Snyk MCP Server
Snyk ships a first-party MCP server as part of Snyk Studio, its agentic-development security layer. It is deliberately LOCAL ONLY: the server runs on the developer's own machine through the Snyk CLI so that it can read local files to scan them. Snyk's own documentation states plainly, "The Snyk MCP Server is designed as a local MCP server, running on your system using the Snyk CLI to ensure local file access. Snyk does not offer a hosted remote MCP server." There is therefore no URL an agent can POST to; a human installs and runs it first. Tools are grouped into three profiles - lite, full (default), and experimental - selectable with --profile or SNYK_MCP_PROFILE.
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Documentation
Documentation link · transport stdio
Tools
snyk_auth— Authenticate the Snyk CLI session used by the MCP server.snyk_code_scan— Snyk Code (SAST) scan of first-party source code.snyk_sca_scan— Snyk Open Source (SCA) scan of dependencies. May execute third-party ecosystem tools (Gradle, Maven) locally to resolve the dependency tree.snyk_version— Report Snyk CLI version information.snyk_logout— Clear the local Snyk authentication session.snyk_trust— Trust a given folder before running a scan.snyk_send_feedback— Summarize issues fixed and send feedback to Snyk.snyk_container_scan— Snyk Container scan of container images.snyk_iac_scan— Snyk Infrastructure as Code scan of Terraform, Kubernetes and CloudFormation files.snyk_sbom_scan— Test an SBOM file for known vulnerabilities.snyk_aibom— Generate an AI-BOM for a local software project.snyk_package_health_check— Evaluate open-source package health (vulnerability counts by severity, maintenance, community, popularity) before an agent selects a dependency. Supported for npm, pypi, nuget, maven and golang only.
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.
Work with this as data
Every MCP server here is available over the APIs.io API and to AI agents over MCP.