Browse all Model Context Protocol servers with quality scores, stars, languages and maintenance activity.
Write-side MCP for Figma — complements Figma's official read-only MCP. 41 tools for building and editing Figma designs from Claude Code, Cursor, Cline: JSX-like tree creation, variables/tokens, components, cross-page navigation, and visual verification via screenshots. Install: `npx -y genable-mcp`.
MCP server for microservices.sh: inspect verified Cloudflare-native modules/templates, generate app plans/projects, run checks, and trigger confirmation-gated preview deploys. Install via `npx -y @microservices-sh/mcp`.
Agent-first synthetic test data MCP server. Estimate usage, detect schemas from SQL or JSON, create loginless Polar checkout, claim API keys, and generate JSON, CSV, or SQL data through a hosted Streamable HTTP endpoint.
Screen-reader navigation cost analyzer. Models real AT user effort with per-profile scoring, graph-based pathfinding, and step-by-step navigation traces.
Web design analysis MCP server with 26 tools for layout extraction, motion detection, quality scoring, and semantic search. Uses Playwright, pgvector HNSW, and Ollama Vision to turn web pages into searchable, structured design knowledge.
Behavioral verification intelligence for autonomous coding agents. Builds a behavioral graph of any TS/JS repo, clusters into 25 semantic workflows (Auth, Payments, Webhooks, Caching, Queue, etc.), detects drift, generates concrete adversarial probes (idempotency, retry storm, cache stampede, replay), emits per-workflow risk + confidence. 17 MCP tools. Local SQLite state. Zero cloud. MIT.
Build, sign, and publish iOS and Android apps through AI agents. Integrates Codemagic CI/CD, App Store Connect, and Google Play in one server.
Official MCP server for [Patchistry](https://patchistry.com), the first DTC fashion brand listed in the official MCP Registry. AI agent commerce tools for the velcro-patch hat system: `list_canvases`, `list_patches`, `recommend_build`, `get_shipping`, and `contact`. Helps ChatGPT, Claude, Cursor, and Perplexity recommend complete hat + patch builds when shoppers ask about custom hats, bachelorette
Hash-anchored file edits for MCP clients. Reads files with line anchors, validates anchors against current content, and rejects stale writes before changing files.
Convert, compress, merge, split, and OCR PDFs, plus convert between 100+ file formats (Word, Excel, PowerPoint, images, ebooks, video) from any AI agent. Backed by the GuruPDF API; free tier with daily credits, zero-config via `npx gurupdf-mcp`.
Create free, no-signup invoices from your AI assistant. Returns a deep link that opens [Blank Invoice Maker](https://blankinvoicemaker.com) pre-filled — review and download a watermark-free PDF. Invoice data stays in the browser. `npx blank-invoice-maker-mcp`
Business-day & public-holiday calculations for 200+ countries (add/count working days, next business day, country weekend rules).
Lightning-paid (L402) Bitcoin mempool intelligence + sovereign on-prem AI inference. 25 pay-per-call tools: live fees with trend, whale/mempool alerts, fee prediction, tx status & exact fee quotes, plus AI summarize/translate/grammar/code-review/code-gen/extract/classify/rewrite/explain/vision/OCR/embeddings and long-context docs — all on a self-hosted solar-powered GPU, no third-party APIs, pay 2
Agent payments ecosystem intelligence. Scans GitHub, Hacker News, and npm for activity across AP2, ACP, x402, MPP, and UCP protocols. Returns scored opportunities with recommended actions. Free protocol comparison + paid scan via x402 USDC.
Generate PDF, JSON & UBL invoices in 11 languages (Arabic RTL, Japanese, Hindi, Cyrillic) from AI agents. Free tier, no key needed for JSON totals.
Zcash shielded operations for AI agents. Chain queries, memo decoding, on-chain attestation, and proof verification.
Taiwan statutory payroll: labor & health insurance, labor pension, 2nd-gen NHI supplementary premium, income-tax withholding, and old-age benefits. Sourced from official gazettes, verified against official sample data.
Agent-ready financial intelligence for AI agents. Curated tools (`get_stock_snapshot`, `get_company_metrics`, `compare_companies`) that fan out to multiple financial data sources, derive human-readable signals (`UNDERVALUED`, `STRONG`, `ACCELERATING`), and pre-compute CAGRs, margin trends, and DCF upside. One call, one flat JSON response — no cross-endpoint stitching. Available on npm (`toolstem-m
England flood-risk by postcode from official Environment Agency open data (OGL) — long-term risk band, or an honest "not found" outside England.
Validates email addresses to reduce email bounces during marketing campaigns.
Backlink intelligence and competitor gap analysis on the public Common Crawl webgraph (4.4B edges, 120M domains) via [CrawlGraph](https://crawlgraph.com). 4 tools: backlink lookups, gap analysis, and a composite outreach-targets finder (domains linking to all your competitors but not you, de-noised and ranked by authority). Install: `npx -y crawlgraph-mcp`.
Local-first AI visibility, GEO/AEO, and llms.txt audit MCP server for Claude, Codex, Cursor, and other agents. Checks AI crawler access, robots, sitemap, canonical, metadata, noindex, and JSON-LD; returns local-only and technical foundation scores, top issues, and action plans. Install: `npx -y maxaeo-ai-visibility-mcp`.
TypeScript MCP server for the Langfuse Public API. 27 read tools covering traces, observations, sessions, scores, score-configs, prompts (with version/label), datasets, dataset items, dataset runs, metrics, models, projects, comments, media, and health. Distributed as `npx -y langfuse-mcp` with provenance-signed releases.
Verified ICD-10-CM medical code lookup, validation & reverse search — official descriptions, never guessed. [](https://glama.ai/mcp/servers/qinisolabs/icdwise)
Search a catalog of 2,000+ AI tools, compare them, find alternatives, and check whether a tool is still active, defunct, or acquired. Hosted remote MCP at `https://tooldirectory.ai/api/mcp` or `npx -y tooldirectory-mcp`.
56 deterministic fact-checkers in one server (IBAN, VAT, VIN, GTIN/barcodes, national & tax IDs, crypto addresses, phone, dates, holidays) — verify the structured facts an agent emits against checksums and curated data.
Trust intelligence for AI agents — identity stamps, reputation scoring (0-100), registry, forensic audit trails, and A2A passports via x402 micropayments.
Points an AI agent at a live URL and confirms publicly-served secret files by fetching the bytes — exposed `.git`, `.env`, JS source maps, backup/SQL dumps, directory listing, and dotfiles. Zero dependencies, read-only.
Pre-execution governance for AI agents. Intercepts and validates every agent tool call through an 8-stage pipeline before execution — risk classification, behavioral drift detection, hold queue for dangerous operations, and complete audit trail. 45 tools, 658 tests.
Pre-install trust layer for MCP servers, AI skills, and npm packages. Scores any repo or package across 15 signals (incl. OSV/KEV/EPSS vulnerability intelligence) with safety scanning for prompt injection, credential theft, and supply-chain risk; the `auto_gate` tool returns a go/no-go install decision. Listed in the official MCP Registry as `io.mcpskills/server`. npm: `@mcpskillsio/server`. https
Post for Me MCP server with 27 typed tools to publish, schedule, edit, delete and analyze social posts across 9 platforms (Instagram, Facebook, TikTok, YouTube, X, LinkedIn, Pinterest, Bluesky, Threads), plus a postforme_raw escape hatch and a readonly safety mode.
AI platform for short-form video creators (TikTok, Instagram Reels, YouTube Shorts, Facebook Reels). Three tools — viral TikTok trend search across 20+ countries, service info, and use-case scenarios for video analysis, competitor research, and content strategy. Install: `npx -y clipwise-mcp-server`. Free plan at tryclipwise.com.
86 running calculators, 29 marathon events, pace/time/distance calculations, race time predictions (Riegel formula), and heart rate training zones (Karvonen method) for AI agents. No API key required.
Live Japan seasonal travel — cherry blossom forecasts, autumn leaves, flower spots, fruit picking & festivals. 1,700+ GPS-tagged spots from Japan Meteorological Corporation. Updated daily.
Live aviation data for AI agents: decoded METAR weather by ICAO, airport & aircraft specs, an aviation glossary, and FAA-style practice questions. Hosted (Streamable HTTP + SSE), no signup.
Decision intelligence MCP server with signal aggregation, RICE scoring, and decision audit trails. Captures product feedback from Slack, Teams, Discord, and GitHub.
Claude Desktop job search assistant: searches LinkedIn plus 8 ATS boards (Greenhouse, Lever, Ashby, Workday, SmartRecruiters, Hacker News, RemoteOK, Remotive), scores each job 0-100 for fit (Claude judges directly, no LLM API key), and shows a ranked, triageable board inline in the chat.
Chinese metaphysics (bazi 八字, qimen 奇門, 5-element, daily 干支) as decision-support tools. Ask "when should I do X" and get specific time windows instead of vague advice. 5 tools: daily reading, compat, best-time-for-action, today's energy, name analysis. `npm install -g @asktian/mcp-server`
Query and summarize your chat messages with AI prompts.
An MCP Server Integration with Apple Shortcuts
Search Google and do deep web research on any topic
An MCP server for browser automation using Playwright
Model Context Protocol (MCP) Server for reading from Google Drive and editing Google Sheets.
The Scrapeless Model Context Protocol service acts as an MCP server connector to the Google SERP API, enabling web search within the MCP ecosystem without leaving it.
Atlassian Bitbucket Cloud integration. Enables AI systems to interact with repositories, pull requests, workspaces, and code in real time.
MCP server that lets LLMs know everything about your OpenAPI specifications to discover, explain and generate code/mock data
An MCP server to interface with the Google Tasks API
Intelligent agent memory with semantic recall, automatic consolidation, contradiction detection, and bi-temporal knowledge graph. 80% on LOCOMO benchmark using 96% fewer tokens than full-context approaches.