Skip to main content Announcing Tool Policies: AI agent permissions down to the field Read the announcement
Live 51 Actions

CEIPAL MCP Server
for AI Agents

Connect your AI agent to StackOne's CEIPAL MCP server and give it 51 MCP tools out of the box. Auth, tool execution, and security all managed.

CEIPAL logo
CEIPAL MCP Server
Built by StackOne StackOne
DrataGPLocalyzeFlipMindtoolsScreenloop

Coverage

51 Agent Actions

Agents can read and write in CEIPAL. Extend your agent's capabilities with custom actions.

Authentication

Agent Tool Authentication

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

Agent Auth →

Security

Agent Protection

Every CEIPAL tool response scanned for prompt injection in milliseconds, with 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 CEIPAL call.

Tools Discovery →

What is the CEIPAL MCP Server?

A CEIPAL MCP server lets AI agents read and write CEIPAL data through the Model Context Protocol, Anthropic's open standard for connecting LLMs to external tools. StackOne's CEIPAL MCP server ships with 51 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 CEIPAL MCP Tools

Every StackOne action for CEIPAL, ready for your agent. Read and write, scoped to exactly what you need.

Applicants

  • Create Applicant

    Create an applicant with a resume

  • List Applicants

    List applicants with filters

  • Update Applicant

    Update an existing applicant

Job Postings

  • List Job Postings

    List job postings with filters

  • Update Job Posting

    Update one or more job postings

Other (46)

  • Create Applicant Notes

    Add notes to one or more applicants

  • Get Applicant Details

    Retrieve one applicant profile, including contact details, skills, status and resume token

  • List Talent Bench

    List talent bench consultants

  • Get Talent Bench Details

    Retrieve one bench consultant with contact details, skills and availability

  • List Clients

    List clients with filters

  • Get Client Details

    Retrieve one client record with status, category, ownership and address details

  • List Client Notes

    Retrieve notes logged against clients and client contacts

  • List Client Contacts

    Retrieve contacts belonging to client accounts, with name, designation and contact details

  • Download Document

    Download an applicant resume

  • List Interviews

    List interviews with filters

  • Get Interview Details

    Retrieve one interview with schedule, mode, round, venue and outcome

  • Get Job Posting Details

    Retrieve one job posting with rates, location, recruiters, client and descriptions

  • List Leads

    Retrieve sales leads (prospective clients) with location, ownership and industry

  • Get Lead Details

    Retrieve one sales lead with business unit, location, ownership and industry

  • List Job Types

    Retrieve CEIPAL job types master data

  • List Domains

    Retrieve CEIPAL job domains master data

  • List Job Categories

    Retrieve CEIPAL job categories master data

  • List Applicant Statuses

    Retrieve CEIPAL applicant statuses master data

  • List Applicant Sources

    Retrieve CEIPAL applicant sources master data

  • List Business Units

    Retrieve CEIPAL business units master data

  • List Countries

    Retrieve CEIPAL countries master data

  • List Client Categories

    Retrieve CEIPAL client categories master data

  • List Client Statuses

    Retrieve CEIPAL client statuses master data

  • List Clearance Types

    Retrieve CEIPAL security clearance types master data

  • List Employment Types

    Retrieve CEIPAL employment types master data

  • List Industries

    Retrieve CEIPAL industries master data

  • List Job Statuses

    Retrieve CEIPAL job statuses master data

  • List Pay Frequency Types

    Retrieve CEIPAL pay frequency types master data

  • List States

    Retrieve CEIPAL states for a country master data

  • List Work Authorizations

    Retrieve CEIPAL work authorization types master data

  • List Departments

    Retrieve CEIPAL departments master data

  • List Notice Periods

    Retrieve CEIPAL notice period options master data

  • List Race And Ethnicity Options

    Retrieve CEIPAL race and ethnicity options master data

  • List Applicant Note Actions

    Retrieve CEIPAL applicant note action types

  • List Priorities

    Retrieve CEIPAL priority master data

  • List Placements

    List placements with filters

  • Get Placement Details

    Retrieve one placement with payment details, overheads and client details

  • List Job Requisitions

    List job requisitions with filters

  • Get Job Requisition Details

    Retrieve one job requisition with hiring manager, rates, status and attachments

  • List Submissions

    List submissions with filters

  • Get Submission Details

    Retrieve one submission with pipeline status, rates, documents and tagging details

  • List Users

    Retrieve recruiters and other ATS user accounts with status and reporting lines

  • Get User Details

    Retrieve one ATS user account with contact details, status and business unit

  • List Vendors

    Retrieve vendor (supplier) companies with contact details and ownership

  • Get Vendor Details

    Retrieve one vendor company with contact details, ownership and technologies

  • Apply To Job Without Registration

    Submit a job application for a candidate

CEIPAL AI Agent Use Cases

Connect your AI agent to CEIPAL 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

Set Up Your CEIPAL MCP Server in Minutes

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

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

247+ actions

Vincere

233+ actions

SmartRecruiters

169+ actions

Recruitee

155+ actions

Ashby

138+ actions

Manatal

132+ actions

HiBob

129+ actions

CEIPAL MCP Server FAQ

Does StackOne have a CEIPAL MCP server?
Yes. StackOne offers a hosted CEIPAL MCP server with 51 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.
CEIPAL MCP server vs direct API integration: what's the difference?
A CEIPAL MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software work, where backend code calls CEIPAL. A CEIPAL MCP server is for AI agents that discover and call CEIPAL at runtime, such as MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI. StackOne provides both.
How does CEIPAL authentication work for AI agents?
CEIPAL authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK to get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own CEIPAL account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.
Are CEIPAL MCP tools vulnerable to prompt injection?
Yes. CEIPAL MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content, such as 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. It runs regex patterns in ~1ms, then a MiniLM classifier in ~4ms. Accuracy is 88.7%, and it runs entirely on CPU.
What is the context bloat of a CEIPAL agent and how do I avoid it?
Context bloat happens when CEIPAL tool schemas and API responses eat your CEIPAL agent's memory, preventing it from reasoning effectively. A single CEIPAL query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery reduces it by loading only the tools relevant to each query.
Can I limit which actions my CEIPAL agent can access?
Yes. You can limit which actions your CEIPAL 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 CEIPAL MCP server?
Yes. You can create custom agent actions for your CEIPAL MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research CEIPAL's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a CEIPAL MCP server?
Skip a CEIPAL MCP server if your integration is purely software-to-software, because direct CEIPAL 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 CEIPAL actions at runtime.
What AI frameworks and AI clients does the StackOne CEIPAL MCP server support?
The StackOne CEIPAL 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.