![\"QueryQuarry](\"https://queryquarry.com/QueryQuarry_Logo_192.png\"){kind=logo}
\n\n \n
\n The consent-based talent graph recruiters' AIs query directly.
\n Search an anonymous corpus of opted-in candidates in natural language — identity is revealed only when the candidate chooses to respond.\n
\n queryquarry.com ·\n MCP docs ·\n Blog ·\n hello@queryquarry.com\n
\n\n---\n\nQueryQuarry is a remote (hosted) MCP server for recruiters and sourcers. Instead of scraping or spraying InMails, your AI assistant queries a structured talent graph where **every profile is explicitly opted in**, candidates stay **anonymous until they accept contact**, and outreach happens through a **double-blind escrow handshake**.\n\n- **Endpoint:** `https://queryquarry.com/api/mcp` (streamable HTTP)\n- **Auth:** OAuth 2.0 — sign up at [queryquarry.com](https://queryquarry.com/recruiter/onboarding), then connect your client and authorize\n- **Server card:** [`/.well-known/mcp/server-card.json`](https://queryquarry.com/.well-known/mcp/server-card.json)\n\n## Connect\n\n**Claude (claude.ai / Claude Desktop):** Settings → Connectors → Add custom connector → `https://queryquarry.com/api/mcp`\n\n**Any MCP client** (via [`mcp-remote`](https://www.npmjs.com/package/mcp-remote)):\n\n```json\n{\n \"mcpServers\": {\n \"queryquarry\": {\n \"command\": \"npx\",\n \"args\": [\"-y\", \"mcp-remote\", \"https://queryquarry.com/api/mcp\"]\n }\n }\n}\n```\n\nOn first use you'll be sent through OAuth to link your recruiter account.\n\n## Tools\n\n| Tool | What it does |\n| --- | --- |\n| `search_candidates` | Search the talent graph. Returns anonymous match cards — headline, skills, seniority, location, availability, salary range. Rich filters: skills, location, remote, seniority, employment type, salary, experience, work authorization, relocation. |\n| `get_candidate` | Evaluate one candidate in depth (full skills, experience, education) — still anonymous. Metered. |\n| `request_contact` | Reach out: you identify yourself, the candidate is notified and decides. If interested, they contact you quoting a one-time code. Metered. |\n| `get_contact` | Status of a contact request: sent, accepted, or declined. |\n| `get_new_candidates` | Profiles new or updated since a timestamp — your standing alert. |\n| `save_candidate` / `get_watchlist` | Watchlist management. |\n| `get_corpus_stats` | Aggregate corpus stats — counts, top skills, top locations. |\n| `check_subscription` | Your tier, limits, and usage. |\n| `get_docs` | The full reference, served to your AI. |\n\nFull documentation: [queryquarry.com/docs/mcp](https://queryquarry.com/docs/mcp)\n\n## How the double-blind flow works\n\n1. `search_candidates` → anonymous match cards, ordered by recency.\n2. `get_candidate` → deeper evaluation, still no name or contact info.\n3. `request_contact` → the candidate is notified with your identity and message.\n4. The candidate decides. If interested, **they** reach out to you with a one-time code. The platform never exposes a candidate's identity or contact details — consent is structural, not policy.\n\n## Pricing\n\nFree accounts include an allowance of candidate reveals and contact requests. Paid plans: [queryquarry.com/#pricing](https://queryquarry.com/#pricing).\n\n---\n\n© 2026 QueryQuarry · This repository hosts documentation for the hosted MCP server; the service implementation is not open source.
\n", "bytes": 3699, "sha": "198de929dcc1f353d7cc6875f49a15e1f875c84a94e5868380558ffb0b718cc1", "repo_slug": "queryquarry/queryquarry", "fonte": "repo", "truncated": false, "api": "https://agentalog.com/api/listings/mcp_io_github_queryquarry_queryquarry_cf0303e1/readme" }