Amazon Shopping with Claude

Open registry of skills, tools, datasets, prompts, and playbooks for local LLMs. Search 155+ resources, get AI-powered recommendations, and install capabilities on demand for Ollama, LM Studio, and llama.cpp. Free, open, community-built.

GitLab API, enabling project management

Repository management, file operations, and GitHub API integration

Creates a live link-in-bio page in under 30 seconds via conversation

Manage your Plesk hosting server using AI assistants.

Cross-channel CPG pricing intelligence — Amazon category benchmarks (percentile rank, trend, tier breakdown) for multi-channel brands selling on Amazon plus retail, DTC, or wholesale. Six tools across 800+ tracked products in Grocery, Health & Beauty, Household, and Pet Supplies. Free alternative to enterprise category data.

Any CSV to any CSV. Get a file the destination app accepts on the first try. Templates for Amazon → Shopify, Amplitude cohorts, more coming. One tool call, same output every time.

GBOX provides environments for AI Agents to operate computer and mobile devices. Mobile Scenario: Your agents can use GBOX to develop/test android apps, or run apps on the Android to complete various tasks(mobile automation). Desktop Scenario: Your agents can use GBOX to operate desktop apps such as browser, terminal, VSCode, etc(desktop automation). MCP: You can also plug GBOX MCP to any Agent you like, such as Cursor, Claude Code. These agents will instantly get the ability to operate computer and mobile devices.

Live access to Henrik Bondtofte's blog — Denmark's leading SEO and GEO consultant. 26 tools: semantic post search, ask_henrik (answers in his own voice), SEO URL audits, AI Overviews & GEO knowledge base, topic authority, term lookups, and book recommendations. 200+ posts in Danish. Also acces to 400 pages from his SEO books.

test

Quizlar is the learning MCP server. It turns whatever source the user brings — a YouTube lecture, a PDF, a URL, a textbook passage, or a pasted block of notes — into flashcards, then runs interactive quizzes with FSRS spaced-repetition scheduling so the material actually sticks. Every tool maps one-to-one to something a real learner does: ingest, quiz, track progress, review what's due. Built as a voice-first tutor (LiveKit + Deepgram + ElevenLabs); the MCP surface exposes the same primitives the voice agent uses internally, so your agent gets production-grade grading, STT-aware answer parsing, and the same FSRS scheduler that powers the consumer app. Three use cases: 1. "Quiz me on X." Call quiz_me(topic) — a composite tool that builds the deck and starts the quiz in one step. Then loop submit_answer → end_quiz. Grading is tier-1 exact match → phonetic fuzz → short LLM fallback (the same pipeline that ships in the voice product). 2. Study from a YouTube lecture. create_deck_from_youtube pulls the transcript, clusters it into concepts, and generates cards proportional to the video length. Poll get_job_status, then run the quiz loop. 3. Daily spaced-repetition review. get_study_recommendations returns exactly the cards due under the user's FSRS schedule, prioritised across all decks. Quizlar is the scheduler of record — your agent executes the plan instead of reinventing one each session. Auth: Bearer token (sk-qz-<32 chars>) for headless installs, or full OAuth 2.1 / DCR / PKCE for one-click clients (Smithery, Claude Connector). Mint keys at https://quizlar.app/settings/api-keys. 22 tools total. Voice and text equal-status. Education-first.

Browser automation and web scraping

Production MCP server with 9 financial and web tools — live on Google Cloud Run. Free tools include live FX rates, crypto prices, financial calculations, real-time news headlines, and URL reading. Paid tools (API key required) cover stock quotes, open banking transactions, and Stripe payment data. Supports x402 micropayments ($0.001 USDC/call on Base) with no account needed.

Create a remote sandbox that can execute code/run commands/upload and download files. 创建远程沙盒，可以执行代码/运行命令/上传下载文件

ExpenseBot is the first expense management tool on the official MCP Registry. Two MCP servers: @expensebot/mcp-server-auth (authenticated) — 13 tools that work with your real ExpenseBot data: - Search expenses by category, merchant, date, amount - Submit photo/PDF receipts via base64 - Scan Gmail for receipts on demand - Create, list, share, download expense reports - Run deep analytics ("compare Q1 vs Q2 spending") - Add cash expenses without a receipt - Check tax deductibility - Check compliance issues @expensebot/mcp-server (read-only) — answers questions about ExpenseBot for pre-sales/help. Auth: Personal Access Tokens generated from Settings → AI Assistant Tokens. 30-day expiry, revokable, scoped to your account only. CASA Tier 2 certified. Free with any ExpenseBot account (60-day free trial).

Lightrun MCP connects AI coding assistants to live runtime context from production and staging applications for safe code-level debugging without redeploying. It lets MCP-compatible clients discover runtime sources, inspect live expression values, capture call stacks, measure execution duration, count executions, and collect numeric runtime metrics directly from the AI workflow.

Financial Modeling Engine for AI Agents: build typed PNLs, scenarios, and sensitivity analyses. Export to Excel.

Write notes to Flomo

Build owned-audience websites: pages, posts, products, subscribers, ShopMy/Shopify imports, tickets, memberships, RSS/Pinterest, and analytics from any AI agent.

Read-only MCP server for U.S. dental practice intelligence. Four tools cover NPI lookup, multi-field provider search, DSO chain affiliation, and territory market summaries across 41 states plus DC. Authenticate with an API key (Bearer) for subscription pricing, or pay per query via x402 USDC micropayments on Base mainnet. Every response carries a citation envelope with source attribution, snapshot date, and confidence score.

Guide to using the Finch framework in Dart

Local-first AI context and memory server for cross-tool coding continuity. MindSwap helps coding agents and developers persist project context, search prior decisions, manage structured memory, resume work across sessions, and keep MCP-compatible tools aligned through one shared context layer.

An MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.

Privacy-first audio intelligence for agents and creative audio workflows. Analyze public audio URLs for BPM, musical key, and waveform shape. Audio is processed ephemerally and not stored; pay per second with no account required for the public UI.

AI-native payment infrastructure that gives AI agents isolated wallets with programmable spending policies for autonomous USDC stablecoin transactions. 11 MCP tools for Claude Desktop, Cursor, and Windsurf. Tri-rail support: x402 (HTTP-native micropayments), MPP (session-based streaming), and traditional fiat. Non-custodial wallets with Shamir key splitting, sub-second settlement on Polygon PoS, Base, and Tempo. Free tier, no credit card. Website: https://moltpe.com Reference impl (Apache 2.0): https://github.com/umangbuilds/moltpe-agent-payments