The Cognitive MCP Server — Drive Recruiting from Claude

What is MCP (the Model Context Protocol)?

The Model Context Protocol (MCP) is an open standard that lets AI assistants like Claude securely connect to external tools and data sources, so the assistant can take real actions - not just answer questions. An MCP server exposes a set of named tools; the assistant calls them on your instruction and reports back in plain language.

For recruiting, that means the chat window becomes a hiring console: instead of clicking through a dashboard, you tell your assistant what you want ("open a senior backend engineer role and draft the JD") and it drives The Cognitive for you.

What can you do with The Cognitive MCP server?

You can run the entire recruiting workflow from your AI assistant. A typical flow, in plain English:

• "Open a role for a Senior Data Engineer" - the assistant calls create_role, then generate_job_description drafts the JD and generate_interview_questions plus generate_evaluation_criteria build the interview and scoring rubric.
• "Invite these 40 applicants" - bulk_invite_candidates (or invite_candidate for one) sends AI interview invitations; candidates self-schedule from your slot window.
• "Score the new resumes against the must-haves" - score_candidate_resume grades each resume with evidence before anyone is interviewed.
• "Who did well this week?" - list_interviews and get_interview_feedback pull evidence-scored scorecards with quotes; you read the highlights in chat.
• "Advance the top three, reject the rest with feedback" - advance_candidate_stage and reject_candidate execute your decision; the AI never decides for you.
• "How is the pipeline looking?" - get_pipeline_summary returns the funnel in one answer; create_offer and list_offers handle the final step, and get_credits tells you what's left on your plan.

Every tool the MCP server exposes

The full public tool surface - these are the real tool names your assistant sees, nothing more and nothing less:

• create_role - open a new role with title, description, and settings
• update_role - change an existing role's details or settings
• generate_job_description - draft a complete JD for a role with AI
• generate_interview_questions - create role-specific interview questions
• generate_evaluation_criteria - build the scoring rubric for a role
• create_evaluation_template - save an evaluation template for reuse across roles
• create_candidate - add a candidate to a role's pipeline
• invite_candidate - send one candidate an AI interview invitation
• bulk_invite_candidates - invite a whole list of candidates at once
• list_candidates - see every candidate in a pipeline, with filters
• get_candidate - pull one candidate's full record
• score_candidate_resume - AI-score a resume against the role's must-haves
• advance_candidate_stage - move a candidate forward in the pipeline
• reject_candidate - reject a candidate (with optional feedback flow)
• list_interviews - list scheduled and completed AI interviews
• get_interview - fetch one interview's details and status
• get_interview_feedback - read the evidence-scored interview feedback
• cancel_interview - cancel a scheduled interview
• get_pipeline_summary - get the funnel picture for a role in one call
• create_offer - create an offer for a successful candidate
• list_offers - list offers and their statuses
• get_credits - check your account's remaining interview and sourcing credits

How do you set up The Cognitive MCP server?

Setup takes a few minutes: you need a The Cognitive account and your MCP endpoint URL, which we provision per workspace.

• 1. Contact us for your MCP endpoint URL - email contact@thecognitive.io or use the contact page; endpoints are provisioned per account.
• 2. In claude.ai, add it under Settings → Connectors as a custom connector (the server also works with any MCP-compatible client).
• 3. Ask your assistant to get started - for example: "Create a role for a Senior Backend Engineer, generate the job description and interview questions, and show me the evaluation criteria."
• 4. Actions run against your real workspace using your plan's interviews and credits - the same account the dashboard uses, so everything stays in one pipeline.

Why drive recruiting through MCP?

• One interface: role setup, JD writing, question generation, invitations, feedback review, and pipeline reporting happen in the same conversation where you already work.
• Agentic recruiting with human control: the assistant executes the busywork (a role with AI-generated JD, questions, and criteria takes about 10 minutes to stand up), while stage moves, rejections, and offers only happen when you say so.
• Evidence stays attached: interview feedback pulled over MCP is the same evidence-scored feedback as the dashboard - scores tied to quotes, not vibes.
• Scriptable hiring: because tools are standard MCP, you can chain them - score resumes, invite everyone above the bar, and summarize the pipeline - in one instruction.

Frequently Asked Questions