For security teams enforcing policy

Automatically secure the code your agents ship

Guardian runs your Semgrep policies the moment an agent writes a file, blocks what violates them, and returns the finding context in the session.

95% of Guardian scans complete in under 5 seconds across more than 3 million scans each week.
Claude Code · Guardian active

Claude Code › writes payments/api.py

+ query = f"SELECT * FROM users WHERE id = {user_id}"

Guardian hook › runs your Semgrep policy

acme-prod · SQL injection BLOCKED
User input reaches a database query without parameterization.

Claude Code › updates the query using the finding context

- f"… WHERE id = {user_id}"
+ cur.execute("… WHERE id = %s", (user_id,))

Guardian › policy check passed on the updated file

Policy at generation time

Fast and deterministic scans

Guardian combines deterministic Semgrep checks with the context of the active Claude Code session. Every engineer gets the same enforcement on every file.

95%of Guardian scans complete in under 5 seconds
3M+Guardian scans run across customers every week
Stays in your engineers' loop

One install, the same enforcement on every file

An MCP server and hooks ship together in one plugin, so policy runs where engineers already work.

MCP Server

The agent asks Semgrep and Semgrep answers. The MCP server exposes Semgrep scanning as tools the agent can call directly.

Learn more about the MCP →

Hooks

Hooks fire whenever Claude Code writes a file, ensuring a scan regardless of what the agent does or forgets.

Learn more about Hooks →
What it enforces

Four policy areas teams can bring into Claude Code

Supply Chain

Block what shouldn't install

  • Malicious and compromised packages from the Semgrep database
  • Typosquats and slopsquats in agent-suggested dependencies
  • Risky packages blocked before they install
Code security

OWASP guardrails at generation time

  • OWASP Top 10 guardrails on generated code
  • SQL injection, XSS, and IDOR blocked as they are written
  • AI-specific risks such as prompt injection and unsafe tool use
Secrets

Keep credentials out of code

  • Keys, tokens, and passwords caught before version control
  • Credentials required to come from a vault or environment variable
  • Cloud provider credentials caught before they leak
Custom rules

Bring your own code standards

  • The Semgrep rules your team already maintains
  • Custom rules for your frameworks and internal APIs
  • The same finding context your reviewers use
Custom rules

You decide where rules run

Run your own Semgrep rules at generation time, in CI, or both. Put fast, deterministic checks in the agent session and leave heavier analysis to the pipeline.

ruleset: acme-secure-defaults
at generation › internal-api-auth-required
in CI › cross-file taint rules
ruleset: acme-secrets
at generation › no-hardcoded-credentials
in CI › historical secret scanning
See it centrally

Every finding, every repo, in the Semgrep AppSec Platform

Guardian reports what it catches to the Semgrep AppSec Platform, so security teams see findings and activity across projects in one place.

  • What agents introduce, by repo and by policy
  • The same platform your team already uses to triage and track

Guardian activity

Developer adoption
Findings
Policy checks
Malicious dependencies blocked
Roll it out safely

Deploy Guardian across engineering, on your terms

Roll out through the agent console or your MDM in a few hours.

  • Read-only tokens scoped to scanning and reporting
  • The same policies across every Claude Code session in your organization
  • Plugin rollout through existing enterprise controls, with one-click CI/CD deploy and SSO
  • Zero-click sign-in for developers when you deploy through MDM
Pricing

Guardian plans for every way you build

Choose the plan that fits how you or your organization builds with AI.

Guardian
$10/month
per seat after a 30-day free trial

Guardian-only for individual developers and teams of any size.

  • Guardian runs in Claude Code
  • SAST, SCA, and Secrets checks
  • In-editor findings and guided remediation
Get started
Enterprise
Custom

For larger organizations planning a tailored rollout.

  • Guardian for larger organizations
  • Tailored rollout
  • Custom pricing through Semgrep Sales
Contact sales

Ship secure code today

Bring Guardian into Claude Code so malicious packages, hardcoded secrets, and vulnerable patterns are caught before they reach a pull request.