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.
Anki MCP Server
8.1/10A Model Context Protocol (MCP) server that enables AI assistants to interact with Anki, the spaced repetition flashcard application.
Adeu
8.0/10docx ↔ LLM translator. Projects .docx office files to Markdown for editing. Projects edits back to OOXML as tracked changes (redlines). Python and Node.js implementations.
Spotdb
7.4/10Give your agents a secure, containerized SQL sandbox with MCP or API access enabled with DuckDB. No infra required, quick spin-up cycle. Push any CSV — query, analyze,…
Docs MCP
7.4/10Tandem is the authority layer between AI agents and company tools: runtime policy for tools, memory, approvals, and audit trails.
Embedded Docs
7.3/10The open-source MCP server behind ByteAsk Embedded Docs: a source-grounded, page-cited evidence-retrieval server for coding agents (Claude Code, Codex, Cursor) that write firmware / driver / protocol code…
Anki MCP Server Addon
7.2/10An Anki addon that implements an MCP server, enabling AI assistants to interact with Anki, the spaced repetition flashcard application.
Affiliate Networks MCP
7.2/10Affiliate network reporting in your AI client. Bring your own keys. Most adapters experimental.
Buywhere MCP
7.2/10BuyWhere MCP server — search and compare products from Singapore, SEA, and US markets via Model Context Protocol. Cross-border e-commerce product catalog for AI agents. Free API key:…
Biel Ai
7.1/10Query your product docs from AI tools. Source-cited answers from your indexed documentation.
Directory
6.9/10Agent commerce directory for Lightning, BOLT12, L402, and USDT merchants. Merchants self-register and land self-attested; an Observer Protocol attestation tier records what has been checked on each.
Bowmark
6.9/10The Bowmark skill — the web as callable functions. The agent reads a typed function library, writes a short script, and Bowmark runs it on the live sites.…
Goji
6.9/10Documentation for GOJI's hosted MCP server. Answers questions about AEO, SEO, web development and branding from GOJI's published material, with a goji.agency URL to cite on every result.…
Bareun
6.6/10Korean NLP & spell/grammar checking MCP server (Bareun) — remote streamable-HTTP at api.bareun.ai/mcp
Server
6.6/10Write timely, well-sourced content with the agents you already use — BetterPost skill + MCP for Claude, Codex, Cursor, Gemini, and more.
Sap Analytics
6.6/10Read-only MCP server for the SAP analytics services market — firms, contract radar, day rates, concepts, studies. Hosted, no install.
Buywhere MCP
6.5/10Agent-native product catalog for AI shopping agents. 296M+ products, 28 countries.
Biddeed MCP
6.5/10Fork of HKUDS/CLI-Anything adapted for BidDeed.AI foreclosure auction and zoning intelligence stack. Agent-native CLI interfaces for ZoneWise Scraper and Auction Analyzer.
Authoryze
6.5/10Give your AI agent a spending limit. Authoryze is a remote MCP server that issues single-use virtual cards with per-merchant and per-amount controls you approve before the agent…
Bitroad
6.4/10Marketplace for AI agents: buy goods and services under spending caps, with returns and disputes.
Market Data
6.4/10US stock market data for AI agents — 23 years of intraday metrics + daily OHLCV with VWAP, SEC fundamentals, filings, insiders. pip install cabrini
Armor MCP
6.2/10Data observability tools for engineering teams: alerts, freshness, schema drift, lineage, quality.
Certscore Light
6.2/10No-account public website privacy risk scans with 20 new scans/day and free recent-result reuse.
Telegram
6.2/10Telegram channels you administer: analytics, content plans, scheduled publishing. No userbot
Calaf
6.2/10Connect your Calaf recruiting book: validate and import seeds; people arrive staged for your review.
Seeds
6.2/10Author and validate Calaf workspace seeds against the app's real importer. No account needed.
Bloopo
6.1/10Turn one sentence into finished ads: video ads, UGC, product photos, voiceover, brand kits, A/B.
MCP Server
6.1/10The bolthub API marketplace, L402 gateways, and your other MCP servers, on one Lightning budget.
Computeback
6.1/10MCP server for Computeback — the Agent Rewards Marketplace + CB Hire B2B labor (paid in $NOMD on Base L2). Public source mirror of the npm package @autonomad1/computeback-mcp.
Directory
6.0/10Indexed ecommerce site directory — vendor lookups, brands by city/market/founder. 10 tools.
Grep
6.0/10Parallel regex across all Boolsai scans — discover new vendor patterns, niche signals. 4 tools.
Scan
6.0/10Live tech-stack scan of any public site — vendors, account IDs, scripts, JSON-LD. 2 tools.
Signals
6.0/10Quant-research MCP — tradeable signals from public-company website stack changes. 7 tools.
MCP Server
6.0/10Search AutoRFP.ai projects, requirements, content library, and tags for Q&A and analytics.
Bittlebits
6.0/10BittleBits MCP plugin. Connect Claude, Cursor, and any MCP client to BittleBits GEO scores and rewrite suggestions."
Auralogs
6.0/10Auralogs MCP server: read-only MCP access to production logs and AI analyses for Claude, Cursor, Codex, Cline, and any Streamable HTTP client
MCP Server
6.0/10MCP server for AgentTrust — A2A communication, agent identity, HITL escalation, and prompt injection detection
Backengine MCP
5.9/10Remote MCP server for BackEngine — query customer & prospect context (Slack, email, call transcripts, support tickets) from MCP client.
MCP Server
5.9/10Agent-native web hosting — deploy sites, manage DNS, register domains, scale infrastructure
Arpi MCP
5.9/10AI-powered ECG analysis: submit ECG images and receive diagnosis reports from ARPI's ECG AI.
Basethread
5.9/10One shared context your team's AI tools read & write over MCP. No re-explaining. Free.
MCP Server
5.9/10Atlaso's hosted MCP server — one shared, persistent memory across every AI tool you connect. Endpoint: https://mcp.atlaso.ai/mcp
Agent Trust Receipt
5.8/10Read-only Remote MCP for externally grounded AI agent trust receipts.
Auxen
5.6/10Provision private AI model endpoints on dedicated GPUs (Llama, Qwen, Mistral). Pay per minute.
Trading
4.9/10AI-powered trading strategy development: backtesting, market data, and portfolio analysis
Agentdm
4.9/10Agent communication platform for agent to agent messaging via MCP. Messages, channels, skills.
MCP Server
4.9/10AI-powered news intelligence — 21 tools for personalized monitoring, briefings, and semantic search
Compliance
4.9/10Check bank marketing for FDIC, NCUA, TILA, Reg DD, Reg Z, UDAAP, and Equal Housing compliance.
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.