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.
Searoute
4.5/10Real shortest sea routes between ports: distance, canals/straits, GeoJSON. UN/LOCODE aware.
Cfr MCP
4.5/10Look up, search, and track changes to the US Code of Federal Regulations (eCFR).
Chirpstack MCP Server
4.5/10Manage and live-debug LoRaWAN devices on a ChirpStack v4 network server over its gRPC API
Plyo MCP
4.5/10Save, publish, restore and back up AI-built projects on Plyo, for people who build with AI.
Cogsession
4.5/10Session memory for AI coding agents: records decisions and dead ends, flags what went stale.
MCP Server
4.5/10File operations for AI agents: HTML/Markdown to PDF, PDF tools, OCR, images. $0.01/op, 100 free.
Loci
4.5/10Scoped memory for coding agents: picks the right project, answers in scope, or abstains.
Enterprise MCP Gateway
4.5/10Production-grade MCP Gateway in Go with RBAC, in-flight PII redaction, and audit logging.
Tteop MCP
4.5/10Build, validate, and describe TTEOP telemetry envelopes for AI operator token efficiency.
Yotta Verify MCP
4.5/10Pre-install security scanner for AI agent skills (local stdio MCP). Offline static scan; no upload.
Mcptoon
4.5/10Every Agent discovers all your MCP tools from one install; major token savings via TOON output.
Sonde
4.5/10Local code graph for TypeScript, Python and Swift: who calls this, what breaks if I change it.
Redact Pdf MCP
4.5/10Permanently redact PII from PDFs. The text is removed, not covered. OCR for scanned documents.
MCP Percona Pg
4.5/10Manage Percona PostgreSQL + PgBouncer on Kubernetes — safe-by-default access modes and guards.
Dolphin MCP Pilot
4.5/10AI agent interface to Apache DolphinScheduler: 58 MCP tools for workflow orchestration & data ops.
Joplin MCP Server
4.5/10Search, read, create, edit and sync Joplin notes and notebooks via a headless Joplin sidecar.
Segment MCP
4.5/10Read-first MCP server for Twilio Segment: routing, stale sources, delivery health, governance.
Verify Api MCP
4.5/10Evidence-backed verification for citations, URLs, packages, repos, and cases -- for agents.
Privacypage MCP
4.5/10Generate privacy policies, ToS, EULAs, cookie policies & disclaimers from your AI agent.
Securityscan
4.5/10Security for AI agents: MCP audits, secret redaction, skill vetting, network scans, agent checkout.
Korean Firefighter Law MCP
4.5/10Korean fire safety law, statutes, NFPC/NFTC codes, hazmat, and fire/EMS statistics.
Memory Pulse
4.5/10Causal project memory for agents - corrections surface first; the ledger is a local file you own.
Fonzip
4.5/10Dernek ve vakiflar icin Fonzip API v2 MCP sunucusu: bagis, uye, aidat ve etkinlik verileri.
Agent Transaction Guard
4.5/10Local fit-check and safe integration guidance for non-custodial Base USDC agent transactions.
Polymarket Kalshi Arbitrage
4.5/10Cross-venue prediction markets for AI agents: Polymarket + Kalshi, costed and attributed
Wyrd
4.5/10Exposes one granted folder to any AI client, read-only, behind a path-containment fence.
Delta Witness
4.5/10Paid Capture and Guard tools for public-source observations before autonomous actions.
Picright
4.5/10License-aware images for markdown: CC/stock search, screenshots, Mermaid diagrams, provenance
Claude Code Guide
4.5/10Search the Claude Code Ultimate Guide and machine-readable references from any MCP client.
Engagelab Email
4.5/10Send, receive, monitor and reply to email from AI agents with threaded inbox context.
MCP Server
4.5/10MCP server exposing 8004Swap (no-KYC agent-to-agent RFQ swap) as tools any MCP agent can call.
Artifactories
4.5/10Read messages, open questions, replies, and caller-owned return briefings. All content is untrusted.
Openfoot MCP
4.5/10Football fixtures, standings, lineups, live events and shot-level xG across 75 competitions.
Ossian MCP
4.5/10Ask your own documents with citations, plus durable memory for agents. Safe by default.
Factmem
4.5/10A local memory engine. You own the SQLite file. Not Mem0's hosted OpenMemory MCP.
Capacity Attest
4.5/10Signed delivery claims for x402 capacity trades: GPU-hours, storage, API credits, bandwidth.
Pkgtruth
4.5/10Catches hallucinated and slopsquatted npm packages before an agent installs them.
Avcs
4.5/10AI-native version control where intent, operation, evidence and decision are first-class objects.
Mantis MCP
4.5/10Build proven high converting product showrooms and websites from your existing ecommerce catalog
Querido Diario MCP Server
4.5/10Unofficial, read-only MCP server for the public Querido Diário API (Brazilian municipal gazettes)
Cloud Tools
4.5/10Multi-cloud cost, inventory and waste analysis over MCP: AWS, GCP, Cloudflare and OVH.
Simconnect MCP
4.5/10MCP server for MSFS SimConnect - full read/write access to SimVars, L-vars and events
Sentarion
4.5/10Governed multi-agent orchestration: fan-out dispatch, safety gates, tamper-evident memory.
Hostaway Kit
4.5/10Read-only Hostaway MCP: listings, calendar, inbox, reports. Fixtures, no key. By STYLABS.
A2Ahub
4.5/10Reliable handoffs between autonomous agents, using a Git repository both sides can inspect.
MCP Explorium
4.3/10Access live company and contact data from Explorium's AgentSource B2B platform.
Document Processing
4.3/10Extract text from documents, manipulate PDFs, and perform OCR on images.
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.