How is this different from connecting Semgrep 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 Semgrep MCP API changes?

We track the Semgrep 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 Semgrep 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 Semgrep?

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 Semgrep MCP server myself?

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

Connect Semgrep MCP to your AI agents, securely.

Q: Is Semgrep MCP secure?

The server itself exposes 9 tools, and some of them can write to your Semgrep 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 Semgrep.

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

Get started for free

Get a demo

Try Semgrep MCP now

What your agents can ask once Semgrep MCP is connected.

Select the tools your AI agents can call

9 tools from the Semgrep MCP schema.

Showing 9 tools

semgrep_scanreadScans code files for security vulnerabilities with a given config string.
semgrep_scan_with_custom_rulereadScans code files using a custom Semgrep rule supplied by the caller.
semgrep_scan_remotereadScans code content supplied by the caller with Semgrep and returns the findings in JSON format.
semgrep_scan_supply_chainreadRuns a Semgrep supply chain scan on a workspace directory to identify vulnerabilities in third-party dependencies.
get_abstract_syntax_treereadOutputs the Abstract Syntax Tree of a piece of code.
semgrep_findingsreadFetches Semgrep findings from the Semgrep AppSec Platform API. Requires login and a Semgrep token.
semgrep_whoamireadReturns the identity of the current Semgrep user. Works only with JWTs, not API tokens.
semgrep_rule_schemareadFetches the latest Semgrep rule JSON Schema.
get_supported_languagesreadReturns the list of languages Semgrep supports.

What Semgrep MCP exposes

Semgrep MCP groups its 9 tools into 4 categories, each with a suggested starting policy.

All 9 tools as JSON, ready to paste.

Category	Covers	Access	Suggested policy
Scan Code	Security scanning of code files, scanning with a given config string, and scanning with a custom Semgrep rule	Read	Code is sent to the scanner; avoid passing files that carry secrets
Meta	The list of supported languages and the latest Semgrep rule JSON Schema	Read	Reference lookups; safe to allow broadly
Understand Code	Producing the abstract syntax tree of a piece of code	Read	Read-only parsing; no findings are recorded
Cloud Platform	Findings from the Semgrep AppSec Platform API. Requires login and a Semgrep token	Read	Needs SEMGREP_APP_TOKEN; findings describe unfixed vulnerabilities, so restrict access

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

Semgrep MCP	9 TOOLS AVAILABLE
Code review agent	4 tools, read only
Issue triage bot	9 tools
Platform team assistant	all 9 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 Semgrep 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.	Semgrep MCP9 documented tools, all read-only. The server also ships one prompt and two resources.
Coding assistants	Connection & credentialsper user	Scan Code4 tools
Internal copilots	Tool access policiesdeny by default	Meta2 tools
Workflow automations	Request & response inspectioninline	Cloud Platform2 tools
Compatible MCP clients	Activity monitoringalerts and logs	Understand Code1 tool