Browse the catalog

An MCP server wrapper around MiniRAG that provides efficient retrieval-augmented generation capabilities through two distinct approaches: naive vector database querying and smart graph-based retrieval using entity relationships and reasoning paths. Leverages client-managed LLM inference with structured output constraints for enhanced reliability, while simplifying MiniRAG setup through UV dependency management. Supports configurable embedding providers including Ollama and OpenAI-compatible services, returning answers with cited sources in JSON format for knowledge retrieval workflows optimized for small language models.

Enables AI assistants to answer tax compliance questions (VAT, sales tax, GST) and validate EU VAT numbers in real time via the VIES registry.

MCP-Server-S3 provides a bridge to Amazon S3 storage services, enabling AI assistants to perform common S3 operations through a standardized interface. The implementation offers seven specialized tools for listing buckets, browsing objects, retrieving file contents, uploading and downloading files, and deleting objects. Built with Python 3.13 using the boto3 library, it authenticates with AWS credentials through environment variables and runs as a FastMCP server. This tool is particularly valuable for developers and data engineers who need to interact with cloud storage directly through AI assistants without switching to separate AWS management interfaces.

A read-only MCP server for Umami analytics, enabling natural language queries of website stats, traffic trends, events, sessions, and analytics reports.

A Node.js/TypeScript implementation of a Model Context Protocol server for the Deepseek R1 language model, optimized for reasoning tasks with a large context window and fully integrated with Claude Desktop.

Agentic Integration testing. No more write mock tests that fail at prod. Test Pilot takes GitHub repository URLs containing OpenAPI/Swagger specs, generates MCP (Model Context Protocol) servers, deploys them and the upstream APIs to Blaxel, then runs an AI agent to validate everything end-to-end.

Enables LLMs to query telemetry data via the Spyglass AI agent, providing intelligent insights about application performance, errors, and bottlenecks.

An MCP server providing RAG and CAG capabilities for querying and augmenting BambiSleep knowledge base data.

A Cloudflare Workers-based implementation of the Model Context Protocol server with OAuth login, allowing Claude and other MCP clients to connect to remote tools.

Claude Code plugin for user interaction via OpenClaw (Telegram, Signal, Discord)

Official AI4Outcomes plugin marketplace for Claude Code: thinqOS Mind integration

An MCP server for inspecting MEV-relevant activity on Polygon, providing tools to check pending swaps, confirmed swap history, and gas price percentiles, while honestly reporting coverage limitations.

Enables AI assistants to analyze IT support tickets, categorize urgency, suggest responses, and retrieve statistics via MCP tools.

**Live cricket scores, IPL tracking, and match alerts for OpenClaw.**.

Bridges Ollama's capabilities with MCP-compatible clients, enabling web search and content fetching to provide real-time information and reduce hallucinations.

MCP server for Joomil.ch — Swiss French classifieds marketplace (45k+ listings). Search ads, get details, browse categories.

This MCP server provides Warden + Magento 2 development workflow automation, enabling AI assistants to manage Docker-based Magento environments through Warden's command-line interface. Built by run-as-root using Node.js with the Model Context Protocol SDK, it offers 12 specialized tools including environment listing with structured JSON output, project lifecycle management (start/stop environments and services), database query execution, PHP script running, Magento CLI command execution, PHPUnit test running with auto-detection of configuration files, Composer package management with version validation, and complete project initialization with customizable PHP/MySQL/Node.js/Redis/OpenSearch/Varnish/RabbitMQ/Xdebug configurations. The implementation features robust path resolution and validation, detailed command output with debug information, automatic detection of available tools (composer2 vs composer), and comprehensive error handling with structured responses, making it valuable for Magento development automation, CI/CD pipeline integration, and building AI assistants that need programmatic control over complex Magento development environments without manual Warden command execution.

Agent memory MCP server with provenance tracking, decay-weighted recall, and feedback loops.

Residential proxy MCP server. 175M+ IPs in 195+ countries with anti-bot bypass.