Skip to main content

Announcing StackOne Defender: leading open-source prompt injection guard for your agent • Read More →

Connect

Connectors Agent Auth MCP Connector Builder

Optimize

Tool Discovery Falcon Engine

Secure

Defender
Connectors

HRIS / HCM

Employee Onboarding Employee Offboarding

Recruiting

Application Screening Interview Scheduling

Customer Support

Ticket Triage Voice Call Summarization

Sales & CRM

Deal Risk Scoring Lead Qualification

Accounting & Finance

Invoice Processing Month-End Accruals

Marketing

Campaign Reports Lead Nurture Sequences
View all use cases

Developers

Docs Changelog Status

Learn

Blog Case Studies Events Partners
Pricing
Login Book Demo Start Free

Workable MCP Server
for AI Agents

Production-ready Workable MCP server with 70 extensible actions — plus built-in authentication, security, and optimized execution.

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

Coverage

70 Agent Actions

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

MCP Actions → Create Actions →

Authentication

Agent Tool Authentication

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

Agent Auth →

Security

Agent Protection

Every Workable 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 Workable call.

Tools Discovery →

What is the Workable MCP Server?

A Workable MCP server lets AI agents read and write Workable data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Workable MCP server ships with 70 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, and optimized agent context. Connect it from MCP clients like Claude Desktop, Cursor, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.

All Workable MCP Tools and Actions

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

Candidates

  • Copy Candidate

    Copy candidate to another job

  • List Candidates

    Get all candidates across all jobs

  • Get Candidate

    Get detailed information about a specific candidate

  • Update Candidate

    Update candidate information

Members

  • List Members

    Get all members in the account

  • Update Member

    Update an existing member's roles and collaboration rules

  • Delete Member

    Deactivate a member in the account

Departments

  • Create Department

    Create a new department

  • List Departments

    Get all departments

  • Update Department

    Update an existing department

  • Delete Department

    Delete a department

Requisitions

  • Create Requisition

    Create a new requisition

  • List Requisitions

    Get all requisitions

  • Get Requisition

    Get a specific requisition by code

  • Update Requisition

    Update an existing requisition

Jobs

  • List Jobs

    Get all jobs in the account

  • Get Job

    Get detailed information about a specific job

Events

  • List Events

    Get all scheduled events

  • Get Event

    Get detailed information about a specific event

Employees

  • Create Employee

    Create a new employee record

  • List Employees

    Get all employees

  • Get Employee

    Get detailed information about a specific employee

  • Update Employee

    Update an existing employee record

Employee Documents

  • Create Employee Document

    Upload a document for an employee

  • Get Employee Documents

    Get all documents for an employee

Time Off Requests

  • Create Time Off Request

    Create a new time off request for an employee

  • List Time Off Requests

    Get all time off requests

Webhook Subscriptions

  • Create Webhook Subscription

    Create a new webhook subscription

  • List Webhook Subscriptions

    Get all webhook subscriptions

  • Delete Webhook Subscription

    Delete a webhook subscription

Other (40)

  • Create Job Candidate

    Create a new candidate for a specific job

  • Create Talent Pool Candidate

    Create a new candidate in the talent pool

  • List Accounts

    Get all accounts accessible by user

  • Get Account Details

    Get detailed information about a specific account

  • List Permission Sets

    Get all permission sets in the account

  • List Legal Entities

    Get all legal entities configured in the account

  • List Disqualification Reasons

    Get all disqualification reasons

  • Get Candidate Activities

    Get activity timeline for a candidate

  • Get Candidate Files

    Get files associated with a candidate

  • Get Candidate Offer

    Get offer details for a candidate

  • List Recruiters

    Get all external recruiters in the account

  • List Stages

    Get all recruitment pipeline stages

  • Get Offer

    Get a specific offer by ID

  • Get Job Activities

    Get activity stream for a job

  • Get Job Application Form

    Get application form details for a job

  • Get Job Questions

    Get questions for a job

  • Get Job Stages

    Get recruitment pipeline stages for a job

  • Get Job Custom Attributes

    Get custom attributes for a job

  • Get Job Members

    Get members in the hiring team for a job

  • Get Job Recruiters

    Get external recruiters for a job

  • List Custom Attributes

    Get all custom attributes

  • List Employee Fields

    Get all employee field configurations

  • List Work Schedules

    Get all work schedule configurations

  • List Time Off Categories

    Get all time off categories

  • List Time Off Balances

    Get time off balances for employees

  • Move Candidate To Stage

    Move candidate to a different stage

  • Update Candidate Custom Attribute

    Update a custom attribute value for candidate

  • Comment On Candidate

    Add a comment to candidate's profile

  • Tag Candidate

    Add or remove tags from candidate

  • Disqualify Candidate

    Disqualify a candidate

  • Revert Candidate Disqualification

    Revert a candidate's disqualification

  • Relocate Candidate

    Move candidate to another job

  • Rate Candidate

    Add a rating to candidate

  • Invite Member

    Invite a new member to the account

  • Enable Member

    Restore a previously deactivated member

  • Merge Departments

    Merge a department into another

  • Approve Requisition

    Approve a requisition

  • Reject Requisition

    Reject a requisition

  • Approve Offer

    Approve an offer (must be in a compatible state)

  • Reject Offer

    Reject an offer (must be in a compatible state)

Set Up Your Workable MCP Server in Minutes

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

MCP Clients

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>"
      ]
    }
  }
}

More Recruiting MCP Servers

JobAdder

246+ actions

Vincere

206+ actions

SmartRecruiters

164+ actions

Ashby

137+ actions

Factorial

127+ actions

HiBob

123+ actions

HiBob (with Webhooks)

123+ actions

All Recruiting MCP Servers →

Workable MCP Server 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

Workable MCP Server FAQ

Workable MCP server vs direct API integration — what's the difference?
A Workable MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Workable. A Workable 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 Workable at runtime. StackOne provides both.
How does Workable authentication work for AI agents?
Workable 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 Workable account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.
Are Workable MCP tools vulnerable to prompt injection?
Yes — Workable 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 Workable agent and how do I avoid it?
Context bloat happens when Workable tool schemas and API responses eat your Workable agent's memory, preventing it from reasoning effectively. A single Workable 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 Workable agent can access?
Yes — you can limit which actions your Workable 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 Workable MCP server?
Yes — you can create custom agent actions for your Workable MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Workable's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Workable MCP server?
Skip a Workable MCP server if your integration is purely software-to-software — direct Workable 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 Workable actions at runtime.
What AI frameworks and AI clients does the StackOne Workable MCP server support?
The StackOne Workable 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