JOIN MCP Server
for AI Agents
Connect your AI agent to StackOne's JOIN MCP server and give it 23 MCP tools out of the box. Auth, tool execution, and security all managed.
StackOne 
Coverage
23 Agent Actions
Create, read, update, and delete across JOIN — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your JOIN MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every JOIN 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 JOIN call.
Tools Discovery →What is the JOIN MCP Server?
A JOIN MCP server lets AI agents read and write JOIN data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's JOIN MCP server ships with 23 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 JOIN MCP Tools
Every action from JOIN's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Jobs
- Create Job
Create a new job
- List Jobs
Retrieve a list of jobs
- Get Job
Retrieve a specific job by ID
- Update Job
Update an existing job
Change Job Status
- Change Job Status
Change the status of a job
Applications
- Create Application
Create a new application
- List Applications
Retrieve a list of applications
- Get Application
Retrieve a specific application by ID
- Delete Application
Delete an application
Application Integration Datas
- Update Application Integration Data
Update the integration external ID for an application
Application Scorecards
- List Application Scorecards
Retrieve scorecards for an application
Candidates
- Update Candidate
Update a candidate's tags
Candidate Notes
- Create Candidate Note
Create a note for a candidate
- List Candidate Notes
Retrieve notes for a candidate
- Update Candidate Note
Update a candidate note
- Delete Candidate Note
Delete a candidate note
Offices
- Create Office
Create a new office
- List Offices
Retrieve a list of offices
- Get Office
Retrieve a specific office by ID
- Update Office
Update an existing office
Categories
- List Categories
Retrieve a list of job categories
Employment Types
- List Employment Types
Retrieve a list of employment types
Seniority Levels
- List Seniority Levels
Retrieve a list of seniority levels
JOIN AI Agent Use Cases
Connect your AI agent to JOIN and help your team scale the recruiting operations they run by hand today.
Use StackOne to connect your AI agent to your ATS and job boards to automate job posting distribution.
ViewUse StackOne to connect your AI agent to your ATS, survey tools, and messaging systems to automate reference checks.
ViewUse StackOne to connect your AI agent to your ATS, HRIS, and document management tools to automate offer letter generation.
ViewSet Up Your JOIN MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to JOIN 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
JOIN MCP Server FAQ
Does StackOne have a JOIN MCP server?
JOIN MCP server vs direct API integration — what's the difference?
How does JOIN authentication work for AI agents?
origin_owner_id.Are JOIN MCP tools vulnerable to prompt injection?
What is the context bloat of a JOIN agent and how do I avoid it?
Can I limit which actions my JOIN agent can access?
Can I create custom agent actions for my JOIN MCP server?
When should I NOT use a JOIN MCP server?
What AI frameworks and AI clients does the StackOne JOIN MCP server support?
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.