Connect
Optimize
Secure
Bullhorn MCP Server
for AI Agents
Production-ready Bullhorn MCP server with 47 extensible actions — plus built-in authentication, security, and optimized execution.
Bullhorn MCP Server
Built by 
StackOne
StackOne 
Coverage
47 Agent Actions
Create, read, update, and delete across Bullhorn — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Bullhorn MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Bullhorn 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 Bullhorn call.
Tools Discovery →What is the Bullhorn MCP Server?
A Bullhorn MCP server lets AI agents read and write Bullhorn data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Bullhorn MCP server ships with 47 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 Bullhorn MCP Tools and Actions
Every action from Bullhorn's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Candidates
- Create Candidate
Create a new candidate record
- List Candidates
Retrieve a list of candidates using search or query
- Get Candidate
Retrieve a specific candidate by ID
- Update Candidate
Update an existing candidate record
- Delete Candidate
Delete a candidate record
Client Contacts
- Create Client Contact
Create a new client contact record
- List Client Contacts
Retrieve a list of client contacts using search or query
- Get Client Contact
Retrieve a specific client contact by ID
- Update Client Contact
Update an existing client contact record
- Delete Client Contact
Delete a client contact record
Client Corporations
- Create Client Corporation
Create a new client corporation (company) record
- List Client Corporations
Retrieve a list of client corporations (companies) using search or query
- Get Client Corporation
Retrieve a specific client corporation by ID
- Update Client Corporation
Update an existing client corporation record
- Delete Client Corporation
Delete a client corporation record
Job Orders
- List Job Orders
Retrieve a list of job orders using search or query
- Get Job Order
Retrieve a specific job order by ID
- Update Job Order
Update an existing job order record
- Delete Job Order
Delete a job order record
Placements
- Create Placement
Create a new placement record
- List Placements
Retrieve a list of placements using search or query
- Get Placement
Retrieve a specific placement by ID
- Update Placement
Update an existing placement record
Notes
- Create Note
Create a new note record
- List Notes
Retrieve a list of notes using search or query
- Get Note
Retrieve a specific note by ID
- Update Note
Update an existing note record
- Delete Note
Delete a note record
Tasks
- Create Task
Create a new task record
- List Tasks
Retrieve a list of tasks using search or query
- Get Task
Retrieve a specific task by ID
- Update Task
Update an existing task record
- Delete Task
Delete a task record
Appointments
- Create Appointment
Create a new appointment record
- List Appointments
Retrieve a list of appointments using search or query. Need to be enabled feature "Calendar & Appointments" in your Bullhorn account.
- Get Appointment
Retrieve a specific appointment by ID
- Update Appointment
Update an existing appointment record
- Delete Appointment
Delete an appointment record
Job Submissions
- Create Job Submission
Submit a candidate to a specific job opening by creating a new job submission record
- List Job Submissions
Retrieve a list of job submissions representing candidate applications to specific job openings
- Get Job Submission
Retrieve comprehensive details about a specific job submission record by its unique identifier
- Update Job Submission
Update an existing job submission record to reflect progress through the hiring pipeline
- Delete Job Submission
Remove a job submission record from active use while preserving it for audit history
All Entity Types
- List All Entity Types
Retrieve a complete list of all available entity types in the Bullhorn system
Entity Field Metadatas
- Get Entity Field Metadata
Retrieve detailed field definitions and metadata for a specific Bullhorn entity type
Entitys
- Search Entity
Search for records in any Bullhorn entity using Lucene search syntax or JPQL query
Entity Records
- Get Entity Record
Retrieve a specific record from any Bullhorn entity by ID
Set Up Your Bullhorn MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Bullhorn in under 10 lines of code.
MCP Clients
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>"
]
}
}
}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
Bullhorn 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
Bullhorn MCP Server FAQ
Bullhorn MCP server vs direct API integration — what's the difference?
A Bullhorn MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Bullhorn. A Bullhorn 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 Bullhorn at runtime. StackOne provides both.
How does Bullhorn authentication work for AI agents?
Bullhorn 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 Bullhorn account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Bullhorn MCP tools vulnerable to prompt injection?
Yes — Bullhorn 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 Bullhorn agent and how do I avoid it?
Context bloat happens when Bullhorn tool schemas and API responses eat your Bullhorn agent's memory, preventing it from reasoning effectively. A single Bullhorn 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 Bullhorn agent can access?
Yes — you can limit which actions your Bullhorn 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 Bullhorn MCP server?
Yes — you can create custom agent actions for your Bullhorn MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Bullhorn's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Bullhorn MCP server?
Skip a Bullhorn MCP server if your integration is purely software-to-software — direct Bullhorn 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 Bullhorn actions at runtime.
What AI frameworks and AI clients does the StackOne Bullhorn MCP server support?
The StackOne Bullhorn 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.