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.
N3Mc Workingmemory
4.5/10Ephemeral 7-day hybrid vector+BM25 working memory, multilingual, backed by Redis Stack.
India MCP Railways
4.5/10MCP server for Indian Railways: search trains, stations, schedules and live status.
India MCP Rto
4.5/10MCP server for Indian vehicle RTO: decode number plates, calculate road tax, check RTO offices.
World Model MCP
4.5/10Temporal knowledge graph for codebases with constraint enforcement at the edit boundary.
MCP Einvoicing De
4.5/10German e-invoicing MCP server: ZUGFeRD 2.x, XRechnung 3.x, EN 16931, KoSIT validation, Peppol.
Gsep MCP
4.5/10AI agent security via MCP: C3 firewall, C4 immune system, C5 action guard, self-evolving prompts.
Author MCP Server
4.5/10Recall, check, search, timeline, and graph tools for fiction writers via Seizn Memory v3.
Filevine MCP
4.5/10Open-source MCP server connecting Claude to Filevine practice management. Built by Oktopeak.
Mneme Ai
4.5/10Memory layer for AI coding assistants. Indexes git history + code, exposes via MCP.
MCP Server
4.5/10AI-driven 3D CAD via build123d: execute, render, measure, and export geometry interactively.
Bash Vet MCP
4.5/10Vet LLM-emitted shell commands BEFORE execution. 26 destructive-pattern rules / 8 families.
Recall
4.5/10Persistent memory for Claude Code. Search, recall, and re-inject context from any session.
Bitbooth Fetch
4.5/10Pay-per-fetch via x402. Agent pays 0.005 USDC, gets clean markdown for any URL. No API keys.
Evermint MCP
4.5/10Mint tamper-evident receipts for AI agent actions. The notary layer for agent-to-agent transactions.
Proofflow
4.5/10Audit infrastructure for AI coding agents with evidence-backed review and policy gates.
Credence
4.5/10Epistemic guard for AI coding: tracks uncertain values and blocks writes until verified.
Formacv
4.5/10FormaCV MCP server for AI-powered CV formatting, anonymization, tailoring, and ATS push-back.
India MCP Banking
4.5/10MCP server for Indian banking: IFSC lookup, UPI VPA validation, bank UPI status.
Evolutiondb Memory
4.5/10Persistent long-term memory for Claude Desktop / Claude Code, backed by EvolutionDB.
Bawbel MCP
4.5/10Scan MCP servers and skill files for AVE vulnerabilities. Conformance scoring and threat intel.
Bawbel Scanner
4.5/10Security scanner for MCP servers and skill files. Detects AVE vulnerabilities before production.
Pruna
4.5/10Ultra-fast image generation, editing, upscaling, and video generation via Pruna AI.
Coinopai MCP
4.5/10Kronos crypto signals + trade decisions + 819 automation prompts. x402 micropayments, USDC/Base.
MCP Clipboard
4.5/10Read and write the system clipboard — tables, text, code, JSON, URLs, images, and more.
MCP Ksef Pl
4.5/10Polish e-invoicing MCP: KSeF API v2, FA(3)/FA(2) XML, Peppol BIS 3.0, NIP/REGON validation.
Clipboard History MCP
4.5/10Your clipboard, but Claude can read it. Type-classified, secret-encrypted. macOS + Linux.
Cowork Qa
4.5/10Goal-driven Playwright browser sessions for LLMs, with full action traces and aria-snapshots.
Idf MCP
4.5/10Turn an IDF domain into an MCP server with invariants and role scopes in every tool description.
Arcwall Security
4.5/10Security scanning for AI coding tools. Detects secrets, threat models, and runs pre-commit checks.
Pixelvault
4.5/10AI-native marketplace for pre-cleared licensed media assets — search, license, and stream rights.
Oceanbus MCP Server
4.5/10Register, discover, message, and transact with other AI agents on the OceanBus network.
Kuriflow MCP
4.5/10Make AI tasks repeatable. Run with new data automatically — zero AI tokens per run.
Airflow
4.5/10Airflow MCP — list DAGs/runs/task instances, tail logs, trigger and clear (write-gated)
Android
4.5/10Android MCP — ADB-based device, apps, UI, logcat, emulator, files, system, debug
Datadog
4.5/10Datadog MCP — 165 tools for metrics, monitors, logs, APM, RUM, incidents, CI/CD, fleet
Dbt
4.5/10dbt MCP — manifest/run_results/sources/catalog parsing + DQ result tables (BigQuery/Postgres)
Google Drive
4.5/10Google Drive + Workspace MCP — Docs, Sheets, Slides, Shared Drives, Labels, Approvals, DWD
Mlflow
4.5/10MLflow MCP — experiments, runs, registered models, versions, traces, assessments (MLflow 3)
Openmetadata
4.5/10OpenMetadata MCP — metadata, lineage, search, data quality, OM 1.12+ Data Contracts
Unifi
4.5/10UniFi semantic-analysis MCP — fleet health, anomaly detection, cross-site analytics
3Dstreet
4.5/10Drive an open 3DStreet scene tab from Claude Desktop or Claude Code via MCP tool calls.
Agentradar
4.5/10Trust scoring, scam detection, and EAS attestations for ERC-8004 + x402 agents on Base.
Dp Engineering Assistant
4.5/10Helps plan and reuse CE-RISE Digital Passport components, models, and deployment assets.
Ai Bom MCP
4.5/10AI Bill of Materials (AI-BOM) generator + auditor MCP — CycloneDX ML-BOM, SPDX 3.0 AI profile, E...
Bias Detection MCP
4.5/10AI bias detection and fairness assessment for AI agents. Instant bias risk scan, demographic ana...
Carbon Footprint MCP
4.5/10An MCP server for calculating carbon footprints from bank statements using EPA GHG emission factors.
Prompt Time
4.5/10Claude Desktop reminders for Windows. Survives MSIX boundary; persists across restarts. Zero deps.
Ryvo Protocol
4.5/10MCP server for Ryvo Protocol state reads and prepare-only payment-channel actions.
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.