Connect
Optimize
Secure
Live 54 Actions
CATS MCP Server
for AI Agents
Connect your AI agent to StackOne's CATS MCP server and give it 54 MCP tools out of the box. Auth, tool execution, and security all managed.
CATS MCP Server
Built by 
StackOne
StackOne 
Coverage
54 Agent Actions
Create, read, update, and delete across CATS — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your CATS MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every CATS 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 CATS call.
Tools Discovery →What is the CATS MCP Server?
A CATS MCP server lets AI agents read and write CATS data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's CATS MCP server ships with 54 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 CATS MCP Tools
Every action from CATS's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Candidates
- Create Candidate
Create a new candidate in CATS.
- List Candidates
List all candidates in CATS.
- Get Candidate
Retrieve a single candidate by ID.
- Search Candidates
Search candidates by a text query.
- Update Candidate
Update an existing candidate by ID.
- Delete Candidate
Delete a candidate by ID.
Jobs
- Create Job
Create a new job order in CATS.
- List Jobs
List all job orders in CATS.
- Get Job
Retrieve a single job order by ID.
- Search Jobs
Search job orders by a text query.
- Update Job
Update an existing job order by ID.
- Delete Job
Delete a job order by ID.
Pipelines
- Create Pipeline
Create a new pipeline linking a candidate to a job.
- List Pipelines
List all pipelines (candidate-job applications) in CATS.
- Get Pipeline
Retrieve a single pipeline by ID.
- Update Pipeline
Update an existing pipeline by ID.
- Delete Pipeline
Delete a pipeline by ID.
Companies
- List Companies
List all companies in CATS.
- Search Companies
Search companies by a text query.
Companys
- Create Company
Create a new company in CATS.
- Get Company
Retrieve a single company by ID.
- Update Company
Update an existing company by ID.
- Delete Company
Delete a company by ID.
Company Departments
- Create Company Department
Add a new department to a company in CATS.
- List Company Departments
List all departments for a company in CATS.
- Get Company Department
Retrieve a single department by ID.
- Update Company Department
Update a department's name in CATS.
- Delete Company Department
Delete a department from CATS.
Contacts
- Create Contact
Create a new contact in CATS.
- List Contacts
List all contacts in CATS.
- Get Contact
Retrieve a single contact by ID.
- Search Contacts
Search contacts by a text query.
- Update Contact
Update an existing contact by ID.
- Delete Contact
Delete a contact by ID.
Activities
- List Activities
List all activities in CATS.
- Search Activities
Search activities by a text query.
Activitys
- Get Activity
Retrieve a single activity by ID.
- Update Activity
Update an existing activity by ID.
- Delete Activity
Delete an activity by ID.
Tasks
- Create Task
Create a new task in CATS.
- List Tasks
List all tasks in CATS.
- Get Task
Retrieve a single task by ID.
Other (12)
- List Candidate Pipelines
List all pipelines (job applications) for a candidate.
- List Candidate Tasks
List all tasks associated with a candidate.
- List Job Pipelines
List all pipelines (applications) for a job.
- List Job Tasks
List all tasks associated with a job order.
- List Company Tasks
List all tasks associated with a company.
- List Contact Tasks
List all tasks associated with a contact.
- Filter Candidates
Filter candidates by a specific field and value.
- Filter Jobs
Filter job orders by a specific field and value.
- Filter Pipelines
Filter pipelines by a specific field and value.
- Filter Companies
Filter companies by a specific field and value.
- Filter Contacts
Filter contacts by a specific field and value.
- Filter Activities
Filter activities by a specific field and value.
CATS AI Agent Use Cases
Connect your AI agent to CATS 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 Reference Check Automation
Use StackOne to connect your AI agent to your ATS, survey tools, and messaging systems to automate reference checks.
View Offer Letter Generation
Use StackOne to connect your AI agent to your ATS, HRIS, and document management tools to automate offer letter generation.
ViewSet Up Your CATS MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to CATS in under 10 lines of code.
Agent Frameworks
JSON{
"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>"
]
}
}
}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
CATS MCP Server FAQ
Does StackOne have a CATS MCP server?
Yes. StackOne offers a hosted CATS MCP server with 54 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.
CATS MCP server vs direct API integration — what's the difference?
A CATS MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling CATS. A CATS 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 CATS at runtime. StackOne provides both.
How does CATS authentication work for AI agents?
CATS 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 CATS account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are CATS MCP tools vulnerable to prompt injection?
Yes — CATS 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 CATS agent and how do I avoid it?
Context bloat happens when CATS tool schemas and API responses eat your CATS agent's memory, preventing it from reasoning effectively. A single CATS 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 CATS agent can access?
Yes — you can limit which actions your CATS 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 CATS MCP server?
Yes — you can create custom agent actions for your CATS MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research CATS's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a CATS MCP server?
Skip a CATS MCP server if your integration is purely software-to-software — direct CATS 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 CATS actions at runtime.
What AI frameworks and AI clients does the StackOne CATS MCP server support?
The StackOne CATS 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.