Browse the catalog

An MCP server for European invoicing rules. Query VAT rates, e-invoicing requirements, format specifications, and compliance rules for EU-27 + EEA countries.

GenPark AI Skill - Aggregate reference feedbacks to verify proof-of-work profiles

MCP-FEISHU is a microservice control plane server that integrates Feishu OpenAPI with Windsurf IDE, enabling seamless API discovery and management. It provides tools for retrieving defect information through two main endpoints: getting specific defect links by ID and fetching recently updated defect lists filtered by status and date range. The server supports both stdio and HTTP/SSE transport methods, making it flexible for different integration scenarios while maintaining a standardized communication protocol for API testing and documentation capabilities.

This MCP server provides AI assistants with advanced JWT security auditing capabilities through four specialized tools for decoding, vulnerability analysis, secret brute-forcing, and token generation/editing. Built using Python with FastMCP and the cryptography library, it offers JWT header and payload decoding without verification, comprehensive vulnerability detection including algorithm confusion attacks, missing security claims, sensitive data exposure, and header injection risks, HMAC secret brute-forcing for HS256/HS384/HS512 tokens using customizable wordlists, and JWT generation with support for both symmetric (HS*) and asymmetric (RS*) algorithms. Inspired by the JWTAuditor tool, the implementation performs all operations locally without sending tokens to external services, includes built-in security checks for token lifetime analysis and replay attack detection, and supports common JWT security testing workflows, making it valuable for penetration testing, security assessments, and building AI assistants that need programmatic access to JWT analysis without manual security tool navigation.

Laravel upgrade automation via MCP. Analyzers, tools & docs for Laravel 6-11 migrations. Breaking change detection. Works with any MCP client (Cursor, Claude Desktop).

An idle dungeon crawler game playable through conversation, featuring equipment collection, time-based dungeon exploration, auto-battles, random events, and encrypted local save data.

Automate a real, logged-in browser on your own device — no stored credentials, no bot detection.

Memory-efficient LoRA kernel gradient optimizer saving 80% VRAM (Unsloth style)

MCP servers that actually work. Landing page for @madebydia open source MCP servers.

AI-powered E2E testing MCP server. Detects and auto-fixes UI bugs via DevQA Loop and Vision AI.

Topical dialog boundary enforcer & safety deflection router (NeMo Guardrails)

This MCP server demonstrates preference elicitation techniques for restaurant recommendations by implementing an interactive system that learns user preferences through strategic questioning and feedback. Built using Python with the MCP CLI framework, it showcases how AI assistants can gather and refine user preferences dynamically rather than relying on static queries, using restaurant selection as a practical example domain. The implementation serves as a reference for building preference-aware recommendation systems and demonstrates advanced interaction patterns where the AI proactively elicits information to provide more personalized and relevant suggestions.

Advantage Actor-Critic (A2C) tabular updates with TD error advantage estimation and softmax policy gradients.

An advanced AI agent that acts as a Senior Brand Strategist.

Enables processing and analysis of large PDF files through text extraction, search functionality, and intelligent chunking strategies. Provides comprehensive PDF operations including metadata retrieval, page-range text extraction, and content search with contextual results.

MCP server for pay-per-call DeFi and crypto data via x402 micropayments on Base. 8 endpoints: token prices, TVL, funding rates, token security, gas tracker, whale monitoring, wallet profiling, and yield scanning.

Unified MCP server for Construct 3 providing offline documentation, project read/write, analysis, and scripting support. Enables AI-driven game development and project management through natural language.

MCP server that scrapes app data from Google Play and Apple App Store, providing tools for search, details, reviews, and similar apps.

Fitness accountability for the Lofy AI assistant — workout logging from natural language, meal tracking.

A reference MCP server that connects any MCP client to a free cloud database, supporting 15 database engines with unified tools for querying, storing, listing tables, and annotating tables.