Search Recruitee candidates, jobs, pipelines and interviews, and add notes, tags and tasks. Hosted by usefulapi — connect from Claude, ChatGPT, Cursor, or any MCP client.
Team and Enterprise: an Owner adds the connector for the organization first.
Run this command, then run /mcp in Claude Code to log in:
Add to Cursor or add this to ~/.cursor/mcp.json:
{
"mcpServers": {
"recruitee": {
"url": "https://recruitee.usefulapi.io/mcp"
}
}
}Add to VS Code or add this to .vscode/mcp.json:
{
"servers": {
"recruitee": {
"type": "http",
"url": "https://recruitee.usefulapi.io/mcp"
}
}
}No Add custom MCP server option? It depends on your account or workspace settings: see OpenAI's guide.
Run these commands. The second one opens the login page:
Other MCP clients (Windsurf, Cline, Zed and more): add the URL as a remote MCP server (Streamable HTTP). The client then opens the login page in your browser. Do not add an Authorization header: see Before you connect.
The login page asks for your Company ID and Personal API token.
Both are in Recruitee → Settings → Apps and plugins → Personal API tokens: create a token there, and the company ID is shown on the same page. The token acts with your own user's role permissions. Your credentials are used only to call the Recruitee API on your behalf and to derive a private account id; they are never shown to anyone.
Add only the URL. Do not add an Authorization header or an API key to the client config. The server signs you in with OAuth: the login page asks for your Company ID and Personal API token. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.
Turn on the Recruitee connector, then ask in plain words. The AI picks the tools.
| Tool | Type | What it does |
|---|---|---|
recruitee_get_current_user | read | Get the current user Fetch the Recruitee user the API token belongs to — name, email, role, role abilities and company id. A cheap way to confirm the token and company id are right. Recruitee: GET /c/{company_id}/admin. |
recruitee_list_team_members | read | List team members List the company's team members (memberships): admin_id, role, whether they are a recruiter or hiring manager, and the jobs they can access. Use admin_id values for task assignees and filters. User names/emails are in the `references` array. Recruitee: GET /c/{company_id}/memberships. |
recruitee_search_candidates | read | Search candidates Search the company's candidates with Recruitee's candidate search (the same engine as the app's filters). `query` is a free-text search across name, emails, phones, tags, sources, job assignments, current stage, cover letter and CV content. `filters` accepts Recruitee filter objects verbatim, e.g. {"field":"created_at","gte":1548975600} (Unix seconds), {"field":"has_cv","eq":true}, {"filter":"tags","id":{"in":[12]}}, {"filter":"stages","name":{"in":["Phone interview"]}}. Returns `hits` (with each candidate's placements: job + current stage) and `total`. Recruitee: GET /c/{company_id}/search/new/candidates. |
recruitee_list_candidates | read | List candidates List candidates, newest first, optionally narrowed to one job, a name/job search, qualified or disqualified only, specific ids, or those created after a date. Paginate with limit + offset (next offset = offset + limit). Recruitee: GET /c/{company_id}/candidates. |
recruitee_get_candidate | read | Get one candidate Fetch one candidate's full profile: contact details, sources, tags, cover letter, CV URL, custom fields, ratings, and `placements` — one per job they are on, each with its placement id and current stage. The placement id is what recruitee_move_candidate_stage needs. Recruitee: GET /c/{company_id}/candidates/{id}. |
recruitee_list_candidate_notes | read | List a candidate's notes List the notes on a candidate's profile, with replies, author admin_id and visibility. Recruitee: GET /c/{company_id}/candidates/{candidate_id}/notes. |
recruitee_list_offers | read | List jobs List the company's jobs (Recruitee calls them offers) with id, title, status, slug, department_id, recruiter_id, hiring_manager_id and pipeline_template_id. Filter by status, department, location, recruiter, hiring manager, tag and more; add heavy fields with `include` (e.g. counters for candidate counts, description, salary, location_ids). Paginated with limit + page (default 1000 per page); `meta.total_count` gives the total. Recruitee: GET /c/{company_id}/offers. |
recruitee_get_offer | read | Get one job Fetch one job or talent pool by id with its full details: description, requirements, location, salary, employment type, candidate counters and pipeline_template_id. Recruitee: GET /c/{company_id}/offers/{id}. |
recruitee_get_pipeline_template | read | Get a hiring pipeline Fetch a pipeline template with its ordered stages (id, name, group, category). A job's `pipeline_template_id` (from recruitee_list_offers / recruitee_get_offer) names its pipeline; the stage ids here are what recruitee_move_candidate_stage takes. Recruitee: GET /c/{company_id}/pipeline_templates/{id}. |
recruitee_list_departments | read | List departments List the company's departments with their ids and job counts. Recruitee: GET /c/{company_id}/departments. |
recruitee_list_tags | read | List candidate tags List the company's candidate tags with ids and usage counts. Tag ids are used in recruitee_search_candidates filters. Recruitee: GET /c/{company_id}/tags. |
recruitee_list_disqualify_reasons | read | List disqualify reasons List the company's configured disqualification reasons (id, name, position). Useful for reading why candidates were disqualified. Recruitee: GET /c/{company_id}/disqualify_reasons. |
recruitee_list_tasks | read | List tasks List recruiting tasks (title, description, due date, completed, candidate_id). With candidate_id, lists that candidate's tasks (Recruitee: GET /c/{company_id}/candidates/{candidate_id}/tasks — only `status` applies). Otherwise lists company tasks with scope, assignee, sorting and paging (Recruitee: GET /c/{company_id}/tasks). |
recruitee_list_interview_events | read | List interviews List scheduled interview events (candidate_id, offer_id, stage_id, start time, duration, location, attendees). Defaults to upcoming events for the whole company; narrow by candidate, date range or interviewer. Recruitee: GET /c/{company_id}/interview/events. |
recruitee_list_evaluations | read | List evaluations List interview results — evaluations (rating + note) and questionnaire scorecards — optionally for one candidate or by selected reviewers. Recruitee: GET /c/{company_id}/interview/results. |
recruitee_create_candidate | write | Create a candidate WRITE: add a candidate manually (as if a recruiter added them in the app — no auto-confirmation email is sent), optionally assigning them straight to one or more jobs in the job's default stage. Recruitee: POST /c/{company_id}/candidates. |
recruitee_update_candidate | write | Update a candidate WRITE: update a candidate's name or contact details. Only the fields you pass change; list fields (emails, phones, links) REPLACE the existing list, so pass the full list you want. Recruitee: PATCH /c/{company_id}/candidates/{id}. |
recruitee_add_candidate_note | write | Add a note to a candidate WRITE: add a note to a candidate's profile, visible to the team. Recruitee: POST /c/{company_id}/candidates/{candidate_id}/notes. |
recruitee_add_candidate_tags | write | Tag a candidate WRITE: add one or more tags to a candidate (existing tags are reused by name; new names create new tags). Recruitee: POST /c/{company_id}/candidates/{candidate_id}/tags. |
recruitee_assign_candidate_to_offer | write | Add a candidate to a job WRITE: put an existing candidate on a job (or talent pool) — creates a placement in the pipeline's first stage. Pass exactly one of offer_id or talent_pool_id. Recruitee: POST /c/{company_id}/placements. |
recruitee_move_candidate_stage | write | Move a candidate to another stage WRITE: move a candidate to another stage of a job's pipeline. Takes the PLACEMENT id (from recruitee_get_candidate → placements[].id, one per job) and the destination stage id (from recruitee_get_pipeline_template). Moving to a 'hired' stage also requires work_location_id. Stage automations configured in Recruitee may run. Undo by moving back. Recruitee: PATCH /c/{company_id}/placements/{id}/change_stage. |
recruitee_create_task | write | Create a task WRITE: create a recruiting task, optionally about a candidate, assigned to team members (admin ids from recruitee_list_team_members), with an optional due date. Recruitee: POST /c/{company_id}/tasks. |
recruitee_usage_status | Usage status (free-tier meter) Report the caller's current usage: the plan, calls used this month, the limit of the plan (the free monthly cap or the Pro fair use limit), remaining, and whether the limit is reached. Read-only; does not count against the meter. | |
recruitee_request_feature | Request a missing feature Tell usefulapi that the user needs something the Recruitee tools cannot do yet (a missing tool, field or filter). Call it only when the user asks for something none of the tools can do, and tell the user that you send the request. Do not call it for errors or for normal requests. Do not include personal data, credentials or customer records. Stored with the product name and the client type (for example Claude or Cursor), without the user's account. At most 5 requests per day. Does not count against the meter. | |
recruitee_upgrade | Upgrade to Pro (unlimited*) Get Pro: unlimited tool calls (fair use limit: 10,000 a month) on Recruitee (the free tier caps monthly usage). Plans: "monthly" — $9/month; "yearly" — $90/year (2 months free). Cancel any time: Pro then runs to the end of the paid period, so it also suits a one-time job. *A fair use limit applies. For heavy use (near Pro's limit): "plus" or "plus_yearly" — Pro+, $19/month or $190/year, unlimited tool calls (fair use limit: 100,000 a month); an existing Pro subscription changes to Pro+ in place (needs confirm: true; the price difference for the rest of the period is charged at once). Otherwise returns a short link to open in your browser (it opens Stripe Checkout); after payment the account upgrades automatically. Does not count against the meter. | |
recruitee_cancel_subscription | Cancel the Pro subscription Cancel the caller's Recruitee Pro subscription at the end of the paid period (no refund for the current period; Pro continues until then, then the free tier applies). Requires confirm: true. Run recruitee_upgrade later to undo the cancel before the period ends. Does not count against the meter. |
| Plan | Price | Limit |
|---|---|---|
| Free | $0 | 50 tool calls / month |
| Proper user | $9/mo · $90/yr | Unlimited* |
*Pro fair use limit: 10,000 tool calls a month on this server. For more, write to [email protected].
Pro covers this Recruitee server only. Subscribe with recruitee_upgrade (it returns a Stripe Checkout link). Cancel any time with recruitee_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running recruitee_upgrade before then undoes the cancel. Or write to [email protected].
No. usefulapi is an independent service. It is not affiliated with or endorsed by Recruitee. The server calls the Recruitee API with your own Recruitee access, so it sees only the data that your account can see.
Yes. In Claude, add this server's URL as a custom connector. In ChatGPT, add it as a custom MCP server in Plugins. Then log in once. Cursor, VS Code, Claude Code and Codex work too. See the setup steps.
The login page asks for your Company ID and Personal API token. See Before you connect for where to find them.
No. Add only the URL. Do not add an Authorization header or an API key to the client config. The server signs you in with OAuth: the login page asks for your Company ID and Personal API token. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.
The login stores them encrypted in the authorization grant of your connection. The server uses them to call the Recruitee API for you and to derive a private account id for usage metering. usefulapi does not show them on any page or in any reply. To stop all access, remove the connector and change or delete these credentials in Recruitee.
Yes, if you approve it. 7 of the 22 Recruitee tools can create or change data. The other 15 are marked read-only. Most MCP clients ask you to approve a tool call before it runs.
The Free plan gives 50 tool calls / month. Pro costs $9/mo or $90/yr, with unlimited tool calls (fair use limit: 10,000 tool calls a month), for this Recruitee server only. Cancel any time: Pro then runs to the end of the paid period. Run recruitee_usage_status to see how many calls you used.
Ask the AI to run recruitee_upgrade: it returns a Stripe Checkout link. To cancel, run recruitee_cancel_subscription. Pro continues to the end of the paid period.
Tell the AI what you wanted to do. It can send the request with recruitee_request_feature. We store the text with the server name, the type of AI client and the tool you tried, not with your account, and read every request when we plan new tools. You can send up to 5 requests per day.
Any client that supports remote MCP servers (Streamable HTTP) with OAuth login: Claude (web and desktop), Claude Code, ChatGPT, Codex, Cursor, VS Code, Windsurf and others.
This is a Model Context Protocol endpoint — meant to be connected from an AI client, not opened in a browser. An invalid_token response at the URL is the auth gate working as designed; clients authenticate automatically.