Lazaretto · MCP server scans

MCP server security scans

An MCP server runs with your agent's access to files, credentials, and tools, so a malicious one is a direct path to your data. Here are automated scan results for widely-used MCP servers. Each page shows the verdict and the signal categories; the full evidence is in the report from the API. Results are automated signals, not a warranty.

• Filesystem Local file read and write access for an agent.
• GitHub GitHub repository, issue, and pull-request access.
• GitLab GitLab project and repository access.
• Slack Slack workspace messaging access.
• Postgres Read-only PostgreSQL database access.
• Puppeteer Headless-browser automation.
• Brave Search Web search via the Brave Search API.
• Google Maps Places, directions, and geocoding.
• Memory A knowledge-graph memory store.
• Sequential Thinking A step-by-step reasoning scratchpad.
• Everything The reference server exercising every MCP feature.
• Playwright Browser automation via Playwright.
• Firecrawl Web scraping and crawling for agents.
• Context7 Up-to-date library documentation for coding agents.
• Tavily Web search and content extraction for agents.
• Exa Neural web search.
• Notion Notion workspace access.
• Kubernetes Kubernetes cluster operations.
• Browserbase Cloud browser automation.
• Cloudflare Cloudflare account and Workers access.

Scan any server or package: try it · use Lazaretto as an MCP server · API