MCP Server List
Every MCP server in the official registry that has something to show: 57 973 in total, of which 33 095 answered our last handshake and 6 905 are listed as active but do not respond. Sorted by uptime, real installs and the number of tools each one exposes — not by date added.
New to this? What an MCP server is, and what all 57 973 of them expose — written from our own handshakes, not from the specification.
33 095 answering 19 119 with real installs 457 527 tools indexed
Figma to pixel-perfect code: deterministic HTML/React, then a render + pixel-diff verify loop.
Pay-per-use AI tools monetized via x402 USDC micropayments on Base, Solana, and Arc.
Convert any public URL to clean, readable Markdown for AI agents. Strips ads, navigation, and boi...
AI agents see and drive the Android Emulator: screenshots, UI in dp, tap, dark mode, RTL, logcat.
Lets one coding agent talk to another: Claude Code, Codex or Grok
Safety-first Git MCP server: rich read tools plus human-approved FluxGit operation proposals.
Turn an agent's findings into a clean web page: tables, charts, diagrams, one shareable link.
MCP server for web search and page extraction across the free tiers of several providers
U.S. grid mix, retail electricity prices and Henry Hub gas prices (EIA), paid per call via x402.
AI agent access to Linux servers without SSH: scoped tools, per-call isolation, root only if granted
A project's long-term memory as plain Markdown files, with an append-only, tamper-evident log.
Exact, durable handoffs between AI coding agents: one turn in the right session, never twice.
Item-by-item inventory that reorders itself: per-SKU forecasts, purchase orders and ETAs.
Your WHOOP recovery, sleep, strain and workouts in Claude, ChatGPT or other MCP apps. Self-hosted.
MCP client for commerce/data skills; requires a configured GuardMarket backend.
Shared ledger for groups that share money: balances, expenses, transfers, budgets and reports.
Economic evidence for AI agents. Paid x402 reports in Base USDC; no credit score.
Self-hosted architecture model that agents read layer by layer, search, build and correct.
Live X/Twitter data: profiles, tweets, search, followers, lists and trends. 29 read-only tools.
Discover and scaffold new apps by reusing code from your GitHub repositories.
Make videos with Rubiic: start one from a brief, render it to MP4, export GIFs, stills and captions.
Find halal restaurants and mosques worldwide, with verified halal status and prayer times.
Verifiable entropy, provably-fair games, and receipt verification for AI agents (FairSeal API).
Arithmetic consistency checks for supplied financial statement data.
Packet ordering simulation and inter-arrival jitter telemetry.
Energy and transcript heuristics for voice turn endpoint detection.
Memory for agents and people: exact recall from a plain-text index, by your own keys.
Unreal Engine MCP server: C++ PDB symbols, Blueprint and .uasset analysis, build-error fixes
Risk limits and an audit log for AI agents trading Hyperliquid, enforced outside the model.
Create, edit, validate, render, and export D2 diagrams with confined workspace access.
A local map of your codebase over time: symbols, callers, subgraphs and structural change.
The x402 agent market on Base: sellers, prices, on-chain payments, operators, buyers. Dated.
Model Context Protocol server for Forgejo, Codeberg and Gitea, in Rust
Token-efficient code reading for coding agents: symbol-aware, budgeted, diff-aware reads.
Plan and run paced startup, SaaS and AI directory launches from your agent, in your own Chrome.
Signed messages between AI agents. Dangerous actions wait for a human-signed approval.
Brazilian business data for AI agents. Public company dossiers by CNPJ.
GitLab over MCP from your own account: issues, merge requests, reviews, the repository and CI.
Gmail over MCP from your own account: search, read threads and messages, labels and drafts.
A second opinion from an unrelated AI model before you commit to a decision.
Instant, resettable Windows, Ubuntu and Arch Linux ARM desktop VMs for AI agents on Apple Silicon.
Set monthly budget categories, log spending, get over/under-budget reports. All data is local.
Loan and mortgage math: monthly payment, amortization schedule, payoff comparison.
Gross-to-net payroll estimates for hourly staff with common withholding assumptions.
Plan a workday into pomodoros, log focus sessions, get daily stats. All data is local.
Parse raw receipt lines into itemized totals with tax. All data is local.
Read your Stripe billing data from AI chat: balances, invoices, subscriptions. Read-only.
US federal income tax estimates: brackets, marginal rate, effective rate. Planning values.
Read and draft email you forward to a private alias. Agents cannot send or delete mail.
Create, organize, and publish marketing work with Goosy's tenant-scoped tools.
MCP server built into Rillsoft Project 10 for multi-project resource planning (local, Windows)
Search source-linked Dallas-Fort Worth local-government records for AI agents.
Topics, semantic search, tasks, projects, areas and documents in TY Agent Drive.
Build, edit and publish websites on PageHub: pages, blocks, themes, collections, domains.
Create, edit, read and review web presentations: slides, linked buttons, pictures, runnable code.
Scans Agent2Agent (A2A) protocol code for webhook SSRF, missing auth, and credential exposure
Finds transitive excessive agency across LangGraph/CrewAI/AutoGen orchestration graphs
Scans code for insecure LLM/AI integration: exposed keys, unsafe output, prompt injection
KVKK/GDPR/CCPA compliance checks for codebases
KVKK/GDPR-compliant LLM-to-database gateway: PII masking, RBAC, rate limiting, audit log
CVE scanning for npm/pip/cargo dependencies via OSV
DNS record enumeration, misconfiguration and dangling-subdomain detection
Active jailbreak/extraction/obfuscation red-teaming for live LLM endpoints
Scans Cursor/Claude/Windsurf/VS Code MCP configs for unpinned versions, secrets, typosquats
Scans MCP server tool definitions for excessive agency, injection sinks, hardcoded secrets
Scans agent code for untrusted input poisoning persistent cross-session memory
Scans ML model files (PyTorch, safetensors, Keras, ONNX) for supply-chain risks
Scans MCP server auth code for OAuth 2.1 anti-patterns: token passthrough, missing audience
Scans RAG content/scraped pages for indirect prompt injection
Catches leaked credentials and PII in outbound LLM prompts
Baselines an MCP server's tools and detects tool-definition changes after approval
Scans files for leaked secrets and API keys
MCP gateway: many servers, one policy, lethal-trifecta blocking, PII masking, audit log
Bundle of secret-scanner, dependency-auditor, ssl-inspector, and dns-intelligence
Checks declared npm/PyPI dependencies against real registries to catch slopsquatting
TLS certificate/cipher/protocol inspection
Scans MCP tool definitions for hidden instructions and confused-deputy sinks
Scans LLM/agent code for Unbounded Consumption / denial-of-wallet risks (OWASP LLM Top 10 2026 #6)
Probes vector-database endpoints for unauthenticated exposure of embeddings/RAG data
Triggers GuardBee scans, queries findings, AI-assisted remediation guidance
Connect MCP clients to local Codex Bridge agents, projects, approvals and workspace tools.
Provenance tree for coding agents: where you are, why, and what was already decided
AI governance MCP: A3 scorecard, ISO 42001 evidence templates, compliance checklist, gov_scan.
Local-first governed MCP memory backend for coding agents.
MCP server for Dubber: call recordings, compliance, groups/accounts/users, and Dub.Point.
See which AI agent and MCP server talks to what on Windows, with a rule-based security verdict
Resultados oficiais parciais das eleições brasileiras 2026 (TSE) por UF, cargo e município.
Search, read and query large folders of Markdown notes (200,000+). Optional, reversible edits.
Grade an AI agent's transcripts on 18 reliability tests. Thin evidence is NOT TESTED, not guessed.
Buy at cash-only or unsupported shops with BTC via a proxy shopper and 2-of-3 escrow, or earn as one
Web search, crawling and ranking evaluation on your own YaCy peer: no API key, no central service.
Run a Prusa 3D printer: status, camera, files, printing, G-code, over PrusaLink or Prusa Connect.
SAP SuccessFactors OData and Compound Employee queries with PII tokenization for AI agents.
Local RAG MCP server for your own .md knowledge base: BM25 + local Ollama, offline, zero egress.
Read-only MCP server for global medical-device regulation (NMPA/FDA/MDR/PMDA), 27 hubs, 4 tools.
Read-only local MCP index of medical-device standards (ISO/GB/YY/ASTM/IEC) with official links.
Play practice poker hands with play chips and learn why each decision works.
Ask your customer portal and CRM anything, in plain English
Read your Pyunto Time Management schedule and log time from an AI assistant. E2EE project planning.
Evaluate an MCP server with passmcp and verify its attestations, from inside the agent. Read-only.