queryquarry
Double-blind talent marketplace: AIs search anonymous opted-in candidates; reveal on consent.
我該用這個嗎
品質與安全性
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高,可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案:
{
"mcpServers": {
"queryquarry": {
"url": "https://queryquarry.com/api/mcp"
}
}
}遠端端點
https://queryquarry.com/api/mcpstreamable-http它能做什麼
工具清單
工具(11)
🟢search_candidates(skills, location, radius_miles, remote_ok, experience_years_min, ...)
Search the talent graph. Returns ANONYMOUS match cards — headline, skills (with skills_matched showing which of YOUR terms hit), seniority, location, availability, salary range, and a short snippet — but NO name, full resume, or contact. Call get_candidate (a metered reveal) for the deeper anonymous profile. Filter by skills, location, seniority, salary, experience, availability, and more; sort by recency (default) or skill_match. Always paginated (max 25 per page).
輸入結構描述
{
"type": "object",
"properties": {
"skills": {
"type": "array",
"items": {
"type": "string"
},
"description": "Skills to match (any of). Case-insensitive partial match — use plain terms like \"React\", \"Node\", \"Postgres\"; they also match versioned/variant skills (\"React 19\", \"Node.js\", \"PostgreSQL\")."
},
"location": {
"type": "string",
"description": "City with state (\"Schaumburg, IL\") or a 5-digit zip (\"60133\" — most precise). Geocoded locally; combine with radius_miles for distance search. Unresolvable text falls back to substring match."
},
"radius_miles": {
"type": "number",
"description": "With location: include candidates within this many miles (e.g. 5, 10, 25, 50; max 100). Omit for exact-place matching."
},
"remote_ok": {
"type": "boolean",
"description": "Only candidates open to remote/hybrid."
},
"experience_years_min": {
"type": "number"
},
"experience_years_max": {
"type": "number"
},
"availability": {
"type": "string",
"enum": [
"actively-looking",
"open-to-contact",
"employed-but-open"
]
},
"employment_types": {
"type": "array",
"items": {
"type": "string"
},
"description": "Engagement types to match (any of): full-time, part-time, contract, freelance, internship. Synonyms/variants are normalized."
},
"work_location_types": {
"type": "array",
"items": {
"type": "string"
},
"description": "Work-location preferences to match (any of): remote, hybrid, onsite."
},
"seniority_levels": {
"type": "array",
"items": {
"type": "string"
},
"description": "Seniority levels to match (any of): entry, junior, mid, senior, staff, principal, manager, director, executive."
},
"work_authorization": {
"type": "string",
"description": "Filter by work authorization: \"authorized\" (no sponsorship needed) or \"sponsorship-required\"."
},
"open_to_relocation": {
"type": "boolean",
"description": "Only candidates willing to relocate for the right role."
},
"salary_min": {
"type": "number"
},
"salary_max": {
"type": "number"
},
"updated_since": {
"type": "string",
"description": "ISO timestamp — only resumes updated since."
},
"page": {
"type": "number",
"description": "1-based page."
},
"limit": {
"type": "number",
"description": "Results per page (max 25)."
},
"sort": {
"type": "string",
"enum": [
"recency",
"skill_match"
],
"description": "Result order. When `skills` are supplied the default is skill_match: candidates matching MORE of your skills terms first (ties by most recently updated) — pure arithmetic over your own criteria, no fit scoring. Pass \"recency\" to order purely by recent updates; searches without `skills` are always recency-ordered."
}
}
}🟢get_candidate(candidate_id, resume_id)
Evaluate one candidate in depth — full skills, summary, seniority, experience (titles + what they did) and education. Stays ANONYMOUS: no name, no contact, and employer names, dates, and graduation years are withheld to protect identity. Counts toward your hourly/daily reveal limit. To actually reach someone, call request_contact.
輸入結構描述
{
"type": "object",
"properties": {
"candidate_id": {
"type": "string"
},
"resume_id": {
"type": "string"
}
},
"required": [
"candidate_id",
"resume_id"
]
}🟢request_contact(candidate_id, resume_id, message)
Reach out to one candidate. You identify yourself (your name + company, from your account); the candidate is notified and decides. If they accept, you receive an EMAIL with their contact, their message, and a unique verification code — their identity stays private until they choose to share it. METERED (counts toward your contact limit) and requires a prior get_candidate for this resume. One active offer per candidate; respect declines. get_contact also shows the status any time.
輸入結構描述
{
"type": "object",
"properties": {
"candidate_id": {
"type": "string"
},
"resume_id": {
"type": "string"
},
"message": {
"type": "string",
"description": "Your pitch to the candidate: the role and why them. Your account email is AUTOMATICALLY attached and shown to them when they express interest, so you don't need to include it. You may optionally add other ways to connect (an application form link, your LinkedIn, etc.). Shown in-app, not your raw query."
}
},
"required": [
"candidate_id",
"resume_id",
"message"
]
}🟢get_contact(contact_id, code)
Check the status of a contact request you sent: sent (awaiting), accepted (the candidate shared their contact — see shared_contact, and expect their intro email quoting the code), or declined. Identify it by contact_id or code. Also shows any hire outcome either side reported.
輸入結構描述
{
"type": "object",
"properties": {
"contact_id": {
"type": "string"
},
"code": {
"type": "string"
}
}
}⚪report_contact_outcome(contact_id, code, outcome)
One-tap outcome report on an accepted contact: did it lead to a hire? Optional but appreciated — it's how the marketplace measures that consented outreach beats cold outreach. Values: hired | not_hired | in_progress.
輸入結構描述
{
"type": "object",
"properties": {
"contact_id": {
"type": "string"
},
"code": {
"type": "string"
},
"outcome": {
"type": "string",
"enum": [
"hired",
"not_hired",
"in_progress"
]
}
},
"required": [
"outcome"
]
}🟢get_new_candidates(since)
Get resumes new or updated since a timestamp (your standing alert). Same filters as search_candidates. Call daily with yesterday's timestamp; no duplicates.
輸入結構描述
{
"type": "object",
"properties": {
"since": {
"type": "string",
"description": "ISO timestamp."
}
},
"required": [
"since"
]
}🟡save_candidate(candidate_id, resume_id, notes)
Save a candidate resume to your watchlist with optional notes.
輸入結構描述
{
"type": "object",
"properties": {
"candidate_id": {
"type": "string"
},
"resume_id": {
"type": "string"
},
"notes": {
"type": "string"
}
},
"required": [
"candidate_id",
"resume_id"
]
}🟢get_watchlist(status, page)
Get your saved candidates (watchlist).
輸入結構描述
{
"type": "object",
"properties": {
"status": {
"type": "string"
},
"page": {
"type": "number"
}
}
}🟢get_corpus_stats
Get aggregate stats about the talent corpus (counts, top skills/locations).
輸入結構描述
{
"type": "object",
"properties": {}
}🟢check_subscription
Check your subscription tier, status, rate limit, and usage this hour.
輸入結構描述
{
"type": "object",
"properties": {}
}🟢get_docs
Get the full QueryQuarry reference (how it works, all tools and filters, search tips, rate limits, privacy). Call this when you need detail beyond these tool descriptions, when guiding a new user, or before composing a complex search.
輸入結構描述
{
"type": "object",
"properties": {}
}社群
證據