Skip to main content
mcpSource-backedReview first Safety Privacy

Snyk MCP Server for Claude

Official Snyk Studio MCP Server for connecting Claude Code, Codex CLI, Cursor, Gemini CLI, and other local MCP clients to Snyk Code, Open Source, IaC, container, SBOM, AI-BOM, package-health, authentication, and secure-at-inception workflows.

by Snyk·added 2026-06-04·
Claude CodeClaude Desktop
HarnessClaude CodeClaude Desktop
Review first review before installing

Open the source and read safety notes before installing.

Safety notes

  • Snyk documents this as a local MCP server that runs through the Snyk CLI so it can access local project files. Do not treat it like a hosted remote endpoint or expose it to untrusted clients.
  • The official examples use `snyk@latest`; this listing pins the currently observed npm package version for reproducibility. Re-check Snyk's docs and npm package metadata before updating the pinned runner.
  • Authenticate with the least-privilege Snyk account that can inspect the target project. Do not commit Snyk tokens, generated MCP configs, CLI auth state, Claude configs, Codex configs, or copied scan output that contains sensitive findings.
  • Snyk requires trusting the current project directory before scanning. Treat that trust step as a real access decision, especially for monorepos, regulated codebases, customer projects, and worktrees containing secrets.
  • The `snyk_sca_scan` tool can execute third-party ecosystem tools such as Gradle or Maven to build dependency trees. Run scans only in projects where dependency resolution commands are acceptable.
  • Container, IaC, SBOM, AI-BOM, and package-health tools may require extra local files, network access, preview feature access, or container image references. Review each tool call before letting the assistant expand the scan surface.
  • Treat generated remediation guidance as advisory. A human should review code changes, dependency upgrades, IaC edits, Dockerfile changes, and suppressions before they are committed or deployed.

Privacy notes

  • Snyk MCP can read local source code, dependency manifests, package lock files, IaC definitions, Dockerfiles, container image references, SBOM files, AI project metadata, and scanner results from the connected project.
  • Scans can send project metadata, dependency information, vulnerability context, code-analysis data, organization identifiers, authentication state, and package-health requests to Snyk services according to the configured product and account.
  • Claude, Codex, IDE logs, MCP client transcripts, screenshots, shell history, and tickets can retain Snyk findings outside Snyk's normal access controls and retention settings.
  • Security findings may reveal vulnerable dependencies, vulnerable code paths, internal package names, container base images, cloud resources, application structure, and remediation priorities. Avoid pasting raw findings into public issues or unaudited chat systems.
  • The `snyk_send_feedback` tool can send issue-fix feedback to Snyk. Use it only when that feedback path is approved for the project and organization.

Prerequisites

  • Snyk account and approval to connect the local project to Snyk security scanning.
  • Node.js and `npx`, or a locally installed Snyk CLI executable available to the MCP client.
  • MCP-capable client such as Claude Code, Codex CLI, Cursor, Gemini CLI, or another local stdio-compatible client.
  • Browser-based Snyk authentication, or an approved token-based authentication flow for the target organization.
  • Project directory trust decision before scans run against local source, dependency manifests, IaC files, container inputs, SBOMs, or AI-related project metadata.
  • Profile choice: `lite` for the smallest useful toolset, `full` for the default stable toolset, or `experimental` for preview tools.

Schema details

Install type
cli
Troubleshooting
No
Source repository stats
Scope
Source repo
Collection metadata
Estimated setup
15 minutes
Difficulty
intermediate
Tool listing metadata
Full copyable content
{
  "mcpServers": {
    "Snyk": {
      "command": "npx",
      "args": ["-y", "snyk@1.1305.1", "mcp", "-t", "stdio", "--profile=lite"],
      "env": {}
    }
  }
}

About this resource

Content

Snyk MCP Server is the official local MCP bridge for Snyk Studio. It lets AI development environments call Snyk security tools while working inside a local project, so Claude Code, Codex CLI, Cursor, Gemini CLI, and other MCP-capable clients can scan generated code, dependencies, IaC, containers, SBOM files, and package choices from the assistant workflow.

The strongest fit is secure-at-inception review: ask the assistant to run Snyk scans before declaring generated code complete, use Snyk context to draft fixes, rescan after changes, and keep a human in the loop before committing remediation. Start with the lite profile when you only need source-code and dependency checks, then move to full or experimental only after reviewing the additional tool surface.

Features

  • Official Snyk Studio MCP Server documented by Snyk.
  • Local stdio MCP server run by the Snyk CLI.
  • Claude Code quickstart with installer, npx, direct MCP config, and SSE options.
  • Codex CLI quickstart through .codex/config.toml.
  • General MCP configuration for clients that do not support the default hooks-based Snyk Studio setup.
  • Snyk Studio installer path for Claude Code, Cursor, Codex CLI, and Gemini CLI hooks-based workflows.
  • Tool profiles: lite, full, and experimental.
  • Stable tools for authentication, logout, version checks, project trust, source-code scanning, open-source dependency scanning, and feedback.
  • Full-profile tools for container scanning, IaC scanning, SBOM scanning, AI-BOM creation, and package-health checks.
  • Secure-at-inception directives for scanning newly generated first-party code and rescanning after fixes.

Use Cases

  • Ask Claude to scan generated source code before marking a task complete.
  • Run Snyk Open Source scans against dependency manifests while reviewing a package upgrade or newly added library.
  • Review Terraform, Kubernetes, CloudFormation, ARM, or Serverless Framework files with Snyk IaC checks before opening an infrastructure PR.
  • Scan a container image or Dockerfile-related dependency surface before release review.
  • Analyze an SBOM for known vulnerabilities when validating a supply-chain artifact.
  • Ask for package-health context before selecting a new dependency.
  • Generate an AI-BOM for a supported Python project when AI model, dataset, and tool inventory is needed.

Installation

Claude Code

Snyk documents an installer-style command for Claude Code:

npx -y snyk@latest mcp configure --tool=claude-cli

For reproducible project configuration, pin the Snyk package version after checking the current Snyk docs and package metadata:

{
  "mcpServers": {
    "Snyk": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "snyk@1.1305.1", "mcp", "-t", "stdio", "--profile=lite"],
      "env": {}
    }
  }
}

Run /mcp in Claude Code to confirm the server and tools are visible, then authenticate the Snyk account and trust the current project directory when prompted.

Codex CLI

Add Snyk to .codex/config.toml:

[mcp_servers.snyk-security]
command = "npx"
args = ["-y", "snyk@1.1305.1", "mcp", "-t", "stdio", "--profile=lite"]

Restart Codex and ask the agent to authenticate the Snyk account or scan the current directory. Snyk notes that the workflow may open a browser confirmation dialog during setup.

Generic MCP config

Snyk's general MCP setup uses npx and stdio:

{
  "mcpServers": {
    "Snyk": {
      "command": "npx",
      "args": ["-y", "snyk@1.1305.1", "mcp", "-t", "stdio"],
      "env": {
        "SNYK_MCP_PROFILE": "lite"
      }
    }
  }
}

If the Snyk CLI is already installed locally, configure the MCP client to run that executable with:

snyk mcp -t stdio

Use the official docs for the exact client-specific config location and keep real authentication material out of committed files.

Tool Profiles

Use profiles to keep the tool surface aligned with the task:

  • lite: essential authentication, trust, code scan, dependency scan, version, logout, and feedback tools.
  • full: the default stable toolset, adding container, IaC, SBOM, AI-BOM, and package-health tools.
  • experimental: full profile plus tools still under evaluation.

Example:

npx -y snyk@1.1305.1 mcp -t stdio --profile=lite

Examples

Secure generated code

Use Snyk MCP to scan the first-party code changed in this task before you mark it complete. Show findings and proposed fixes before editing.

Dependency review

Run a Snyk Open Source scan for this package manifest and summarize dependency vulnerabilities, license issues, and the safest upgrade path.

IaC review

Use Snyk MCP to scan the Terraform and Kubernetes files changed in this branch. Keep the result read-only and list each finding with file context.

Package selection

Before adding this dependency, use Snyk package health checks and explain the security and maintenance tradeoffs.

Source Notes

  • Snyk's Agentic security with Snyk Studio overview describes Snyk Studio as a connection between the Snyk platform, development environment, AI tools, directives, and a local Snyk MCP Server.
  • Snyk's getting-started guide states that the Snyk MCP Server is designed as a local server that runs through the Snyk CLI, and that Snyk does not offer a hosted remote MCP server.
  • Snyk's Codex CLI guide documents .codex/config.toml setup using npx -y snyk@latest mcp -t stdio.
  • Snyk's Claude Code guide documents npx -y snyk@latest mcp configure --tool=claude-cli, alternate MCP configuration, authentication, project trust, and secure-at-inception directives.
  • Snyk's docs list MCP tools including snyk_sca_scan, snyk_code_scan, snyk_iac_scan, snyk_container_scan, snyk_sbom_scan, snyk_aibom, snyk_trust, snyk_auth, snyk_logout, snyk_version, snyk_send_feedback, and snyk_package_health_check.
  • The npm package metadata checked at submission time showed snyk@1.1305.1 with MCP package name io.snyk/mcp and repository redirect target https://github.com/snyk/cli.

Duplicate Check

Checked current upstream/main, open PR titles, open PR changed files, source URLs, and content files for Snyk MCP, Snyk Studio, snyk-mcp-server, snyk@latest mcp, snyk_code_scan, snyk_sca_scan, docs.snyk.io/evo-by-snyk/agentic-security-with-snyk-studio, and related title variants. Existing security hooks, rules, and scanner entries mention Snyk only as a possible security tool or dependency scanner. No dedicated Snyk MCP Server entry, Snyk Studio source URL duplicate, or open content PR for this server was found.

Editorial Disclosure

Snyk is a commercial security platform, but this listing is not sponsored, paid, affiliate-backed, or submitted by Snyk. Use Snyk's current docs, package metadata, account permissions, privacy terms, and organization policies as the source of truth before connecting a local codebase to any AI client.

#snyk#security#mcp#sast#sca

Source citations

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.