Every MCP server in the official registry that has something to show: 57 554 in total, of which 32 723 answered our last handshake and 6 829 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 57 554 of them expose — written from our own handshakes, not from the specification.
32 723 answering 19 139 with real installs 453 425 tools indexed
Make, approve, schedule and measure your Product's TikTok, Instagram and YouTube Posts.
Short-form video intelligence: your TikTok, Reels and Shorts data, reports, Studio, live editor.
Ranked lenders and investors for real asset deals, with appetite level reasoning.
Read-only financial evidence: disclosure cutoffs, operating changes and cash calculations.
Make images and video with 30+ AI models from your assistant, on your own credits and library.
Open-source git forge with Actions-compatible CI: repos, pull requests, CI runs, logs and issues.
Assess a business or product idea: market, customer needs, innovation options, and product features.
Your local Zenitsu tasks and notes for AI apps. Needs the Zenitsu app (Linux).
Your YOD birth chart and today's transits to it, plus saving notes to your YOD journal.
Manage Static Forms (staticforms.dev) form endpoints, form rules and submissions over OAuth.
Offline file tools and opt-in direct sharing, camera and voice sessions by Abox Technologies.
S.C.A.L.A. AI OS and Score: company data, CRM and SARA tools for AI agents via MCP.
Your AI works in Adobe After Effects and proves what it did: change reports, pixel proofs, QC.
Deterministic MCP tools for tattoo briefs, small-size legibility checks, and line-art prompts.
Self-hosted inbox for questions your AI agents couldn't answer. Report knowledge gaps over MCP.
Passive AppSec scanners as eight parameterless MCP tools; the audited repository is data.
Search 20k+ live, probed x402 pay-per-call endpoints and route to the best-scored one.
Create tutorial videos by chatting with AI.
Check how long ago a package version was published before an agent adds it, in 20 ecosystems.
MCP server for App Store Connect: releases, TestFlight, reviews, reports. Read-only by default.
MCP server for App Store Connect: releases, TestFlight, reviews, reports. Read-only by default.
Local-first shared memory for AI coding agents: one searchable store, served over MCP. MIT.
List bands and read, post, and comment on BAND posts through the BAND Open API.
Contract-first MCP server for RabbitMQ: one typed tool per message contract, safe error recovery.
Self-hosted agent memory: redaction before write, append-only audit, local embeddings.
Self-hosted Docker sandboxes for agents: create one, deploy a compose stack, read its files and URLs
Gmail for Google Antigravity via the official API; sends only after the user's yes.
Local security scanner for AI agents: SAST, SCA, secrets, IaC; verifies exploit and fix.
Project board for teams and coding agents: Kanban, sprints, 46 tools, OAuth 2.1 or API tokens.
Free read-only feed of curated MSC, NK cell, extracellular vesicle and senescence research.
Analyze C# complexity, inspect member evidence, and compare deterministic snapshots.
Byte-patch CG unlock flags in offline single-player game saves, with backup and rollback.
List, check and package a SKILL.md skill for every agent-skill store.
Your YouTube channels’ private analytics for AI assistants: revenue, views, retention. Read-only.
Headless LSP bridge MCP server: pinned language-server sessions as bounded read tools.
Work in your workonit account: people, records, app actions and AI agents.
Your brand's visibility in AI answers: trends, competitor ranking, cited sources and next tasks.
Find businesses for sale and off-market businesses to buy, with deep dives and a deal pipeline.
Clone websites, scrape pages to markdown and crawl whole sites. A free Firecrawl alternative.
Dependency audits, live CVE scans, migration detection and stack health across 9 languages.
Drive a real Chrome live, record a flow once, replay it in milliseconds without an LLM.
Fast, telemetry-free local MCP: shell, files, search, processes, PDF, Excel and Word for agents.
One MCP endpoint for all your servers: a few meta-tools, Keychain secrets, sandbox, audit, OAuth.
Long-term memory for AI agents: fast recall, project brains and skills, local, in one binary.
Read your Entry profile and drafts, write drafts and request publication. You approve changes.
Render SwiftUI #Preview as PNG images, so an AI agent sees the views it changes
Policy-scoped agent wallet: caps, recipient allowlist, human approvals, kill switch, audit trail.
Governed design-to-print authority for agents — signed provenance from model to machine, safety
Point an agent at a codebase: narrowed-scope architecture map, dependency/EOL risk list.
Governed Docker and Kubernetes operations for AI agents: scoped keys, guardrails, human approvals.
Read, edit, search and compile the LaTeX, Typst or Markdown project open in Oleafly.
RAM-only HTTP debugging proxy and MCP server in Go. AI agents see salted tags, never secrets.
Vedic astrology and astronomical ephemeris: kundali, panchanga, dashas, vargas, transits
Read-only NVIDIA GPU monitor: bottlenecks, VRAM forecast, crash diagnosis, pre-render check, jobs.
Spawn panes, inject input and read output in a tiling terminal workspace
Compile, run and check CUDA and HIP kernels without a GPU: wrong results, races, memory errors
Bills, hearings, votes and legislators for all 50 US states, DC and Congress, from official sources.
Live domain availability checks plus every free 1-4 character .com .net .de .ai .io .dev .app .tools
Free desktop CAE: import CAD/STL, solve FEM structural/thermal and CFD, verify the answer.
Compare supplied supplier statement and AP open items locally, with complete discrepancy evidence.
Compare supplied vendor statement and AP open items locally; keep missing and ambiguous evidence.
Public AI-written review DB. recall before recommending; propose after use.
MCP compatibility and transport verification server.
MCP compatibility and transport verification server.
Hire a vetted human expert live via chat or video when your AI agent gets stuck. $1/min.
MCP compatibility and transport verification server.
MCP compatibility and transport verification server.
Address in. Defendable offer out. 60 seconds. Comps, ARV, repairs and max offer for any address.
MCP oficial de Talo Pay: pagos por transferencia, transacciones, clientes y saldos desde tu agente.
Create and manage Instagram comment-to-DM keyword automations in CommentKeyword.
A profile you control: gives your AI your role, projects and preferences, across ChatGPT and Claude.
Company signals in your assistant: technologies, hiring, buying intent, news and site changes.
YouTube growth tools: keyword research, title scoring, AI titles, tags, audits, outliers, ideas.
Your coding agent keeps your help center current: it drafts article fixes after code changes.
Search your MarklyKit web highlights and notes from AI assistants, with source links.
Real estate agent AI library: Claude setup guide, CRM and social media prompts, free skills, kits.
A server you run yourself between AI agents and your accounts; by default, writes wait for your yes.
Mobile-network checks for AI agents: phone number, SIM swap, age and location (CAMARA).
Run a service business from your AI agent: CRM, leads, scheduling, invoicing, jobs and more.
Work, docs, CRM, calendar, chat and hiring for small teams. OAuth 2.1 with scoped, audited access.
GLEIF LEI and legal entity lookup for AI agents. 20K entities.
Run local models on your Apple silicon Mac with Loci. Requires macOS 26.2 or later.
Free vendor self-bench SDK — Assay scorecard format + verifier spot-check sampling.
Agent birth-certificate sealing + out-of-purpose detection, fixture records; detects, never blocks.
MCP deprecation radar: witnessed, hash-chained registry snapshots prove deprecated/removed tools.
Warranty witness for agent purchases: sealed, transferable claim packs. LOCAL/fixture only.
Free job-search agent: finds matching jobs, applies through your AI app, tracks it all locally.
Company context and tools for research, CRM, email, social publishing, and roadmaps.
NTRanch maker MCP: authoring, safety gates, playtest QA and release handoffs for adult games/apps.
Krafters club members open their specialized AI kits (ads, SEO/GEO, short videos) in one sentence.
Learning sidebar for AI coding assistants: quizzes on your changes, debug memory, term explanations
Self-hosted shared memory and docs for Claude Code, Codex and Antigravity agents, with a graph UI
Compile and run Omega (.om) programs in a sandbox, and look up Omega errors and keywords.
Read-only, dated public crypto source registry with evidence status. Local stdio; no API keys.
Japan business day & holiday calculator MCP. Official holidays + business-day arithmetic, 6 tools.
Public DNS, certificate transparency, and identity observations.
Ask about Adrian Capraru, Head of AI & Automation: case studies, services, availability, hiring.
Read-only health checks and data questions for SQL Server and PostgreSQL, with your saved profiles.
Remote MCP firewall with barter protocol: identity, threat-intel, IoC lookup.
Self-hosted kanban for humans and agents. One 4 MB binary, starts in 2 ms, zero setup.