which checks claims against source data and labels them VERIFIED, PARTIAL or UNSUPPORTED; jd_analyzer, which matches a job description against a resume and gives proof anchors; ats_readiness, which runs a heuristic audit of keyword coverage, format and length; and source_filter, which tiers sources by domain, suppresses noise and filters outdated news. The wider project is a career workspace that also scrapes pages with Jina AI Reader and classifies sources as company official, job portal or engineering news.
The server suits someone preparing a job application who wants a cover letter checked against resume evidence rather than written freely. The workspace adds a human approval step before web sources enter the generation prompt, marks claims with resume and source citations that can be hidden on export, and runs a veracity audit that softens verbs not supported by the resume.
Running it requires Python 3.11 and the MCP server in the mcp-server directory. Company research and scraping depend on the Tavily and Jina AI Reader services.
Limitations and requirements
Requires Python 3.11. Company research depends on Tavily web search, and page scraping depends on Jina AI Reader. The readme does not describe any other setup requirements.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
CoverCraft AI by Ambuj Kumar Tripathi
Live Hugging Face model proofing, ATS resume scoring and career tools by Ambuj Kumar Tripathi
v1.0.0As shown on registry.modelcontextprotocol.io when we last read it