MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Free, open-source desktop QA browser for testing your own website forms by US location (state, city, ZIP), emulated device and browser. Windows, Linux, macOS.
Apache-2.0 ★ 1 -
Free, API-keyless MCP for resilient web search and safe, visible Chrome automation—with dynamic companion status, forms, uploads, and WebGL testing.
★ 2 -
MCP server for popups and opt-in forms: build, A/B test and read lead capture stats from Claude or any MCP client.
-
cdpilotno update data
cdpilot is a browser automation CLI and local MCP server that talks to Chrome, Chromium, Brave or Vivaldi directly over the Chrome DevTools Protocol, with no Puppeteer, Playwright or Selenium and no browser download. Its 45 MCP tools cover navigation, clicks and form filling (including inside cross-origin iframes), accessibility-tree snapshots, screenshots, test assertions, a page's own WebMCP tools, and Web Bot Auth request signing. `cdpilot connect` attaches to a browser you started yourself, so a person can clear a login or CAPTCHA and the agent continues; cdpilot never closes that browser. Every feature has a runnable example with its real output: https://github.com/mehmetnadir/cdpilot/tree/main/examples
smithery -
Digaso for Claude: conversational research agents (feedback, reviews, A/B, price, MaxDiff, user tests) for 12 sectors, with sample-sized findings.
MIT -
Autonomous QA scanner: point it at your running app and it walks the real user flows in a headless browser and reports what's actually broken: broken pages/links, console and network errors, empty/placeholder data, broken forms, state-loss, bad loading/er
npm Apache-2.0 -
MCP server that lets AI agents control a real web browser with 42 tools for navigation, clicking, typing, forms, and data extraction. It supports multi-agent sessions, human-like behavior, a built-in identity vault, and agent-to-agent messaging.
MIT -
jig-mcpgithub.com/lesnyak-cyber/qiksy-releasesupdated this year
MCP bridge to Jig — let the agent in your editor open the running page, sign in as a role, fill the form and read the console in the tester's own workbench.
npm SEE LICENSE IN README.md -
gos-claim-validator-mcpgithub.com/csoai-org/gos-claim-validator-mcpupdated this year
Validate NHS General Ophthalmic Services (GOS) claims pre-submission. Catches errors in GOS 1-6 forms before they hit eGOS. For UK opticians + care-home domiciliary providers.
pypi MIT License -
qiksy-mcpactive
Browser MCP server for the Chrome tab you already have open — your session, your logins. Gives Claude Code, Cursor, Codex and VS Code the live page: findings, forms, failed requests with server bodies.
npm SEE LICENSE IN README.md