DIRECTORY

Search AI components

Search and filter on the server without downloading the full catalog.

95 matching componentsClear filters

mcp-airlock

MCP Service · MCP Services
◷ Pending review

Stateless governance proxy for MCP (2026-07-28): policy, dry-run, human confirmation, audit, tracing.

See official docsTerms pending review
View evidence →

yelp-mcp

MCP Service · MCP Services
◷ Pending review

MCP server for Yelp: business search, place details and the full review feed as JSON. Hosted, no Yelp Fusion key. 1,000 free credits every month.

See official docsTerms pending review
View evidence →

bing-mcp

MCP Service · MCP Services
◷ Pending review

MCP server for Bing search: organic results, the ad block and the Copilot answer, with geo, market and language targeting. No Azure subscription. 1,000 free credits every month.

See official docsTerms pending review
View evidence →

facebook-mcp

MCP Service · MCP Services
◷ Pending review

MCP server for Facebook: a public page or profile by handle with likes, followers, contact details and the post feed with reactions. No Meta developer app. 1,000 free credits every month.

See official docsTerms pending review
View evidence →

maintainer-skills-lab

MCP Service · MCP Services
◷ Pending review

16 reusable skills and 6 agents for Codex, Claude Code, Cursor, OpenCode and Grok Bot: Humanizer, ML debugging, PR review and Skill Watch.

See official docsTerms pending review
View evidence →

blitzstrike

MCP Service · MCP Services
◷ Pending review

⚡ Blitz Strike — a universal MCP penetration-testing toolbelt. Structured methodology: reconnaissance & attack-surface mapping, source-to-sink analysis, and live validation. 57 escalation chains, 130-tool catalog, intelligence data layer. One server, every agent.

See official docsTerms pending review
View evidence →

google-scholar-mcp

MCP Service · MCP Services
◷ Pending review

MCP server for Google Scholar: search papers with Scholar operators, year ranges, cited-by and all-versions lookups, plus citations in five styles with BibTeX export. 1,000 free credits every month.

See official docsTerms pending review
View evidence →

AunoStudio

MCP Service · MCP Services
◷ Pending review

AI-native, self-hosted studio for editable video, motion, documentary creation, social publishing, and workspace collaboration.

See official docsTerms pending review
View evidence →

artifact-site

MCP Service · MCP Services
◷ Pending review

A self-hosted home for your team’s AI-generated pages and documents. Publish HTML, build folders, ZIPs and PDFs as sandboxed, versioned links. CLI + remote MCP for AI agents.

See official docsTerms pending review
View evidence →

jev-browser

MCP Service · MCP Services
◷ Pending review

Browser automation where an LLM plans and Jev (Typesafe System One) decides. Library, CLI and MCP server.

See official docsTerms pending review
View evidence →

Awwards-mcp

MCP Service · MCP Services
◷ Pending review

Free, open-source MCP server that gives AI coding agents (Claude Code, Codex, Cursor, OpenCode, ZCode…) design inspiration from award-winning websites — search with real screenshots, pull design DNA, capture and record live sites. A Mobbin alternative. No API key.

See official docsTerms pending review
View evidence →

jev-seo

MCP Service · MCP Services
◷ Pending review

100% free ₹0 agent-first SEO & GEO CLI suite and MCP server in Rust replacing Semrush and OpenSEO via DuckDuckGo and TypeSafe Jev System One.

See official docsTerms pending review
View evidence →

jev-use

MCP Service · MCP Services
◷ Pending review

Claude Code / Codex / pi plugin that hands agent steps needing no text output to Jev (TypeSafe's judgment model) — measured p50 ~230 ms and ~$0.02 per 1,000 judgments, with typed escalation back to the LLM.

See official docsTerms pending review
View evidence →

jev-cli

MCP Service · MCP Services
◷ Pending review

Command-line tool for TypeSafe AI's Jev model. Ask yes/no, multiple-choice and rubric questions about any text and get calibrated probabilities back. Answers become exit codes for shells and CI, JSON for scripts, and MCP tools for AI agents.

See official docsTerms pending review
View evidence →

jevcore

MCP Service · MCP Services
◷ Pending review

TypeSafe Jev for DeepSeek Harness, the Model Context Protocol, and plain Node: typed judgments instead of prose, offline by default.

See official docsTerms pending review
View evidence →

jev-ultrafast-mcp

MCP Service · MCP Services
◷ Pending review

Hand the browser work off: an MCP server where a decision model drives the page for your agent, so a flow costs one tool call instead of a turn per click. Ref-based element tables, code-checked assertions, zero-model macro replay. Speaks CDP to your Chrome.

See official docsTerms pending review
View evidence →

system1-agents

MCP Service · MCP Services
◷ Pending review

System 1 decision models (Jev, Laya, Cua-S1) as brain for agents: Browser use, computer use, games and robotics.

See official docsTerms pending review
View evidence →

jev-judge-mcp

MCP Service · MCP Services
◷ Pending review

Typed judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate, and score: the model judges, policy decides auto, review, or escalate.

See official docsTerms pending review
View evidence →

morocco-communes

MCP Service · MCP Services
◷ Pending review

Morocco's 1,503 communes as open data: HCP codes, the 2024 and 2014 censuses, boundaries, an HTTP API and an MCP server.

See official docsTerms pending review
View evidence →

farhand

MCP Service · MCP Services
◷ Pending review

Remote hands for coding agents: an MCP server that runs OpenCode / Claude Code / Codex work on a remote host over SSH, keeps credentials and the local machine closed, and audits everything.

See official docsTerms pending review
View evidence →

mcp-audit-tool

MCP Service · MCP Services
◷ Pending review

🛡️ Security audit CLI for Model Context Protocol (MCP) servers — scan AI agent configs for tool poisoning, rug pulls, hardcoded secrets, command injection & supply-chain risks. Pure Python, SARIF + CI ready.

See official docsTerms pending review
View evidence →

genspark-claw

MCP Service · MCP Services
◷ Pending review

🦀⚡ Community skill pack & CLI for Genspark Claw, OpenClaw & Hermes agents — 5 production-ready SKILL.md skills (deep research, reports, slides, browser automation, AI call prep), zero-dependency Node.js installer, MCP server, one-line install.

See official docsTerms pending review
View evidence →

usagetrim

MCP Service · MCP Services
◷ Pending review

Keep the signal. Cut the noise. Local CLI + MCP — fold verbose tool output for Claude Code, Codex, Cursor & Desktop.

See official docsTerms pending review
View evidence →

proxy-scraper

MCP Service · MCP Services
◷ Pending review

Free proxies that actually work: 700+ sources, every hit verified (honeypots, injected scripts, TLS), a live list every hour, a rotating proxy server and an MCP server for AI agents.

See official docsTerms pending review
View evidence →

app

MCP Service · MCP Services
◷ Pending review

Binders for macOS: local-first dictation, meeting notes and memory, with an MCP server for your AI tools. Private by design, free, open source.

See official docsTerms pending review
View evidence →

jevmem

MCP Service · MCP Services
◷ Pending review

Automatic project memory for Claude Code. Also works with Cursor and Codex.

See official docsTerms pending review
View evidence →

reverse-cad

MCP Service · MCP Services
◷ Pending review

⚙️ Industrial-grade deterministic STL ➔ STEP AP242 solid B-Rep converter & semantic CAD Features JSON engine with built-in MCP server for AI agents. Sub-second speed, ISO threads (M2–M24), Print-in-Place kinematics, and 99.958% RSVS mathematical fidelity across macOS, Windows, and Linux.

See official docsTerms pending review
View evidence →

oh-my-android

MCP Service · MCP Services
◷ Pending review

Android emulator & ADB GUI for Mac: dark mode, font size, RTL, TalkBack, network, GPS, Layout Inspector in dp. Built-in MCP server lets Claude Code, Codex and Cursor drive the emulator.

See official docsTerms pending review
View evidence →

showtime

MCP Service · MCP Services
◷ Pending review

A local video studio for your coding agent. Describe a video in one sentence: your agent directs, your machine renders. Claude Code, Codex, Cursor, Devin and more. No API keys, no uploads.

See official docsTerms pending review
View evidence →

AdLibrarySpy

MCP Service · MCP Services
◷ Pending review

A free, open-source Shopify store and Meta ads spy tool. Find winning stores, see the ads they run, track competitors. Every number measured, nothing estimated.

See official docsTerms pending review
View evidence →

loci

MCP Service · MCP Services
◷ Pending review

Typed long-term memory for AI agents. One core, an MCP server, and a Hermes plugin.

See official docsTerms pending review
View evidence →

kenfold

MCP Service · MCP Services
◷ Pending review

Self-hosted memory server for AI agents. Share context across Claude Code, Codex, OpenCode, and ChatGPT over MCP.

See official docsTerms pending review
View evidence →

BashCut

MCP Service · MCP Services
◷ Pending review

Native macOS video editor that coding agents can drive: everything the UI does, Claude Code and Codex can do through the bashcut CLI or MCP server. Layered timeline, captions, voiceover, plugins.

See official docsTerms pending review
View evidence →

snapp-mcp

MCP Service · MCP Services
◷ Pending review

Unofficial read-only MCP server for Snappfood & SnappMarket: search food and groceries, compare prices, find deals.

See official docsTerms pending review
View evidence →

official-mcp-servers

MCP Service · MCP Services
◷ Pending review

A curated directory of 280+ official MCP servers from the companies behind the products. No unofficial forks, no abandoned projects.

See official docsTerms pending review
View evidence →

AiPC

MCP Service · MCP Services
◷ Pending review

Give the agent "this" and he gets a real PC.

See official docsTerms pending review
View evidence →

arabic-ai-atlas

MCP Service · MCP Services
◷ Pending review

The Arabic AI ecosystem as a map, a list, and a skill your agent can install.

See official docsTerms pending review
View evidence →

passportsim

MCP Service · MCP Services
◷ Pending review

Develop and debug FoloToy AI Passport firmware without the device: an ESP32-C3 emulator that runs unmodified ESP-IDF images in the browser (WebAssembly) or on macOS and Windows, with a CLI and an MCP server for AI agents.

See official docsTerms pending review
View evidence →

framejam

MCP Service · MCP Services
◷ Pending review

Make videos with your coding agent: pick a style, then point at the frame and say what to change. Works with Hyperframes, Remotion or any video tool, over MCP.

See official docsTerms pending review
View evidence →

amber-notes

MCP Service · MCP Services
◷ Pending review

Amber Notes: the free, open-source notes app for iPhone and Mac that ChatGPT and Claude can use (MCP).

See official docsTerms pending review
View evidence →

paper-preflight

MCP Service · MCP Services
◷ Pending review

Pre-submission integrity gate for LaTeX papers: every reference verified against real scholarly records. No LLM guessing.

See official docsTerms pending review
View evidence →

digikala-mcp

MCP Service · MCP Services
◷ Pending review

Unofficial read-only MCP server for Digikala: search products, compare sellers and prices, price history, reviews, deals.

See official docsTerms pending review
View evidence →

shipstores

MCP Service · MCP Services
◷ Pending review

Ship iOS and Android apps from your AI agent. MCP server for App Store Connect, Google Play Console and Expo EAS.

See official docsTerms pending review
View evidence →

verifiedhandles-mcp

MCP Service · MCP Services
◷ Pending review

Connect an AI agent to Verified Handles: setup for each client, the MCP Registry listing, a Claude Desktop extension.

See official docsTerms pending review
View evidence →

watchtower

MCP Service · MCP Services
◷ Pending review

Self-hosted error tracking. A drop-in for Sentry and AppSignal SDKs: one Go binary and Postgres, with Slack, Linear, email and an MCP server for coding agents.

See official docsTerms pending review
View evidence →

outsystems11-mcp

MCP Service · MCP Services
◷ Pending review

Skills that let Claude Code, GitHub Copilot, Cursor, Kiro and other coding agents work with OutSystems 11 apps via the Service Studio MCP server.

See official docsTerms pending review
View evidence →

agent-mail-gateway

MCP Service · MCP Services
◷ Pending review

Self-hosted email MCP server & REST gateway: give each AI agent its own IMAP/SMTP mailbox with sender/recipient allow lists, HTML-to-Markdown, attachments and calendar invites. One Docker container.

See official docsTerms pending review
View evidence →