How is this different from connecting Endor Labs 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 Endor Labs MCP API changes?

We track the Endor Labs 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 Endor Labs 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 Endor Labs?

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 Endor Labs MCP server myself?

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

Connect Endor Labs MCP to your AI agents, securely.

Q: Is Endor Labs MCP secure?

The server itself exposes 6 tools, and some of them can write to your Endor Labs 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 Endor Labs.

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

Get started for free

Get a demo

Try Endor Labs MCP now

What your agents can ask once Endor Labs MCP is connected.

Select the tools your AI agents can call

6 tools from the Endor Labs MCP schema.

Showing 6 tools

check_dependency_for_vulnerabilitiesreadChecks whether a dependency in the project is vulnerable.
check_dependency_for_risksreadChecks a dependency for security risks, including vulnerabilities and malware.
get_endor_vulnerabilityreadReturns the details of a specific vulnerability from the Endor Labs vulnerability database.
get_resourcereadRetrieves additional context from commonly used Endor Labs resources about the organization's software, such as findings, vulnerabilities and projects.
scanwriteRuns an Endor Labs security scan to detect risks in open source dependencies, find common security issues, and spot credentials accidentally exposed in the Git repository.
security_reviewwritePerforms security review analysis on code diffs: local uncommitted changes, both staged and unstaged, compared to HEAD, or diffs between the main branch and the last commit. It sets the diff-scope option automatically based on the review type. Requires the Enterprise Edition, a namespace in the server configuration, and AI security code review enabled for that namespace.

What Endor Labs MCP exposes

Endor Labs 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
Dependency & Vulnerability Lookup	Checking whether a dependency in the project is vulnerable, checking a dependency for security risks including vulnerabilities and malware, and retrieving the details of a specific vulnerability from the Endor Labs vulnerability database	Read	Read-only lookups against Endor's database, cheap and safe to allow freely. These are the guardrail tools worth making mandatory before an agent adds a dependency
Scanning & Review	Running an Endor Labs security scan over the Git repository to detect risks in open source dependencies, find common security issues and spot accidentally exposed credentials, and performing AI security review on local code diffs	Write	Both read the working tree and send content to the Endor Labs cloud. scan surfaces exposed credentials into the result, so the finding itself is sensitive; security_review needs Enterprise Edition and a namespace with AI security code review enabled
Platform Data	Retrieving additional context from commonly used Endor Labs resources about the organization's software, such as findings, vulnerabilities and projects	Read	Read-only, but it reaches the organization's own findings across projects rather than just the repository in front of the agent

Connect Endor Labs 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 Endor Labs
Find Endor Labs 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 Endor Labs MCP or block it. You allow the exact tools each agent can call, one by one.

Endor Labs 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 Endor Labs 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.	Endor Labs MCP6 documented tools. The server runs locally as a lightweight process launched through npx or a system-installed endorctl, and uses the stdio transport only, so it is configured with a command and args rather than an HTTP URL. Individual tools can be disabled after setup.
Coding assistants	Connection & credentialsper user	Dependency & Vulnerability Lookup3 tools
Internal copilots	Tool access policiesdeny by default	Scanning & Review2 tools
Workflow automations	Request & response inspectioninline	Platform Data1 tool
Compatible MCP clients	Activity monitoringalerts and logs