Connect
Optimize
Secure
Live 47 Actions
BreezyHR MCP Server
for AI Agents
Connect your AI agent to StackOne's BreezyHR MCP server and give it 47 MCP tools out of the box. Auth, tool execution, and security all managed.
BreezyHR MCP Server
Built by 
StackOne
StackOne 
Coverage
47 Agent Actions
Create, read, update, and delete across BreezyHR — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your BreezyHR MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every BreezyHR 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 BreezyHR call.
Tools Discovery →What is the BreezyHR MCP Server?
A BreezyHR MCP server lets AI agents read and write BreezyHR data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's BreezyHR MCP server ships with 47 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 BreezyHR MCP Tools
Every action from BreezyHR's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Candidate Custom Attributes
- Add Candidate Custom Attribute
Add or update a custom attribute on a candidate. This is different from update_candidate_custom_field.
- Get Candidate Custom Attributes
Get custom attribute definitions for candidates in a company
Position Custom Fields
- Get Position Custom Fields
Get custom field values for a position. Only returns fields that already have values set on the position.
- Update Position Custom Field
Update a specific custom field value for a position. The field must already have a value set on the position.
Candidates
- Create Candidate
Add a new candidate to a position
- Update Candidate
Update candidate information
Candidate Custom Fields
- Get Candidate Custom Fields
Get custom field values for a candidate. Returns fields defined at company level with their per-candidate values.
- Update Candidate Custom Field
Update a specific custom field value for a candidate. Use get_candidate_custom_fields to get the custom_field_id.
Other (39)
- Create A New Position
Create a new job position
- Add Note To Candidate Stream
Add a note to candidate's discussion stream
- Send Message To Candidate
Add a new conversation message for the candidate
- Add Candidate Education Entry
Add an education entry to a candidate
- Add Candidate Work History Entry
Add a work history entry to a candidate
- Send Questionnaire To Candidate
Send a questionnaire to a candidate
- Get User
Get information about the authenticated user or another user by ID
- Get User Details
Get detailed information about the currently authenticated user
- List Companies
Get all companies accessible to the authenticated user
- Get Company Details
Get detailed information about a specific company
- Get Position Custom Attributes
Get custom attribute definitions for positions in a company
- List All Positions
Get all positions/jobs for the company
- Get A Specific Position
Get details of a specific position by ID
- Get Position Activity Stream
Get activity stream for a position
- Get Position Team Members
Get team members assigned to a position
- List Position Candidates
Get all candidates for a specific position with abbreviated candidate objects
- Search Candidates By Email
Retrieve all candidates with entered email address across all positions
- Get Candidate Details
Get detailed information about a specific candidate
- Get Candidate Activity Stream
Get activity stream/timeline for a candidate
- Get Candidate Metadata
Get metadata information for a candidate
- Get Candidate Resume
Get the resume file for a candidate
- Get Candidate Documents
Get all documents attached to a candidate
- Get Candidate Conversation
Get email conversation thread for a candidate
- Get Candidate Questionnaires
Get questionnaires submitted by a candidate
- Get Candidate Assessments
Get assessment results for a candidate
- Get Candidate Background Checks
Get background check results for a candidate
- List Pipelines
Get all hiring pipelines for a company
- Get Pipeline Details
Get details of a specific hiring pipeline
- List Questionnaires
Get all questionnaires for a company
- Get Questionnaire Details
Get details of a specific questionnaire
- List Templates
Get all email and message templates for a company
- Get Template Details
Get details of a specific email or message template
- Update A Position
Update details for a given position
- Update Position State
Update the state of a position (draft, published, closed, archived)
- Move Candidate To Another Position
Move a candidate from one position to another
- Update Candidate Stage
Move candidate to a different stage in the hiring pipeline
- Update Candidate Scorecard
Update scorecard/evaluation for a candidate
- Update Questionnaire Response
Update or submit questionnaire responses for a candidate
- Sign Out
Sign out the current user and invalidate the access token
BreezyHR AI Agent Use Cases
Connect your AI agent to BreezyHR 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 BreezyHR MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to BreezyHR 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
BreezyHR MCP Server FAQ
Does StackOne have a BreezyHR MCP server?
Yes. StackOne offers a hosted BreezyHR MCP server with 47 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.
BreezyHR MCP server vs direct API integration — what's the difference?
A BreezyHR MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling BreezyHR. A BreezyHR 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 BreezyHR at runtime. StackOne provides both.
How does BreezyHR authentication work for AI agents?
BreezyHR 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 BreezyHR account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are BreezyHR MCP tools vulnerable to prompt injection?
Yes — BreezyHR 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 BreezyHR agent and how do I avoid it?
Context bloat happens when BreezyHR tool schemas and API responses eat your BreezyHR agent's memory, preventing it from reasoning effectively. A single BreezyHR 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 BreezyHR agent can access?
Yes — you can limit which actions your BreezyHR 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 BreezyHR MCP server?
Yes — you can create custom agent actions for your BreezyHR MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research BreezyHR's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a BreezyHR MCP server?
Skip a BreezyHR MCP server if your integration is purely software-to-software — direct BreezyHR 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 BreezyHR actions at runtime.
What AI frameworks and AI clients does the StackOne BreezyHR MCP server support?
The StackOne BreezyHR 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.