---
title: "MCP server security scans. Lazaretto"
description: "Automated Lazaretto scan results for popular Model Context Protocol (MCP) servers: known-bad matching plus deterministic behavioral signals."
url: "https://lazaretto.dev/mcp-servers"
---

[Home](https://lazaretto.dev/) / [reports](https://lazaretto.dev/packages) / MCP servers

# MCP server security scans

An MCP server runs with your agent's access to files, credentials and tools. A bad one can reach your data. Here are scan results for widely used MCP servers. Each page shows the verdict and the kinds of signal we found. The full evidence is in the API report. These are automated signals, and they carry no warranty.

**Checking a remote server?** Paste its URL into the [free MCP server check](https://lazaretto.dev/check/mcp) and see if its tool text is poisoned. No account.

- [Filesystem](https://lazaretto.dev/mcp-server/filesystem) Lets an agent read and write local files.
- [GitHub](https://lazaretto.dev/mcp-server/github) GitHub repository, issue, and pull-request access.
- [GitLab](https://lazaretto.dev/mcp-server/gitlab) GitLab project and repository access.
- [Slack](https://lazaretto.dev/mcp-server/slack) Slack workspace messaging access.
- [Postgres](https://lazaretto.dev/mcp-server/postgres) Read-only PostgreSQL database access.
- [Puppeteer](https://lazaretto.dev/mcp-server/puppeteer) Headless-browser automation.
- [Brave Search](https://lazaretto.dev/mcp-server/brave-search) Web search via the Brave Search API.
- [Google Maps](https://lazaretto.dev/mcp-server/google-maps) Places, directions, and geocoding.
- [Memory](https://lazaretto.dev/mcp-server/memory) A knowledge-graph memory store.
- [Sequential Thinking](https://lazaretto.dev/mcp-server/sequential-thinking) A step-by-step reasoning scratchpad.
- [Everything](https://lazaretto.dev/mcp-server/everything) A test server that uses each MCP feature.
- [Playwright](https://lazaretto.dev/mcp-server/playwright) Browser automation via Playwright.
- [Firecrawl](https://lazaretto.dev/mcp-server/firecrawl) Web scraping and crawling for agents.
- [Context7](https://lazaretto.dev/mcp-server/context7) Up-to-date library documentation for coding agents.
- [Tavily](https://lazaretto.dev/mcp-server/tavily) Web search and page text for agents.
- [Exa](https://lazaretto.dev/mcp-server/exa) Neural web search.
- [Notion](https://lazaretto.dev/mcp-server/notion) Notion workspace access.
- [Kubernetes](https://lazaretto.dev/mcp-server/kubernetes) Kubernetes cluster operations.
- [Browserbase](https://lazaretto.dev/mcp-server/browserbase) Cloud browser automation.
- [Cloudflare](https://lazaretto.dev/mcp-server/cloudflare) Cloudflare account and Workers access.

Scan any server or package: [try it](https://lazaretto.dev/#try) · [use Lazaretto as an MCP server](https://lazaretto.dev/docs/api#mcp) · [API](https://lazaretto.dev/openapi.json)

---

Machine-readable index: https://lazaretto.dev/llms.txt. OpenAPI: https://lazaretto.dev/openapi.json. MCP endpoint: https://lazaretto.dev/mcp. Any page on this site is available as markdown by adding .md to its path.