How to Connect Recruitee to Microsoft Copilot via MCP

💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → Recruitee, paste your credentials, mint an MCP API key and you're done. No Docker, no git clone, no local server.

Recruitee + Microsoft Copilot

Recruitee (Tellent Recruitee) applicant tracking: jobs and talent pools, candidates with full search, pipelines and stages, placements, notes, tags, departments, locations, interviews and evaluations, tasks and the activity feed. It also moves candidates through stages and creates and publishes jobs. Recruitee ATS API with a personal API token.

Prerequisites

See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:

RECRUITEE_COMPANY_ID, RECRUITEE_API_TOKEN

Step 1 — Get credentials

Setting up takes about 3 minutes.

1. In Recruitee open Settings > Apps and plugins > Personal API tokens (https://app.recruitee.com/#/settings/api_tokens), click Add new token, give it a label and confirm your password. Copy the token into RECRUITEE_API_TOKEN; it cannot be shown again.
2. Copy the company ID shown on the same page (a number) into RECRUITEE_COMPANY_ID. The company subdomain also works.
3. Install the connector: recruitee_get_current_admin is the install check.

The token acts as you, with your role, in that one company only; another company needs its own token. Recruitee cannot narrow a token's scope, so create it with a user whose role fits what the AI should do.

Personal data: candidates are applicants with CVs, contact details, evaluations and sometimes date of birth or nationality. Ask only for what the task needs, respect the company's GDPR settings and do not copy candidate data into other tools without a reason.

Recruitee's words: a job is an offer (kind job; a talent pool is an offer of kind talent_pool). A candidate in a job is a placement, which carries the stage and the disqualification for that job. Team members are admins.

What it reads:

• Team: recruitee_get_current_admin and recruitee_list_admins (ids for task assignees and filters).
• Jobs: recruitee_list_offers (filter by statuses such as published, kind, department, location, tag, recruiter or hiring manager), recruitee_get_offer (description, requirements, hiring team and the pipeline stages with their ids) and recruitee_list_offer_notes.
• Candidates: recruitee_list_candidates (simple filters), recruitee_search_candidates (full search with filters_json), recruitee_get_candidate (contact details, CV and cover letter links, sources, tags, custom fields, ratings, placements and question answers), recruitee_list_candidate_notes, recruitee_list_candidate_tasks and recruitee_list_candidate_activities. The company-wide feed: recruitee_list_activities.
• Pipeline of a job: recruitee_list_placements (who is in which stage), recruitee_list_pipeline_templates, recruitee_get_pipeline_template and recruitee_list_disqualify_reasons.
• Reference lists: recruitee_list_departments, recruitee_get_department, recruitee_list_locations, recruitee_get_location, recruitee_list_tags and recruitee_list_sources.
• Interviews: recruitee_list_interview_events (upcoming by default), recruitee_get_interview_event and recruitee_list_interview_results (evaluations and scorecards). Tasks: recruitee_list_tasks.

What it writes:

• Candidates: recruitee_create_candidate (optionally applied to jobs; a remote_cv_url is parsed), recruitee_update_candidate, recruitee_add_candidate_tags (tag names that do not exist yet are created), recruitee_remove_candidate_tags, recruitee_add_candidate_field (for example skills, languages or nationality) and recruitee_create_candidate_note (visible to the hiring team, not to the candidate).
• Pipeline: recruitee_assign_candidate puts a candidate into a job (first stage) or a talent pool; recruitee_change_stage moves a placement to another stage (placement id from the candidate, stage id from recruitee_get_offer; a hired stage can need hired_at, work_location_id and, with requisitions, opening_id); recruitee_disqualify_candidate with a reason and recruitee_requalify_candidate undo each other.
• Jobs: recruitee_create_offer creates a draft, recruitee_update_offer changes its fields, recruitee_publish_offer puts it on the careers site and the job boards set up for it, recruitee_unpublish_offer takes it off and keeps its candidates, recruitee_close_offer stops new applications.
• Tasks: recruitee_create_task and recruitee_complete_task (or reopen a task with completed false).

Automations: creating a candidate on a job, changing a stage with run_actions true, or disqualifying can trigger the emails and actions the company configured in Recruitee, so candidates may hear from you. The AI says so before doing it for many candidates.

Switched off at install: recruitee_delete_candidate (deletes the candidate with all their data) and recruitee_remove_placement (removes a candidate from a job together with that placement's stage history). They cannot be undone; a workspace admin switches them on when the team needs them. Disqualifying is the reversible way to take a candidate out of a job.

Search filters: filters_json of recruitee_search_candidates is a JSON array as a string, for example [{"field":"all","query":"java"},{"filter":"tags","id":{"in":[12]}},{"field":"created_at","gte":"2026-10-01"}]. Status and source: {"field":"status","in":["qualified"]}; stages: {"filter":"stages","name":{"in":[...]}}.

Data formats: ids are integers; dates and times are ISO 8601 in UTC (2026-10-19T11:02:32Z). A candidate's placements list one entry per job with offer_id, stage_id and disqualify_reason; stage and qualification changes take the placement id. adminapp_url links to the candidate in Recruitee.

Paging: recruitee_list_candidates pages with limit (up to 1000) and offset; offers, search, locations, activities, events and tasks page with limit and page (from 1). The AI stops when a page returns fewer items than limit.

Common errors: 401 invalid_token means a wrong, revoked or other company's token; 403 a role without the right; 404 a wrong company ID or record id; 422 a validation error, with the field named in the body.

The connector does not email candidates directly, does not schedule interviews and does not write evaluations.

Step 2 — Install the adapter

curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d

Step 3 — Add the connector in Microsoft Copilot

Your server URL: in AnythingMCP, open MCP Servers → the server this connector is on, and copy its URL (https://cloud.anythingmcp.com/mcp/…). Use it wherever this guide shows YOUR_SERVER_ID.

Microsoft Copilot uses MCP servers through agents built in Copilot Studio: you add AnythingMCP to an agent as a tool, then publish the agent to Microsoft 365 Copilot and Teams. Copilot Studio connects from Microsoft's cloud over Streamable HTTP, which AnythingMCP supports.

1. In Copilot Studio, open your agent (or create one), go to Tools and choose Add a tool → New tool → Model Context Protocol.
2. Enter a Server name (for example AnythingMCP), a Server description that says what the connector does, and the Server URL https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID. Copilot Studio uses the description to decide when to call the server.
3. Under authentication, choose API key, set Type to Header and the header name to X-API-Key, then select Create.
4. In Add tool, choose Create a new connection, paste an MCP API key from AnythingMCP (MCP Servers → your server → API keys) and select Add to agent.
5. Try it in the agent's Test pane: ask for something that needs the Recruitee tools.
6. Select Publish, then Channels → Microsoft 365 and Microsoft Teams, keep Make agent available in Microsoft Copilot selected and choose Add channel. See agent in Teams installs it for you; in Microsoft 365 Copilot, type @ and pick the agent.

Prefer per-user sign-in? Choose OAuth 2.0 → Dynamic discovery instead of an API key: each user then signs in to AnythingMCP the first time the agent calls it.

Self-hosting? Use your instance's public HTTPS address instead of https://cloud.anythingmcp.com. Copilot Studio connects from Microsoft's cloud, so localhost does not work.

Available tools

Example prompts

• "Which candidates applied to the Senior Backend Developer job this week, and in which stage are they?"
• "Find candidates tagged java who applied after 1 October."
• "What interviews are scheduled for tomorrow, with candidate, job and participants?"
• "Move Laura Rossi to the Interview stage of the Product Designer job and add a note that the phone screen went well."
• "Create a draft job for a Customer Support Specialist in the Support department, located in Berlin."

FAQ

Which Copilot is this for? Microsoft 365 Copilot at work, through agents built in Copilot Studio. The Microsoft Copilot app for personal accounts has no option to add your own MCP server.

What do I need? A work account with access to Copilot Studio (a license or a trial) to build the agent. People who use it in Microsoft 365 Copilot or Teams need access to the agent: share it with them, or ask an admin to publish it to the organization. If your organization applies data policies to Power Platform connectors, they cover MCP servers too.

The agent doesn't call the tools. Check that the header name is exactly X-API-Key and that the key belongs to the same MCP server as the URL, and make the server description specific: Copilot Studio uses it to decide when to call the server. Publish the agent again after each change; in an open chat, type "start over" to get the new version.

Next steps

• Connector landing page
• Connect to Claude
• Connect to ChatGPT
• Connect to Cursor
• Connect to Gemini
• Connect to Meta Muse