Every MCP server in the official registry that has something to show: 33 956 in total, of which 17 659 answered our last handshake and 3 674 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 33 956 of them expose — written from our own handshakes, not from the specification.
17 659 answering 11 784 with real installs 261 041 tools indexed
Tells an AI agent when another is already doing its work. Board, typed mail, directory claims.
Wisp Panel MCP server for secure game server management through the Wisp Client API.
Reads your own Garmin mirror: readiness, training load, muscle freshness, and read-only SQL.
A typed, policy-controlled OS capability layer for AI agents.
Talos Linux cluster operations as one thin MCP tool over the official machine API.
Persistent code memory for AI agents: notes pinned to files and symbols that survive refactors.
Give an AI agent a real .NET debugger: breakpoints, stepping, locals, expression evaluation.
Local memory for coding agents. A rule with a runnable proof can refuse a wrong command.
Auditable MCP server for PubMed, Europe PMC, ClinicalTrials.gov, and bioRxiv/medRxiv queries
GMCA Certainty Matrix Validate: 11 vragen om een project te screenen vóór investering.
Read-only MCP servers for Russian marketplaces: prices, stock, ratings, reviews, seller identity
Stateful backend for AI agents: memory, watch, render, execute, and shared boards with digests.
Self-hosted file host: upload a file, get a public URL an agent can paste into a pull request.
Read-only MCP server for self-hosted Atlassian Bamboo CI/CD
Drive an Android emulator or device over adb: screenshot, inspect UI, tap, type, build and test.
Drive one tmux server: sessions, windows, panes, and the output they produce.
Role-aware Agent memory with cross-session recall, durable writes, and multi-Agent project scope.
The API-change deploy gate for AI coding agents. Read-only breaking-change detection.
AI colleagues that keep your standards, your project and their reasoning between sessions
World Cup 2026 match, team, player and market context from Machina Sports, the sports AI platform.
Gate/Prove: deny unattended destructive agent tools. Instant Audit $499 on a2zsoc.com.
Local-first document accessibility remediation using the canonical AlloFlow app pipeline.
Code intelligence for repository graphs, change impact, test selection, and engineering memory.
Every Auvik endpoint as a command, plus the cross-client answers the Auvik UI and API cannot give
Publish and manage WordPress pages, posts, media
Solana Jupiter quotes and package preflight for AI agents. Free sample. Paid x402 on Solana USDC.
Voice interface for Claude Code: talk to your agent and it talks back while it works.
Multitenant Streamable HTTP bridge over Nutanix's official v4 API MCP server (Prism Central).
AI visibility & recommendation monitoring for ChatGPT, Claude, Gemini & Perplexity.
Billing, subscriptions and quoting for B2B SaaS
Create, list, and complete todo items through MCP.
Samsara fleet management — vehicles, routes, drivers, HOS compliance. Unofficial, bring your token.
Sanctions, PEP, watchlist, recall, business, and contract screening. Free tier, no auth required.
Read, search, and send personal WhatsApp messages from any MCP client, behind a send-confirm gate.
Redacts PII from your business tools before the AI sees them — with a provable audit log.
Get transcripts from YouTube, TikTok, X, Instagram and more - even when captions are off.
Curated operational knowledge for AI agents. 2 tools. Paid.
Web toolkit for AI agents: read any URL as Markdown, screenshot, extract data, or crawl a site.
MCP server with an interactive dinosaur dashboard (MCP Apps UI). No API keys required.
MCP server for the MST Chain ecosystem providing search and retrieval tools for documentation.
MCP server for Mailprotector — customers, domains, users, quarantine, allow/block rules for MSPs.
Agentic AI for business intelligence: discover, verify and enrich company and contact data.
Ground your AI in verified Korean venue data: search & book across Seoul, Gyeonggi, Busan, Jeju.
Synthetic-only transaction screening with evidence and ES256-signed decision receipts.
Quote and book airport transfers on a RideDesk operator's live desk. Agents never set prices.
Query your data warehouses, run workflows, and render maps from your CARTO workspace.
Read your SenPrints sales, orders, customers, campaigns and payouts, and publish blog posts.
Drive KittyClaw, a self-hosted agent-fleet kanban, from any MCP client (embedded /mcp endpoint).
Solo journaling RPG — Claude runs The Fortuneteller's Hand, reading cards and casting Omens.
Every Cork API operation, plus cross-client risk attribution and exploitability-first vuln triage.
Create an access review checklist
Build a grouped account report
Set account merge guidance
Merge an account revision
Compose an account grouping recipe
Prepare an agreement obligation schedule
Select a reviewer group
Register an artifact delivery route
Plan the delivery route for an artifact
Set the intended audience for a briefing
Normalize a calendar handoff
Forecast a scenario amount
Map candidate skills to an interview plan
Record a capacity-window entry
Compose audience-ready briefing sections
Select a contact for a client brief
Set handling guidance for a content item
Prepare a content review plan
Create a coordination calendar entry
Prepare a customer record field
Set timezone guidance for project deadlines
Set acknowledgement guidance for a delivery
Compose a delivery signature section
Create a delivery acknowledgement
Set delivery recovery guidance
Determine a signature requirement
Build a delivery ledger entry
Register a deployment region
Build a dispatch manifest
Set document release selection guidance
Select a document release
Select an event callback address
Set the style guidance for an executive report
Sequence stops for a field route
Send a finance-review message
Record a fulfillment reservation
Register a handoff recovery policy
Assign an incident owner
Build an interview agenda
Record an inventory planning quantity
Build an invoice reconciliation summary
Set invoice rounding guidance
Calculate an invoice summary
Register a queued processing profile
Update a section and backlink index
Segment a knowledge note for indexing
Plan a knowledge-base placement path
Plan a translation setting
Plan a lot allocation
Calculate a metric trend summary