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.
Sandbase Harness
4.5/10Stdio MCP bridge for SandBase Harness agents, sessions, turns, artifacts, and cancellation.
MCP Dino
4.5/10MCP server with an interactive dinosaur dashboard (MCP Apps UI). No API keys required.
Grabhire Ai MCP
4.5/10GrabHire.AI MCP server. UK grab lorry + tipper hire. Tools: estimate load volume, get grab lorry...
Bridge MCP
4.5/10Bridge GS1 / EPCIS supply-chain identity + traceability to ONE OS — parse, map, govern (EU Digital
Bridge MCP
4.5/10Bridge ISO 8583 card-payment messages to ONE OS — parse, map, govern (PCI-DSS / scheme rules).
MCP Scorecard MCP
4.5/10Score any MCP server against a 100-point production-readiness rubric (static AST + PyPI +...
Meok Allmi Hiab MCP
4.5/10UK lorry-loader (hiab) compliance — ALLMI ACoP, BS 7121-4 lift planning, LOLER Thorough
Meok Imo Marpol Marine MCP
4.5/10IMO MARPOL + marine fuel + container ship compliance MCP. MARPOL Annex VI, EU ETS maritime, CII
Meok Rail Freight Uk MCP
4.5/10UK rail freight compliance — ORR licensing, ROGS safety certificate, Railway Interoperability
Obsify
4.5/10Local, privacy-preserving PII toolkit over MCP — shape to the model, substance stays local.
Fortunetellers Hand
4.5/10Solo journaling RPG — Claude runs The Fortuneteller's Hand, reading cards and casting Omens.
Timps
4.5/10Persistent memory with contradiction detection, burnout monitoring, and 69 intelligence tools.
Cork MCP
4.5/10Every Cork API operation, plus cross-client risk attribution and exploitability-first vuln triage.
Codasms MCP
4.5/10Receive one-time SMS/OTP verification codes via the CODASMS API: get a number, wait, release.
Demandscope
4.5/10Live demand signals for idea validation: npm/PyPI downloads, GitHub + HN attention trends.
Mandateguard
4.5/10Deterministic payment policy guardrail for AI agents - budgets, allowlists, signed mandates.
App Intel
4.5/10App Store & Google Play data: app details, IAP prices, reviews, top charts, estimates, rank history.
Mdcx
4.5/10Query a verified document collection: passages that answer a question, with their source.
Neurarch MCP
4.5/10Gives AI agents structural awareness of a neural network via a typed Neurarch model graph.
Boot Doctor MCP
4.5/10Deterministic PC no-boot/no-POST diagnostics: real beep-code tables, no LLM guessing.
Netdiag MCP
4.5/10MCP server wrapping dig, ping, mtr, whois and TLS/HTTP checks for on-demand network diagnostics
Uisight
4.5/10AI and human share live mobile+desktop browser sessions; measured UI findings your agent can act on
Grounded Support Agent
4.5/10Governed support MCP: answers only KB-grounded questions with citations, escalates the rest.
Itsoc MCP
4.5/10Read-only MCP server over a local log-analysis backend; a client that computes no verdicts.
Australian Law MCP
4.5/10Read Australian Commonwealth law as it stood on any date, and verify citations against the register
Is It Ai MCP
4.5/10MCP server that reads C2PA Content Credentials: what an image declares about its own origin
Actionforge
4.5/10MCP server for ActionForge: expose your account's tools to Claude and any MCP client.
Codecalc
4.5/10Code & logic calculator for AI agents: run 31 languages, symbolic math, SMT logic, complexity.
Samuraizer
4.5/10Local MCP server for meeting transcripts, summaries, action items & decisions — no cloud.
Claudeclear MCP
4.5/10Remove the Claude text watermark by rewriting text, and strip C2PA/EXIF metadata from images.
Archicad MCP
4.5/10Delivery-readiness QA and full official + Tapir API access for a running Archicad 29.
Gha Intel
4.5/10Workflow timing analysis, configuration audit and billing insight for GitHub Actions.
Qodercli MCP
4.5/10MCP server mode for Qoder CLI — delegate coding tasks to local Qoder agents from any MCP client.
Inferrail
4.5/10Read-only MCP tools over Inferrail's local receipt ledger: attributed spend and gateway health.
Katto MCP
4.5/10AI video clipping MCP: long videos and podcasts into scored, captioned 9:16 shorts.
Brain MCP
4.5/10Records your Claude Code, Codex and Pi history before deletion. Cited-or-abstain recall.
Redpill
4.5/10A transparent MCP server for agent reflection, conversation, and operator-enabled task decline.
MCP Paperless Ngx
4.5/10MCP server for Paperless-ngx 3.x — full REST API coverage, schema-aware, token-frugal.
MCP Server Uiautomation
4.5/10Windows UI Automation MCP server for desktop inspection and element lookup. Windows only.
Code Factory
4.5/10Local proof facts for AI coding clients: intent, tests, Graph Ops, and review evidence.
Ozon MCP Server
4.5/10Ozon Seller & Performance API: 151 tools — prices, promos, ads, orders, finance. Multi-shop.
Wb MCP Server
4.5/10Wildberries Seller API: 202 tools — products, prices, orders, ads, supplies, finance.
Refigure
4.5/10Convert DOCX/XLSX to Markdown — native chart-data extraction, optional VLM for figures
Lachesis
4.5/10Compiler-precise code property graph for C, Python, and TypeScript, navigable over MCP.
Mailsink
4.5/10Disposable inboxes for AI agents and CI: catch the verification email, read the OTP or link.
Chp MCP
4.5/10Spend approval gate for AI agents: budget caps, HITL thresholds, signed audit hash.
Governed MCP Gateway
4.5/10HTTP MCP gateway: principal on tools/call + SSE, allowlists, vault rotate, CHP gates.
MCP Google Analytics
4.5/10GA4 MCP that reads AND writes: reports, funnels, audits, and server-side events. 26 tools.
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.