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.
Crawlwise MCP
3.9/10Per-URL tech-stack, feed and sitemap change events for AI agents, delivered as signed webhooks.
Product Discovery
3.9/10Search and compare EWIGSC wigs, toppers, and extensions; find first-party care guidance.
Reconstitution Calculator
3.9/10Lab math: reconstitution, unit conversion, C1V1, molarity, percent w/v, serial dilution.
Backtest Auditor
3.9/10Automated red-team checks for trading backtests: lookahead lint, Deflated Sharpe, costs. Local.
Lakewave MCP
3.9/10Verified B2B contacts at named accounts, email verdicts, contract signals and drafted campaigns.
Adn Node
3.9/10AgentPeer ADN node: publish, filter and forward signed posts for their human owners.
Ntfyx
3.9/10Public Topics, rich messages, usage and verified phone replies. Pair only for protected messages.
MCP Server
3.9/10Re-Agents.ai tools for AI agents: website audits and your approved company knowledge.
Datarunner
3.9/10Query, monitor and schedule SQL across your databases: schemas, read-only SQL, alerts, hosts.
Memtrove
3.9/10Let Claude search and read the files and bookmarks on your Mac by name, content or meaning.
Papertype MCP
3.9/10Render Markdown, HTML or invoice/certificate/report templates to PDF files via the PaperType API.
Maiday
3.9/10Distress signal for AI agents: report where you get stuck on websites and fetch site-owner hints.
Krmaazha Binance MCP
3.9/10Security-first Binance MCP. 26 tools, human-confirmed spot trades, offline quant research.
Verify
3.9/10Check Proof of Process chains: record, file match, timestamps, registry. Never one verdict.
MCP Server
3.9/10Free WCAG accessibility checks for any page, including localhost, with fix guidance for each issue.
MCP Server
3.9/10Read, write, search, lock and audit files in LucidLink filespaces, plus workspace admin tools.
Easytdd
3.9/10Generate C# builders, FluentMocks, tests and test cases from your .NET solution.
Daknode
3.9/10Email and calendar API tools for agents: inboxes, conversations, availability and reliable booking.
Preclone
3.9/10Check what a repo would run on your machine (open, agent start, install) before you clone it.
Verdict MCP
3.9/10Ask if an action is safe before your agent runs it: injection, shell, MCP installs. Free samples.
Murmur
3.9/10An AI agent offloads heavy compute to your own Macs and Windows PCs, with a deadline verdict.
Kimiko
3.9/10Kimiko, the private AI notepad: local MCP for your meetings, notes and tasks. Off by default.
Flieber
3.9/10Your Flieber account in your AI assistant: sales, forecast, inventory, replenishment and more.
MCP Protocol Era Negotiation Conformance
3.9/10Per-era MCP negotiation verdicts: signed documents, drift alerts, client pre-flight.
Wagate
3.9/10Read WhatsApp chats and groups, and send messages when allowed, through the WaGate API.
Jitters
3.9/10How wrecked is your monkey? Jitters' mood from the hours of your own git commits this week.
MCP Server
3.9/10Links your AI assistant app to the Paramability tab open in Chrome. Runs on your computer only.
App
3.9/10Local tools: PDF, Office, e-Factura, OCR, images, video, speech, translation and nutrition.
Calculators
3.9/10Exact calculators (loans, dates, units, LLM tokens, API cost, VRAM) + prefilled nanocalcs.com links
Tool Result Context Binding Verdict
3.9/10Pre-consumption verdict for cached/replayed tool results: BOUND, STALE, CONTEXT-MISMATCHED, UNBOUND.
MCP Server
3.9/10Ask your AI about your site's traffic, channels, revenue, goals and funnels (XPmetric analytics).
3Dapi
3.9/103D print on demand through the 3DAPI API: quotes, orders, products, stock, wallet and webhooks.
Agent Tools
3.9/10Load, read, edit, and recalculate .xlsx workbooks headlessly — no Excel required.
Gateway
3.9/10Governed access to private code for coding agents: policy, redaction, audit chain, provenance.
MCP Server
3.9/10App Store and Google Play screenshots, ASO text and feature graphics from your AI agent
Loverflaw
3.9/10Court other AI agents on Loverflaw: thirty-word messages, gates, seven-day clocks.
MCP Server
3.9/10XRechnung und ZUGFeRD lokal erstellen, lesen und prüfen. Fehlercodes wie BR-DE-15 erklärt.
Agent Ready
3.9/10Can an AI agent actually buy from your store? Score it, see the evidence, fix the gaps.
Apply
3.9/10The auto-apply tool that shows its work — policy-scoped autonomy, review-first, receipts for
Attest
3.9/10signed performance attestations for agents, issued only against settled, receipt-backed work
Bidmatrix
3.9/10Drop in a solicitation, get back the compliance matrix — Section L/M extraction, requirements
Blackbox
3.9/10The record that survives the agent: append-only, recorder-signed, and graded by proof — never by
Book
3.9/10Market data + venue access layer — not an exchange: one book, one fee truth, one ledger of record.
Charter
3.9/10Your broker watches its own account. Charter watches your rules — across all of your accounts.
Cluster
3.9/10Signed images, governed runtimes — the gate runs first: no verified signature and provenance, no
Codex
3.9/10Banking regulation as data: a citation-exact library, a deadline engine, sanctions screening, and
Colophon
3.9/10Catalog of record for books: signed titles, rights, prices & royalties, checked everywhere they
Compass
3.9/10The Thumbtack adapter: one approved Task Brief becomes a native Thumbtack request, and a hire runs
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.