How is this different from connecting Checkr MCP directly?

Connected directly, an agent sees every tool the server exposes and holds the credential itself. Through TrustGate you choose which tools each agent gets, and every call is logged against the agent that made it.

What if the Checkr MCP API changes?

We track the Checkr MCP schema, so the tool catalogue stays current. Tools you have already allowed keep working, and anything new stays denied until you enable it.

Can I give different agents different Checkr tools?

Yes. Access is set per agent: one can get a handful of read tools, another the full set. You grant the whole MCP or single tools within it.

Where can I see what my agents did in Checkr?

Every call is logged against the agent that made it, with the tool it used. Activity can be sent on to your own monitoring.

Do I need to run the Checkr MCP server myself?

No. TrustGate connects to the Checkr MCP server and sits in front of it. Your agent only talks to your TrustGate URL, never to Checkr directly.

Connect Checkr MCP to your AI agents, securely.

Q: Is Checkr MCP secure?

The server itself exposes 6 tools, and some of them can write to your Checkr account. Behind TrustGate an agent only sees the tools you allow, requests and responses are inspected, and every call is logged. Anything outside the allowlist is denied before it reaches Checkr.

One secured endpoint for every Checkr call your AI agents make, scoped per user, inspected, and logged.

Get started for free

Get a demo

Try Checkr MCP now

What your agents can ask once Checkr MCP is connected.

Select the tools your AI agents can call

6 tools from the Checkr MCP schema.

Showing 6 tools

get_candidatereadGet a candidate by ID.
get_candidates_tablereadList candidates with filtering options, formatted for table display.
get_reportreadGet a background check report by ID. Full SSN, date of birth, address and record-level detail are redacted before the response leaves Checkr.
request_candidate_verificationwriteSend a 6-digit verification code to the candidate's email (OTP flow, step 1). Candidate MCP.
verify_candidate_otpreadVerify the candidate's OTP code and lock the session to that candidate (OTP flow, step 2). Candidate MCP.
get_reportreadReturn the identified candidate's latest background check report. Candidate MCP.

What Checkr MCP exposes

Checkr MCP groups its 6 tools into 3 categories, each with a suggested starting policy.

All 6 tools as JSON, ready to paste.

Category	Covers	Access	Suggested policy
Candidate verification	The Candidate MCP flow: sending a 6-digit code to the candidate's email, verifying it and locking the session to that candidate, then returning that candidate's latest background check report	Read / Write	The OTP lock is what keeps an agent from reading a report for anyone other than the verified candidate, so the session belongs in the log. request_candidate_verification sends email to a real person, so rate-limit it per agent
Candidates	Getting a candidate by ID and listing candidates with filtering options, formatted for table display	Read	Read-only, but every result names a real person, with name and email returned so the right candidate can be confirmed. Limit which agents can list candidates, since a table view pulls many people at once
Reports	Getting a background check report by ID, with full SSN, date of birth, address and record-level detail redacted before the response leaves Checkr	Read	The most sensitive call on the server. Redaction removes identifiers, not the outcome of the check, so allow it only for agents with a hiring reason to see results and keep the requested report IDs in the log

Connect Checkr MCP to your AI agent

Four steps, under ten minutes.

01
Sign in to NeuralTrust
Open the NeuralTrust platform, sign in and go to Getting started, then Connect your tools.
02
Choose your agent
When asked which agent you use, pick Claude Code, Codex, Cursor, Windsurf, Copilot or your own code.
03
Connect Checkr
Find Checkr in the tool list and connect it.
04
Connect your agent
Follow the steps on screen to add the config to your agent, then send the test prompt.

Permissions down to the single tool

You do not allow Checkr MCP or block it. You allow the exact tools each agent can call, one by one.

Checkr MCP	6 TOOLS AVAILABLE
Code review agent	4 tools, read only
Issue triage bot	9 tools
Platform team assistant	all 6 tools

Tool by toolConnecting the server is not the unit of access. Each tool is granted on its own.
Default denyA tool you have not enabled is never exposed to the agent.
Approval on writesTools that change or delete things can require a human to confirm.

Is Checkr MCP secure?

One endpoint instead of raw credentials. Every call is checked against policy and logged.

AI agentsConnect through your MCP client configuration.	NeuralTrustApply controls based on your configuration.	Checkr MCP6 documented tools across two remote servers over streamable HTTP. The Customer MCP at mcp.checkr.com signs in with the user's Checkr account through OAuth Dynamic Client Registration, with nothing provisioned in advance. The Candidate MCP at mcp.checkr.com/candidate-mcp/ uses OAuth 2.0 client credentials from the Checkr Dashboard and is session-stateful, with an Mcp-Session-Id header on every request.
Coding assistants	Connection & credentialsper user	Candidate verification3 tools
Internal copilots	Tool access policiesdeny by default	Candidates2 tools
Workflow automations	Request & response inspectioninline	Reports1 tool
Compatible MCP clients	Activity monitoringalerts and logs