MCP server directory

DevMatch

DevMatch is an MCP server for hiring engineers based on what they've actually built. Connect from Cursor, Claude Desktop, or any MCP-compatible AI assistant and search 35M+ developers ranked by verified open-source contributions — not LinkedIn keywords or self-reported skills. **Three tools:** **`find_candidates`** — paste a job description, get a ranked shortlist with bio, top repos, contribution evidence, and contact info. Pro tier adds verified email enrichment on the top 5 results. **`get_profile`** — deep-dive any GitHub handle. Bio, recent activity, top projects, and outreach channels in one call. **`find_similar_projects`** — landscape mapping from a seed repo with top contributors surfaced, so you can pivot from a project to its maintainers in one step. Built for mission-driven teams that want engineers who care about the work, not just check the keyword box. OAuth sign-in (no API keys to juggle). Free tier with 50 monthly credits, $129/mo Pro for higher quotas plus verified email enrichment.

DevMatch finds engineers and scientists from public work like papers, open source, and patents for deeptech and hardtech teams, providing evidence and source links for each candidate.

Version:: hosted
Publisher:: zachary-royals
Company:: DevMatch
Docs:: dev-match.xyz/MCP
Pricing:: Free platform credits available, no card required.; Summary written by google/gemini-2.5-flash-lite from the server’s own site and README; facts above come from the registries.; Logo: https://dev-match.xyz/opengraph-image?038246dc359968f4

Install

Generated from the server’s transport data — never hand-written. Placeholders in angle brackets are yours to fill.

Run it with its own identity, a budget you set, and every call audited — no local config to keep in sync.

Add to a connect0 project

You will sign in first, then land back on this page.

What it can do

As declared by the publisher

Tools · 3

find_candidates
Search the DevMatch index for engineers matching a job description. Pass JD text — formal description, informal request, role brief, paste of a README, or anything in between. The longer + more specific, the better the match. Returns ranked candidates with FULL profile data inline per result: handle, name, bio, location, followers, top\_repos, top\_topics, matched\_projects (with contribution counts), contact info (email + social URLs when available), and candidate\_score. You do NOT need to call get\_profile for candidates returned here — their profiles are already embedded in the response. Only call get\_profile when the user asks about a handle that was NOT in the find\_candidates results. Public github.com repo URLs are also accepted as input (server fetches README + topics + language and uses it as the JD), but ONLY for PUBLIC repos. For private repos, paste the README content directly as the JD string.
find_similar_projects
Find open-source projects similar to a given GitHub repo, ranked by semantic similarity to its description/topics/README. Each result includes the project's top contributors so the caller can pivot from a project to its maintainers in one step. Use for landscape mapping ("what else is like X?"), competitive intel, or to expand a candidate search past a single anchor project.
get_profile
Fetch one contributor's profile card when the user mentions a specific GitHub handle that was NOT already returned by find\_candidates. Use cases: (a) user types 'tell me about @karpathy'; (b) user references a handle they found elsewhere; (c) user wants to verify someone before outreach. Do NOT call this immediately after find\_candidates for handles in those results — find\_candidates already returns full profile data inline per candidate (bio, location, contact, top\_repos, top\_topics). IMPORTANT — interpreting recent\_activities: this field reflects indexed GitHub activity in the current ingestion window (2025–2026), up to \~20 events per recent project. It is NOT a complete career history. Older or empty activity does not mean the person is inactive; they may be outside the index window or not yet enriched. Do not infer tenure or 'last active' from activity older than 2025.