Connect
Optimize
Secure
Lever MCP Server
for AI Agents
Production-ready Lever MCP server with 77 extensible actions — plus built-in authentication, security, and optimized execution.
Lever MCP Server
Built by 
StackOne
StackOne 
Coverage
77 Agent Actions
Create, read, update, and delete across Lever — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Lever MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Lever 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 Lever call.
Tools Discovery →What is the Lever MCP Server?
A Lever MCP server lets AI agents read and write Lever data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Lever MCP server ships with 77 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 Lever MCP Tools and Actions
Every action from Lever's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Archive Reasons
- List Archive Reasons
Retrieve all archive reasons configured in the account
- Get Archive Reason
Retrieve a specific archive reason by its unique identifier
Contacts
- Get Contact
Retrieve a specific contact by its unique identifier
- Update Contact
Update the properties of an existing contact
Opportunity Feedbacks
- List Opportunity Feedback
Retrieve all feedback forms submitted for a specific opportunity
- Get Opportunity Feedback
Retrieve a specific feedback form for an opportunity
- Delete Opportunity Feedback
Delete a feedback form from an opportunity
Feedback Templates
- List Feedback Templates
Retrieve all active feedback templates in the account
- Get Feedback Template
Retrieve a specific feedback template by its unique identifier
Opportunity Files
- Upload Opportunity File
Upload a file to a candidate's opportunity
- Get Opportunity File
Retrieve metadata for a single file attached to an opportunity
- List Opportunity Files
List all files attached to an opportunity
- Download Opportunity File
Download the actual file content from an opportunity
- Delete Opportunity File
Delete a file from an opportunity
Opportunity Interviews
- Create Opportunity Interview
Create a new interview for an opportunity
- Get Opportunity Interview
Retrieve a single interview for an opportunity
- List Opportunity Interviews
List all interviews for an opportunity
- Update Opportunity Interview
Update an existing interview
- Delete Opportunity Interview
Delete an interview from an opportunity
Opportunity Notes
- Create Opportunity Note
Create a new note for an opportunity
- Get Opportunity Note
Retrieve a single note from an opportunity
- List Opportunity Notes
List all notes for an opportunity
- Delete Opportunity Note
Delete a note from an opportunity
Opportunity Applications
- List Opportunity Applications
List all applications for an opportunity
- Get Opportunity Application
Retrieve a single application for an opportunity
Opportunity Resumes
- List Opportunity Resumes
List all resumes for an opportunity
- Get Opportunity Resume
Retrieve metadata for a single resume
- Download Opportunity Resume
Download a resume from an opportunity
Opportunity Panels
- List Opportunity Panels
List all interview panels for an opportunity
- Get Opportunity Panel
Retrieve a single interview panel for an opportunity
Opportunity Offers
- List Opportunity Offers
List all offers for an opportunity
- Download Opportunity Offer
Download an offer document
Opportunity Referrals
- List Opportunity Referrals
List all referrals for an opportunity
- Get Opportunity Referral
Retrieve a single referral for an opportunity
Opportunity Forms
- List Opportunity Forms
List all profile forms for an opportunity
- Get Opportunity Form
Retrieve a single profile form for an opportunity
Postings
- Create Posting
Create a new job posting
- List Postings
Retrieve all job postings
- Get Posting
Retrieve a single job posting by ID
- Update Posting
Update an existing job posting
Requisitions
- Create Requisition
Create a new requisition
- List Requisitions
Retrieve all requisitions
- Get Requisition
Retrieve a single requisition by ID
- Update Requisition
Update an existing requisition
Requisition Fields
- Create Requisition Field
Create a custom requisition field
- List Requisition Fields
Retrieve all requisition custom fields
- Get Requisition Field
Retrieve a single requisition field
- Update Requisition Field
Update a custom requisition field
Requisition Field Options
- Add Requisition Field Options
Add options to a dropdown requisition field
- Update Requisition Field Options
Update existing options on a dropdown requisition field
- Delete Requisition Field Options
Delete options from a dropdown requisition field
Stages
- List Stages
Retrieve all pipeline stages
- Get Stage
Retrieve a single pipeline stage by ID
Users
- Create User
Create a new user with Interviewer role
- List Users
Retrieve all users in the account
- Get User
Retrieve a single user by ID
- Update User
Update an existing user
Other (20)
- Upload File
Upload a temporary file for use with posting applications
- Add Tags To Opportunity
Add tags to an opportunity
- Add Sources To Opportunity
Add sources to an opportunity
- Add Links To Opportunity
Add links to an opportunity contact
- List EEO Responses With PII
Retrieve EEO responses including personally identifiable information
- List Anonymous EEO Responses
Retrieve anonymized EEO responses without personally identifiable information
- List Opportunities
Retrieve all opportunities in the pipeline
- Get Opportunity
Retrieve a single opportunity by ID
- List Deleted Opportunities
Retrieve all deleted opportunities
- Get Posting Apply Questions
Get application form questions for a posting
- List Sources
Retrieve all candidate sources
- List Tags
Retrieve all tags
- Update Opportunity Stage
Change the pipeline stage for an opportunity
- Remove Tags From Opportunity
Remove tags from an opportunity
- Remove Sources From Opportunity
Remove sources from an opportunity
- Remove Links From Opportunity
Remove links from an opportunity contact
- Archive/Unarchive Opportunity
Update the archived state of an opportunity
- Apply To Posting
Submit an application to a posting
- Deactivate User
Deactivate a user account
- Reactivate User
Reactivate a deactivated user account
Set Up Your Lever MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Lever 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
Lever 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
Lever MCP Server FAQ
Lever MCP server vs direct API integration — what's the difference?
A Lever MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Lever. A Lever 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 Lever at runtime. StackOne provides both.
How does Lever authentication work for AI agents?
Lever 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 Lever account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Lever MCP tools vulnerable to prompt injection?
Yes — Lever 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 Lever agent and how do I avoid it?
Context bloat happens when Lever tool schemas and API responses eat your Lever agent's memory, preventing it from reasoning effectively. A single Lever 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 Lever agent can access?
Yes — you can limit which actions your Lever 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 Lever MCP server?
Yes — you can create custom agent actions for your Lever MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Lever's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Lever MCP server?
Skip a Lever MCP server if your integration is purely software-to-software — direct Lever 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 Lever actions at runtime.
What AI frameworks and AI clients does the StackOne Lever MCP server support?
The StackOne Lever 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.