The MCP Server Directory
Every Model Context Protocol server, scored on reliability, documentation, maintenance, and adoption. Independent, opinionated, refreshed daily from the official registry.
What this is
The MCP Server Directory is a live, independently maintained index of Model Context Protocol servers published to the official registry. Each server is scored 0–10 on four dimensions: reliability, documentation quality, maintenance velocity, and adoption. The directory is free, updated daily, and built by MegaOne AI.
Kernel MCP Server
4.7/10Access Kernel's cloud-based browsers and app actions via MCP (remote HTTP + OAuth).
Autobrowserapproval MCP
4.7/10A paid remote MCP for AI agent browser approval MCP, built to return verdicts, receipts, usage logs,
Chromedevtoolsmcp MCP
4.7/10A paid remote MCP for AI agent browser DevTools MCP, built to return verdicts, receipts, usage logs,
Playwritermcp MCP
4.7/10A paid remote MCP for AI agent browser MCP session, built to return verdicts, receipts, usage logs,
Developer Tools
4.7/1065+ free in-browser developer tools (JSON, Base64, JWT, hash, regex…) callable over MCP.
Notary Exam Prep
4.7/10Fetch real California Notary Public exam practice questions and grade answers in-chat.
Nostr Signer
4.7/10Approve Nostr signatures with your own browser signer without exposing a private key.
MCP Server
4.7/10macOS desktop control for Claude: click, type, screenshot, AX tree, browser control, agentic loops.
Uplink
4.7/10Automate a real, logged-in browser on your own device — no stored credentials, no bot detection.
Ghostlight
4.7/10Visible local browser automation in signed-in Chromium, with optional policy and audit.
MCP Browser Workflow
4.7/10MCP server for the @agentutility browser-workflow cluster — pay-per-call x402 tools, no API keys…
Browser Use
4.7/10Control a real Chrome browser to complete any task: fill forms, extract data, book flights.
Scrapeunblocker MCP
4.7/10Fetch any web page's HTML or AI-parsed JSON through the ScrapeUnblocker anti-bot API.
Crawlio Browser
4.7/10Bridge a live Chrome browser to your agent: 150 tools for capture, extraction, and observation.
MCP Server
4.7/10Fetch any public URL as a visitor in a chosen country, with a signed receipt of its origin.
Figma MCP
4.7/10Figma MCP: list frames in a file and fetch one frame's JSON and image safely. 2 tools.
Resolve
4.7/10Fetches receipts, genesis and accumulator snapshots for @forestrie/mcp-verify and labels provenance
Exnos
4.7/10Read-only live state of your Chrome tabs for AI agents: fields, console errors, network, storage.
MCP Server
4.7/10Isolated browsers with a persistent identity for AI agents, on your own Windows machine.
MCP Server
4.7/10Act for a person on websites: sandboxed browser, phone approvals, saved logins, scheduled plans.
Creator
4.5/10Build browser games on gamedev.pl from your coding agent.
Lookup
4.5/10Look up a FindMeTool page URL. Tool input stays in the browser.
MCP Server
4.5/10Publish, test and share browser games on PlayDrop from your AI agent.
Openbrowser Ai
4.5/10AI browser automation. Write async Python to navigate, click, type, and extract data.
Browserbase
4.5/10Create and control browser sessions for web automation, testing, and AI agent tasks
Fetchpet
4.5/10MCP server for Fetch Pet insurance claims management using Playwright automation.
Playwright Stealth
4.5/10Browser automation using Playwright with optional stealth mode to bypass anti-bot protection.
Pulse Fetch
4.5/10MCP server for fetching web resources with content extraction and anti-bot bypass.
Kogiqa MCP
4.5/10This web browser has been designed to help your agent debug and develop complex web applications.
Witnessd
4.5/10Neutral third-party witness: independently fetch, hash, timestamp, archive any URL or API response.
Smithery Ai Fetch
4.3/10A simple tool that performs a fetch request to a webpage.
Browserspendguard MCP
4.3/10Approval receipts for AI browser purchases.
Playwrightselectorguard MCP
4.3/10Playwright selector risk checks with healing suggestions and receipts.
Source Browser
4.3/10Generate, parse, and validate walkerOS data-elb HTML tagging attributes
Flow Orchestrator
4.3/10Compose BrandBrain asset flows, run mock/live generation, and fetch outputs
Dime Experiment Tools
4.1/10Free MCP server: Nostr profile fetcher + a tip-metadata tool. AI-earns-a-dime experiment.
Exec Brief
4.1/10Weekly 5-15 reports for executive teams: submit reports, fetch the Friday briefing.
Openhelm
4.1/10Autonomous cloud agent tasks: real browser + your tools, structured evidence-backed results.
Transcripts
4.1/10Fetch YouTube video transcripts individually or in bulk via get_transcript and get_bulk_transcripts.
Browser Ssh
4.1/10Scoped, audited SSH exec, sessions, and SFTP on your saved servers without exposing credentials
MCP Server
4.1/10A perpetual, crowd-written AI novel — fetch an assignment, write a chapter, submit it. CC0.
A11Y Check
4.1/10Real-browser WCAG audit that also finds keyboard-inoperable controls axe-core misses, with fixes.
Browser Citation Capture
4.1/10Cite or capture a web page; installs the capture extension in Firefox and Chrome.
MCP Server
4.1/10List WaterrAI scenarios, fetch AI-run meetings, and pull rubric-scored analyses.
Webrun
4.1/10Run multi-step tasks in a real Chrome browser: persistent environments, live view, human takeover.
Crx Permission Risk
4.1/10Score the privilege a Chrome MV3 extension takes from its manifest, and diff permission sets.
Reduck
4.1/10Automate any website: discover, run and create browser scripts that work behind logins.
Free · No spam
New servers, score changes, breakages
Every Monday: what shipped, what broke, what's worth trying. Five minutes. No filler.
Four dimensions, weighted
- Reliability (30%) — repository present, permissive license, not archived, official status.
- Documentation (20%) — description length, website presence, README quality.
- Maintenance (25%) — how recently the code was pushed; versioning discipline.
- Adoption (25%) — GitHub stars (log-scaled), remote availability, official endorsement.
What is MCP?
MCP stands for Model Context Protocol. It is an open standard introduced by Anthropic in late 2024 that lets AI assistants like Claude connect to external tools, data sources, and services through a common interface. An MCP server is a small program that exposes one capability (file access, a database, an API) to any MCP-compatible AI client.
Where does the data come from?
Every server in this directory is pulled from the official Model Context Protocol Registry at registry.modelcontextprotocol.io. We also enrich each entry with GitHub metadata (stars, last commit, license, primary language) where a repository is linked. The full re-scan runs daily.
How are servers scored?
Each server gets a 0–10 overall score, weighted from four sub-scores: reliability (30%), documentation (20%), maintenance (25%), and adoption (25%). The full methodology is visible on this page under "How scoring works".
Is this affiliated with Anthropic?
No. MegaOne AI is independent. Anthropic created the MCP standard and maintains the reference implementations, but this directory is built separately and rates all servers including Anthropic's own.
How often does the directory update?
The pipeline re-fetches the full registry and re-scores every active server once per day. Individual entries are refreshed whenever a new version is published to the official registry.
Is it free?
Yes. Browsing, filtering, and searching the directory is free. The weekly email briefing is free. There is no account required.