Skip to main content

The #1 agentic semantic tool search: 91.6% first-try accuracy on S1 Search Bench • Explore Tool Discovery →

Live 26 Actions

Comeet MCP Server
for AI Agents

Connect your AI agent to StackOne's Comeet MCP server and give it 26 MCP tools out of the box. Auth, tool execution, and security all managed.

Start Free Book Demo Read Docs →
Comeet logo
Comeet MCP Server
Built by StackOne StackOne
DrataGPLocalyzeFlipMindtoolsScreenloop

Coverage

26 Agent Actions

Create, read, update, and delete across Comeet — and extend your agent's capabilities with custom actions.

MCP Actions → Build Actions →

Authentication

Agent Tool Authentication

Per-user OAuth in one call. Your Comeet MCP server gets session-scoped tokens with zero credentials stored on your infra.

Agent Auth →

Security

Agent Protection

Every Comeet tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.

Prompt Injection Defense →

Performance

Max Agent Context. Min Cost.

Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Comeet call.

Tools Discovery →

What is the Comeet MCP Server?

A Comeet MCP server lets AI agents read and write Comeet data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Comeet MCP server ships with 26 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, observability, and agent execution runtime. Connect it from MCP clients like Claude Desktop, Claude Code, Cursor, Goose, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.

All Comeet MCP Tools

Every action from Comeet's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.

Positions

  • Create Position

    Create a new position. Requires name, status, is_discreet, and users (hiring_manager and lead_recruiter with email addresses).

  • Clone Position

    Clone a template position to create a new position. Only positions with is_template=true can be cloned — use list_positions with is_template=true filter to find templates.

  • List Positions

    List all positions in the company

  • Get Position

    Retrieve a single position by ID

  • Update Position

    Update an existing position by ID

Candidates

  • Create Candidate

    Create a new candidate (formal applicant) for a position

  • List Candidates

    List all candidates in the company

  • Get Candidate

    Retrieve a single candidate by ID

  • Update Candidate

    Update an existing candidate by ID

Leads

  • Create Lead

    Create a new lead (sourced prospect) for a position

  • List Leads

    List all leads in the company

  • Get Lead

    Retrieve a single lead by ID

  • Update Lead

    Update an existing lead by ID. Requires updated_by object identifying who made the change.

Other (13)

  • Create Opening

    Create a new opening (headcount) for a position. Requires position_uid, name, reason, and expected hire date.

  • Create Conversation

    Create a new conversation thread for a candidate. Requires conversation_type, visibility, and at least one message.

  • Create Message

    Add a new message to an existing conversation by conversation UID. Requires time_sent, body, from (sender contact), and to (recipient contacts).

  • Create Candidate Note

    Create a note for a candidate (formal applicant)

  • Create Lead Note

    Create a note for a lead (sourced prospect)

  • List Locations

    List all locations in the company

  • List Candidates By Position

    List candidates for a specific position by position UID, with pagination and filtering

  • List Deleted Candidates

    List deleted or pseudonymized candidate UIDs from the Recruit API for syncing deletions to downstream systems

  • List Deleted Candidates (Evaluation)

    List deleted or pseudonymized candidate UIDs from the Evaluation API (Enterprise plan). Use this instead of list_deleted_candidates when working with Comeet's Evaluation product.

  • List Questionnaires

    List all questionnaires in the company

  • Delete Person

    Permanently delete a person and all associated candidates. The person UID is found in the person_uid field of candidate objects.

  • Find Duplicate Candidates

    Search for duplicate candidates by personal details

  • Pseudonymize Person

    Pseudonymize a person's data and all associated candidates according to company settings. The person UID is found in the person_uid field of candidate objects. Use this for GDPR compliance when full deletion is not required.

Comeet AI Agent Use Cases

Connect your AI agent to Comeet and help your team scale the recruiting operations they run by hand today.

Job Posting Distribution

Use StackOne to connect your AI agent to your ATS and job boards to automate job posting distribution.

View
GreenhouseLeverAshbySmartRecruitersWorkableJobviteiCIMSTeamtailor
Reference Check Automation

Use StackOne to connect your AI agent to your ATS, survey tools, and messaging systems to automate reference checks.

View
GreenhouseLeverWorkdayiCIMSSmartRecruitersAshbyTeamtailorSurveyMonkey
Offer Letter Generation

Use StackOne to connect your AI agent to your ATS, HRIS, and document management tools to automate offer letter generation.

View
GreenhouseLeverAshbyWorkdayBambooHRPersonioHiBobGusto
More Recruiting use cases

Set Up Your Comeet MCP Server in Minutes

One endpoint. Any framework. Your agent is talking to Comeet in under 10 lines of code.

MCP Clients

Claude Desktop setup guide
Claude Code setup guide
Cursor setup guide
Goose setup guide

Agent Frameworks

Claude Desktop
{
  "mcpServers": {
    "stackone": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://api.stackone.com/mcp?x-account-id=<account_id>",
        "--header",
        "Authorization: Basic <YOUR_BASE64_TOKEN>"
      ]
    }
  }
}

Check More Recruiting MCP Servers

JobAdder

246+ actions

Vincere

206+ actions

SmartRecruiters

164+ actions

Ashby

137+ actions

Manatal

130+ actions

Factorial

127+ actions

HiBob

123+ actions

All Recruiting MCP Servers →

Platform Resources

MCP Code Mode: Keeping Tool Responses Out of Agent Context

Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.

11 min

Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery

Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.

10 min

Indirect Prompt Injection Defense for MCP Tools: A Technical Guide

MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.

12 min

MCP vs A2A: Architecture, Security, and When to Use Each

MCP vs A2A: what each protocol standardizes, how they differ, their shared security risks including indirect prompt injection, and when to use one, both, or a hybrid architecture.

12 min

MCP vs API: What 200+ Connector Builds Taught Us

MCP wraps APIs, it doesn't replace them. After building 200+ connectors that serve both, here's when each approach wins.

14 min read

Comeet MCP Server FAQ

Does StackOne have a Comeet MCP server?
Yes. StackOne offers a hosted Comeet MCP server with 26 pre-built actions, and every action is tested and QA'd by StackOne. Connect it to Claude, Cursor, and any other MCP client, or to any agent framework through the AI Action SDK. It ships with managed agent authentication, prompt injection defense, and tool discovery with server-side execution that preserve your agent's context window and keep reasoning performance.
Comeet MCP server vs direct API integration — what's the difference?
A Comeet MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Comeet. A Comeet MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling Comeet at runtime. StackOne provides both.
How does Comeet authentication work for AI agents?
Comeet authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Comeet account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.
Are Comeet MCP tools vulnerable to prompt injection?
Yes — Comeet MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a Comeet agent and how do I avoid it?
Context bloat happens when Comeet tool schemas and API responses eat your Comeet agent's memory, preventing it from reasoning effectively. A single Comeet query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my Comeet agent can access?
Yes — you can limit which actions your Comeet agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my Comeet MCP server?
Yes — you can create custom agent actions for your Comeet MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Comeet's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Comeet MCP server?
Skip a Comeet MCP server if your integration is purely software-to-software — direct Comeet API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call Comeet actions at runtime.
What AI frameworks and AI clients does the StackOne Comeet MCP server support?
The StackOne Comeet MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.

Put your AI agents to work

All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.

Start Free Book Demo