Tracecat

Semgrep MCP server

Run Semgrep scans and pull AppSec Platform findings from your AI agents.

AppSec
stdio
Official docs

About

Connect Tracecat to Semgrep to run SAST scans and pull AppSec Platform findings for AppSec engineers and security agents reviewing code changes. You can scan a repository on demand with default or custom rules and inspect the AST for any snippet. From there, pull platform findings for a project, draft new detection rules, and triage pull requests with precision.

Setup

  1. 1

    Create an access token

    The Semgrep MCP server runs scans locally without auth. To pull findings from the Semgrep AppSec Platform you set the `SEMGREP_APP_TOKEN` environment variable with a token generated from your Semgrep account settings.

  2. 2

    Select the Semgrep tile in the Tracecat MCP catalog

    Open the MCP catalog in your workspace, select the Semgrep tile, and paste your access token.

  3. 3

    Enable Semgrep in your agent

    In your ai.agent action or Agents tools tab, select Semgrep from the MCP integrations dropdown.

Tools

security_checkScan code for security vulnerabilities with Semgrep's default rulesets.
semgrep_scanRun a Semgrep scan against a given code path with a chosen config.
semgrep_scan_with_custom_ruleRun a scan using a custom Semgrep rule supplied at call time.
get_abstract_syntax_treeReturn the AST for a snippet, useful when authoring custom rules.
semgrep_findingsFetch findings from the Semgrep AppSec Platform for a project or org.
supported_languagesList languages Semgrep can parse and scan today.
semgrep_rule_schemaReturn the JSON Schema for Semgrep rule files.
write_custom_semgrep_rulePrompt-style helper that guides the agent through writing a new rule.

Deploy the Semgrep MCP server in minutes

Connect your security agents to 50+ hosted MCP servers.

Self-host free