Snyk MCP Server

Snyk security scanning and vulnerability detection MCP server

Tools

Last Updated

Apr 13, 2026

What is the Snyk MCP Server?

The Snyk MCP server gives AI agents structured, permission-aware access to Snyk through the Model Context Protocol. With 12 pre-built actions, agents can read, create, and update Snyk data on behalf of authorized users.

Willow ships the Snyk MCP server as part of an enterprise control plane. Every call runs behind SSO (Okta, Azure AD), enforces RBAC and least-privilege at runtime, writes to a full audit trail, and integrates with Splunk and Loki for SIEM visibility. Connect from Claude Desktop, Claude Code, Cursor, ChatGPT, VS Code, n8n, or any custom agent. Install once, distribute org-wide, and see exactly how Snyk is being used by every AI agent in your stack.

Tools

snyk_aibom

Generates an AI Bill of Materials (AIBOM) for Python software projects in CycloneDX v1.6 JSON format. This feature analyzes local Python projects to identify AI models, datasets, tools, and other AI-related components. Requires an active internet connection and access to the experimental feature (available to customers on request). The command must be run from within a Python project directory and requires the CLI from the preview release channel. When to use: When you need to create an inventory of AI components in a Python project for compliance, security analysis, or documentation purposes.

snyk_auth

Authenticate the user with Snyk. When to use When a snyk tool reports that the user is not authenticated or when authentication is required.

snyk_code_scan

Performs Static Application Security Testing (SAST) directly from the Snyk MCP. It analyzes an application's source code with a SAST scan to identify security vulnerabilities and weaknesses without executing the code. When to use: During local development, developers can run it on their feature branches for immediate feedback, or after you generate new code files. How to use: Test directory: run snyk_code_scan with parameter <path>, add parameters as needed. Languages that Snyk supports: Apex, C/C++, Dart and Flutter, Elixir, Go, Groovy, Java and Kotlin, Javascript, .NET, PHP, Python, Ruby, Rust, Scala, Swift and Objective-C, Typescript, VB.NET

snyk_container_scan

Scans container images for known vulnerabilities in OS packages and application dependencies. How to use: Test image: <snyk_container_scan> `IMAGE`=`my-image:v1`. Test with Dockerfile for context: <snyk_container_scan> `IMAGE`=`my-image:v1` `file`=`absolute/path/to/Dockerfile`. Test and exclude base image vulns: <snyk_container_scan> `IMAGE`=`my-image:v1` `exclude_base_image_vulns`. Test OCI archive: <snyk_container_scan> `IMAGE`=`oci-archive:image.tar` `platform`=`linux/arm64`.

snyk_iac_scan

Analyzes Infrastructure as Code (IaC) files for security misconfigurations. Supports Terraform (.tf, .tf.json, plan files), Kubernetes (YAML, JSON), AWS CloudFormation (YAML, JSON), Azure Resource Manager (ARM JSON), and Serverless Framework. When to use: Locally by developers while writing IaC. In CI/CD pipelines to scan IaC changes before applying to cloud environments, preventing insecure deployments. The `report` option sends results to Snyk UI for ongoing visibility. How to use: Test directory: <snyk_iac_scan> `path`=`absolute/path/to/dir`. Test specific TF file: <snyk_iac_scan> `path`=`absolute/path/to/file.tf`. Test dir, report to UI: <snyk_iac_scan> `path`=`absolute/path/to/dir` `report` `org`=`my-org`. Test K8s configs, report to UI, high severity: <snyk_iac_scan> `path`=`./k8s/` `report` `target_name`=`prod-k8s` `severity_threshold`=`high`. Test with custom rules: `<snyk_iac_scan> `path`=`/absolute/path/to/infra/` `rules`=`rules.tar.gz`.

snyk_logout

Logs the Snyk MCP out of the current Snyk account by clearing the locally stored authentication token. When to use: When needing to switch Snyk accounts, or to ensure a clean state by removing existing authentication from the local machine.

snyk_package_health_check

Retrieves package information and health metrics from Snyk's package intelligence API. Returns details about a package including security vulnerabilities, maintenance status, popularity metrics, and community health indicators. When to use: When evaluating a package before adding it as a dependency, when changing a package version, or when assessing the health and security of existing dependencies.

snyk_sbom_scan

Analyzes an existing SBOM file for known vulnerabilities in its open-source components. Requires components in SBOM to be identified using PackageURLs (purls). When to use: After SBOM generation (by Snyk or other tools) to assess components. In CI/CD to test generated/received SBOMs. For vulnerability scanning of third-party software when only an SBOM is available. How to use: <snyk_sbom_scan> `file`=`/absolute/path/to/my_app.cdx.json`. Input Requirements: SBOMs in CycloneDX (JSON 1.4-1.6) or SPDX (JSON 2.3). Packages must have purls (types: apk, cargo, cocoapods, composer, deb, gem, generic, golang, hex, maven, npm, nuget, pub, pypi, rpm, swift). Secure SDLC Integration: Testing/Validation Phase: Scans inventoried components post-SBOM generation. Third-Party Risk Management: Assesses vulnerabilities from SBOMs of external software.

snyk_sca_scan

WE NEED TO USE THE ABSOLUTE PATH IN THE PATH ARGUMENT. Analyzes projects for open-source vulnerabilities and license compliance issues by inspecting manifest files (e.g., package.json, pom.xml, requirements.txt) to understand dependencies and then queries the Snyk vulnerability database. When to use: During local development by developers on their workstations before committing changes for immediate feedback. How to use: Test locally: run tool with at least the path parameter. Prerequisites: Project's package manager (e.g., Gradle, Maven, npm) must be installed for accurate dependency resolution.

snyk_send_feedback

Report ONLY the delta (this run only) of Snyk issues. Use preventedIssuesCount if the model prevented introducing a vulnerability in new code. Use fixedExistingIssuesCount if the model repaired an issue in existing code. Counts must NEVER be cumulative. Always send an absolute path.

1 2

1–10 of 12 tools

Customize Tools

Edit descriptions, modify arguments, select tools, or add new ones

Set Up Your Snyk MCP Server in Minutes

Add the following configuration to your MCP client. Authentication is handled via OAuth. Compatible with Claude Desktop, Claude Code, Cursor, ChatGPT, VS Code, n8n, and any MCP-compatible agent.

Claude Desktop

claude_desktop_config.json

{
  "mcpServers": {
    "willow-snyk": {
      "type": "http",
      "url": "https://<org>.mcp-s.com/mcp/mcp/snyk"
    }
  }
}

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "willow-snyk": {
      "type": "http",
      "url": "https://<org>.mcp-s.com/mcp/mcp/snyk"
    }
  }
}

Claude Code

CLI

claude mcp add willow-snyk --transport http https://<org>.mcp-s.com/mcp/mcp/snyk

n8n

HTTP Request Node

{
  "url": "https://<org>.mcp-s.com/mcp/mcp/snyk",
  "method": "POST"
}

Or click "Install with Willow" above to set up automatically with SSO and RBAC preconfigured.

Enterprise Governance for Snyk

Willow adds the layer Snyk and every other SaaS doesn't ship out of the box: every call runs behind SSO (Okta, Azure AD), enforces RBAC and least-privilege at runtime, writes to full audit logs, and detects shadow AI usage across your stack. One MCP gateway. Any agent. Every tool.

Snyk MCP Server FAQ

What is the Snyk MCP server?

The Snyk MCP server is a Model Context Protocol implementation that lets AI agents like Claude, Cursor, and ChatGPT read and write Snyk data through a standardized interface. Willow hosts and governs this server so enterprises can roll it out without a security review backlog.

How is Willow's Snyk MCP server different from the official one?

The official Snyk MCP server is scoped to a single user's account and does not include enterprise governance. Willow's version adds SSO, RBAC, audit logging, shadow AI detection, and centralized control over which actions agents can take across the entire org.

Which AI clients work with the Snyk MCP server?

Claude Desktop, Claude Code, Cursor, ChatGPT, VS Code with MCP support, n8n, and any custom agent built with OpenAI Agents SDK, LangChain, Vercel AI SDK, or Anthropic SDK.

Is the Snyk MCP server secure? How does Willow handle authentication?

Every call runs behind your existing SSO (Okta, Azure AD). Per-user OAuth scopes the agent to exactly what that user can do in Snyk, nothing more. No credentials reach the LLM. Every action writes to an audit trail.

Can I limit which Snyk actions agents can take?

Yes. Willow lets you scope agents to specific actions, specific projects, or specific environments. Toggle actions on or off in the dashboard, or enforce policy via infrastructure-as-code through GitHub.

How do I detect shadow Snyk MCP servers in my org?

Willow's browser extension and discovery service surface unmanaged MCP servers, skills, and AI agents across the org. If a developer installed an unapproved Snyk MCP locally, you'll see it.

What does the Snyk MCP server cost?

Pricing depends on org size and deployment model (SaaS, dedicated cloud, self-host). See withwillow.ai/pricing or contact sales for a quote.

How do I install the Snyk MCP server with Willow?

Install via the Willow Connect Panel in one click, or paste the JSON snippet above into your Claude Desktop, Cursor, or Claude Code config. SSO and RBAC inherit from your existing Willow setup.