Connect
Optimize
Secure
Live 62 Actions
Checkr MCP Server
for AI Agents
Connect your AI agent to StackOne's Checkr MCP server and give it 62 MCP tools out of the box. Auth, tool execution, and security all managed.
Checkr MCP Server
Built by 
StackOne
StackOne 
Coverage
62 Agent Actions
Create, read, update, and delete across Checkr — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Checkr MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Checkr 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 Checkr call.
Tools Discovery →What is the Checkr MCP Server?
A Checkr MCP server lets AI agents read and write Checkr data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Checkr MCP server ships with 62 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 Checkr MCP Tools
Every action from Checkr'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 in Checkr with contact details, identification, and address information for background check processing.
- List Candidates
Retrieve a paginated list of existing candidates with optional filtering by email, name, adjudication, custom ID, and date ranges.
- Get Candidate
Retrieve an existing candidate by ID, optionally embedding related reports and geos.
- Update Candidate
Update an existing candidate's details. After a report has been ordered, only null-valued fields and certain always-updatable fields can be changed.
Reports
- Create Report
Create a new background check report for a candidate using a specified package. Use list_packages to discover available package slugs.
- Get Report
Retrieve an existing report by ID, optionally embedding related screening sub-resources.
- Update Report
Update the package or adjudication of an existing report.
Packages
- List Packages
Retrieve a paginated list of existing background check packages.
- Get Package
Retrieve an existing background check package by ID.
- Delete Package
Delete an existing background check package by ID.
Invitations
- Create Invitation
Create a new invitation to send a candidate an email to submit their information for a background check. Use list_packages to discover available package slugs.
- List Invitations
Retrieve a paginated list of existing invitations with optional filtering by candidate ID or status.
- Get Invitation
Retrieve an existing invitation by ID.
Adverse Actions
- Create Adverse Action
Create a new adverse action for a report, initiating the pre-adverse action notice process. Use list_adverse_items first to get valid adverse_item_ids for the report.
- List Adverse Actions
Retrieve all formal adverse action notices associated with a report. These are the official pre/post adverse action records. To get individual flagged records within screenings, use list_adverse_items instead.
- Get Adverse Action
Retrieve an existing adverse action by ID.
Subscriptions
- Create Subscription
Create a new repeating background check subscription for a candidate on a defined interval. Use list_packages to discover available package slugs and list_candidates to get the candidate_id.
- List Subscriptions
Retrieve a paginated list of existing subscriptions with optional filtering.
- Get Subscription
Retrieve an existing subscription by ID.
- Update Subscription
Update an existing subscription's settings.
Continuous Checks
- Create Continuous Check
Create a new continuous check enrollment for a candidate to enable ongoing criminal or MVR monitoring.
- List Continuous Checks
List existing continuous checks for a candidate.
- Get Continuous Check
Retrieve an existing continuous check by ID.
- Update Continuous Check
Update an existing continuous check's node or work locations.
Webhooks
- Create Webhook
Create a new webhook endpoint to receive event notifications from Checkr.
- List Webhooks
Retrieve a list of existing webhooks for the authenticated account.
- Get Webhook
Retrieve an existing webhook by ID.
- Delete Webhook
Delete an existing webhook by ID.
Candidate Documents
- Upload Candidate Document
Upload a new document for a candidate.
- List Candidate Documents
List all documents for a candidate, optionally filtered by document type.
Verifications
- List Verifications
List existing verifications for a report.
- Get Verification
Retrieve an existing verification by ID. Use list_verifications with a report_id first to discover verification IDs.
Report Tags
- Add Report Tag
Add a tag to a report, returning the updated list of all tags for that report.
- List Report Tags
Retrieve all tags currently associated with a report.
Programs
- List Programs
Retrieve a paginated list of programs configured for your account.
- Get Program
Retrieve an existing program by ID.
Other (26)
- Get Report ETA
Retrieve the estimated completion date (ETA) for a report. Returns when the report is expected to finish processing — not the report itself. Use get_report to retrieve the full report details.
- Get SSN Trace
Retrieve an SSN Trace screening result by ID. Use get_report first to extract the ssn_trace_id from the report response.
- Get National Criminal Search
Retrieve a National Criminal Search screening result by ID. Use get_report first to extract the national_criminal_search_id from the report response.
- Get County Criminal Search
Retrieve a County Criminal Search screening result by ID. Use get_report first to extract the county_criminal_search_ids from the report response.
- Get State Criminal Search
Retrieve a State Criminal Search screening result by ID. Use get_report first to extract the state_criminal_search_ids from the report response.
- Get Federal Criminal Search
Retrieve a Federal Criminal Search screening result by ID. Use get_report first to extract the federal_criminal_search_ids from the report response.
- Get Sex Offender Search
Retrieve a Sex Offender Registry Search screening result by ID. Use get_report first to extract the sex_offender_search_id from the report response.
- Get Global Watchlist Search
Retrieve a Global Watchlist Search screening result by ID. Use get_report first to extract the global_watchlist_search_id from the report response.
- Get Motor Vehicle Report
Retrieve a Motor Vehicle Report screening result by ID. Use get_report first to extract the motor_vehicle_report_id from the report response.
- Get Education Verification
Retrieve an Education Verification screening result by ID. Use get_report first to extract the education_verification_id from the report response.
- Get Employment Verification
Retrieve an Employment Verification screening result by ID. Use get_report first to extract the employment_verification_id from the report response.
- Get Drug & Alcohol Clearinghouse Search
Retrieve a Drug & Alcohol Clearinghouse Search screening result by ID. Use get_report first to extract the drug_alcohol_clearinghouse_search_id from the report response.
- Get FACIS Search
Retrieve a FACIS (Fraud and Abuse Control Information System) Search screening result by ID. Use get_report first to extract the facis_search_id from the report response.
- List Adverse Items
List individual flagged records (adverse items) from a report's screenings. These are specific findings that can be selected as the basis for creating a formal adverse action via create_adverse_action. Not the same as list_adverse_actions which returns formal notices.
- Get Document
Retrieve a document by ID, including a time-limited download URL.
- Get Account
Retrieve authenticated account details.
- List Users
Retrieve a paginated list of all existing users on the account.
- List Counties
Get counties by state(s) for county criminal search configuration.
- List Report Addresses
Retrieve all addresses associated with a report.
- List Geos
Retrieve a paginated list of geographic locations (geos) configured for your account.
- Delete Candidate PII
Request the removal of personally identifiable information (PII) from an existing candidate.
- Complete Report
Cancel all pending or suspended screenings within a report and force-mark it as complete. This is destructive — it stops all in-progress screenings. To update report fields like package or adjudication, use update_report instead.
- Cancel Invitation
Cancel an existing invitation by ID.
- Cancel Adverse Action
Cancel an existing adverse action by ID.
- Cancel Subscription
Cancel an existing subscription by ID.
- Cancel Continuous Check
Cancel an existing continuous check by ID.
Checkr AI Agent Use Cases
Connect your AI agent to Checkr and help your team scale the HR operations they run by hand today.
Employee Onboarding
Use StackOne to connect your AI agent to your HRIS, identity management, and LMS to automate employee onboarding.
View HR Policy Q&A Chatbot
Use StackOne to connect your AI agent to your HRIS, knowledge base, and messaging tools to automate HR policy Q&A.
View Job Posting Distribution
Use StackOne to connect your AI agent to your ATS and job boards to automate job posting distribution.
ViewSet Up Your Checkr MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Checkr 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>"
]
}
}
}Check More HRIS / HCM MCP Servers
UKG Ready
139+ actions
Workday (Rest and Soap)
128+ actions
Factorial
127+ actions
HiBob
123+ actions
Oracle Fusion HCM
120+ actions
Humaans
117+ actions
SAP SuccessFactors
111+ actions
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
Checkr MCP Server FAQ
Does StackOne have a Checkr MCP server?
Yes. StackOne offers a hosted Checkr MCP server with 62 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.
Checkr MCP server vs direct API integration — what's the difference?
A Checkr MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Checkr. A Checkr 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 Checkr at runtime. StackOne provides both.
How does Checkr authentication work for AI agents?
Checkr 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 Checkr account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Checkr MCP tools vulnerable to prompt injection?
Yes — Checkr 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 Checkr agent and how do I avoid it?
Context bloat happens when Checkr tool schemas and API responses eat your Checkr agent's memory, preventing it from reasoning effectively. A single Checkr 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 Checkr agent can access?
Yes — you can limit which actions your Checkr 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 Checkr MCP server?
Yes — you can create custom agent actions for your Checkr MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Checkr's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Checkr MCP server?
Skip a Checkr MCP server if your integration is purely software-to-software — direct Checkr 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 Checkr actions at runtime.
What AI frameworks and AI clients does the StackOne Checkr MCP server support?
The StackOne Checkr 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.