Bullhorn MCP Agent
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Bullhorn MCP AgentFind recent placements from the last 30 days"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Bullhorn MCP Agent
A Python Model Context Protocol (MCP) server for Bullhorn CRM, extended for agent-oriented recruiting workflows.
This project is based on the open-source osherai/bullhorn-mcp-python project and expands it with additional tools intended for AI agents, recruiting automation, candidate document workflows, and cross-system orchestration.
The goal is to provide a controlled MCP layer between an AI agent and Bullhorn rather than giving the model direct access to Bullhorn credentials or unrestricted API access.
What It Does
The server exposes Bullhorn functionality as MCP tools that can be called by MCP-compatible AI clients such as Codex.
Current MCP Tools
Connection
connection_statusChecks whether required Bullhorn environment variables are configured.
Attempts to verify Bullhorn connectivity when credentials are present.
Does not expose credentials to the AI client.
Jobs
list_jobsList and filter Bullhorn JobOrders.
Supports Lucene search, status filtering, limits, and field selection.
get_jobRetrieve a specific JobOrder by Bullhorn ID.
Candidates
list_candidatesList and filter Bullhorn Candidates.
Supports Lucene search, status filtering, limits, and field selection.
get_candidateRetrieve a specific Candidate by Bullhorn ID.
get_candidate_filesList files attached to an existing Bullhorn Candidate.
upload_candidate_resumeUpload a local resume or document to an existing Bullhorn Candidate.
Placements
get_recent_placementsRetrieve Bullhorn Placement records created within a specified number of days.
Includes bounded date and result limits for safer agent use.
Generic Bullhorn Access
search_entitiesSearch Bullhorn entities using Lucene query syntax.
query_entitiesQuery Bullhorn entities using Bullhorn's SQL-like/JPQL-style query syntax.
Related MCP server: Bullhorn CRM MCP Server
Example Architecture
The MCP server acts as a controlled adapter between an AI agent and Bullhorn.
AI Agent / Codex
|
| MCP
v
Bullhorn MCP Agent
|
| Bullhorn REST API
v
BullhornThis server cannot be deployed
Maintenance
Related MCP Connectors
Let AI agents query data and act across all your business apps via MCP.
Connect MCP clients to 2,000+ AI models without managing provider API keys.
Query InterviewFlowAI candidate and interview data from MCP-compatible AI assistants.
Remote MCP for 1,500+ APIs. Vault-managed credentials; OAuth or API key. Search, load, and execute.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceThis read-only MCP Server allows you to connect to Bullhorn CRM data from Claude Desktop through CData JDBC Drivers. Free (beta) read/write servers available at https://www.cdata.com/solutions/mcp1MIT
- AlicenseAqualityFmaintenanceEnables AI assistants to query Bullhorn CRM data using natural language through direct REST API access with OAuth 2.0 authentication.61MIT

HireFrog MCPofficial
AlicenseNot gradedqualityBmaintenanceEnables MCP-compatible AI assistants to securely access a user's job-search account, letting them search and save jobs, analyze job fit, and retrieve job queue and profile summaries with links back to the web app.MIT- AlicenseNot gradedqualityCmaintenanceA hosted, OAuth-authenticated MCP endpoint exposing 176 tools that let AI assistants read and write jobs, candidates, applications, interviews, scorecards, prospects, talent pools, and imports within an organization's own applicant tracking data, scoped to the signed-in user's existing permissions.MIT