Watch Claude actually do the work.
Real prompts, real tool calls, real results. This is what your assistant looks like after you connect Pin — no screenshots, no simulation, no sleight of hand.
Claude What is the Pin MCP?
Plain-language answer, written for the recruiter who's heard the phrase "MCP server" three times this week and nodded.
The Pin MCP is a Model Context Protocol server from Pin (pin.com) that lets AI assistants run a recruiting workflow on your behalf — kicking off searches, reviewing candidates in an accept/reject loop, tuning the ranker, and persisting per-job memory — using natural language.
- Who it's for
- Recruiters, agencies, founders, and hiring teams who already use Pin.
- What you connect
- Claude Desktop, Claude Code, ChatGPT, Codex, and any MCP-compatible client.
- How it authenticates
- OAuth 2.1 via WorkOS — one click through your pin.com account. No API keys to rotate.
- What it runs on
- A hosted, stateless Streamable HTTP endpoint at mcp.pin.com/mcp. No local install.
- What it exposes
- 10 tools across 4 phases: kickoff, review, tuning, and per-job memory.
- What it costs
- Free on every paid Pin plan. No add-on fee, no metered call limit.
- Data handling
- SOC 2 Type 2. Every call is workspace-scoped and written to the audit trail.
Everything the assistant can actually do.
Four small phases, ten small tools. The assistant sets up a search, reviews candidates with you, tunes on the fly, and remembers what it learned for next time. You still approve every accept, reject, and outreach.
List active candidate searches in your workspace. Used to resolve a role the recruiter mentions by name before any other call.
"Pull up my open searches — I think we have one for a staff PM."
Fetch a job posting from Greenhouse, Lever, Ashby, or any public job board URL. Returns the title, location, and full description.
"Grab the JD from this Greenhouse link and start a search."
Kick off a new candidate search from a title, description, and company. Sourcing runs in the background; call get_candidates right after.
"Start a search: Senior iOS engineer at Acme, Swift + SwiftUI, NYC, remote OK."
Return up to 10 top-ranked, unreviewed candidates for a job. Each batch ships with fit hints, pattern analysis, and anything the assistant has learned so far.
"Show me the next batch — 10 at a time is fine."
Advance a candidate. Kicks off outreach from your Pin-configured sequence. Always confirmed — the assistant never sends silently.
"Accept Maya — she's exactly the shape."
Decline a candidate with a standard or free-text reason. Sourcing quietly backfills a replacement so the queue never runs dry.
"Pass on Robert — wrong stack. Replace him."
Adjust the search with plain-language instructions — location, seniority, skills, comp, anything. Applies before the next batch.
"Only candidates in the NYC metro, drop anyone below staff level."
Feed accumulated accept/reject signal back into the ranker, then pull a fresh, better-matching batch. Auto-suggested when patterns emerge.
"You've rejected 5 junior people in a row — recalibrate."
Load what the assistant learned about your taste for this role in prior sessions — accepted signals, decline reasons, current confidence.
"What do you already know about how I evaluate for this one?"
Persist the running summary — patterns spotted, predicted criteria, confidence level — so the next session doesn't re-learn from scratch.
"Remember: never below 5 yrs of production Swift; de-rank bootcamp-only."
Connect Pin to your AI of choice.
One OAuth click and the Pin tools appear in your assistant. Streamable HTTP, remote hosted — no local server, no API keys, no config drift.
Copy-paste your first 10 minutes.
Real prompts from real recruiters, tuned to get a useful result on turn one. Every recipe lists the tools the assistant will reach for.
Start a search from a JD link
Here's the Greenhouse link for our Senior iOS role. Scrape it, start the search, and pull me the first batch of 10.
Resume an in-flight search
What's open right now? Find my Staff PM role, load what you remember about my criteria, and show me the next batch.
Tell me why — then decide together
For each candidate in this batch: 2–3 sentence fit summary, predict accept or reject, then ask me. Skip the preamble.
Tighten the search mid-flow
Require 5+ years of production Swift, drop anyone in an agency background, and keep NYC / remote only. Then get a fresh batch.
Recalibrate after a rejection streak
You've noticed I've rejected 5 in a row for the same reason. Lock in what I prefer, recalibrate the ranker, and go again.
Go autonomous for the rest
You've predicted my last 4 decisions correctly. Take over — accept the next 10 you're confident on. Surface anything you're unsure about.
When to reach for the MCP, when to open the app.
Both share the same backend. The MCP is faster for prompts and batch moves; the app still wins for deep review sessions and hiring-manager collaboration.
The assistant gets exactly what you let it touch — nothing more.
One OAuth scope. Workspace-level tenancy. Confirmation on every write. Full audit trail in the Pin app. Revoke any connected assistant in one click.
"I run my whole day from Claude now. I haven't opened the Pin dashboard in three weeks — and we closed two roles last sprint."
Answers to what recruiters, developers, and LLMs keep asking.
Can't find what you need? Email the team or drop into docs.pin.com/pin-mcp-server.
hiring game?
Bring Pin into every AI tool you use.
As featured in
