Packages

Provides an MCP server (Streamable HTTP) that runs Python code in a fresh interpreter state with pyautogui instrumentation, returning captured stdout/stderr/results and inline screenshots (including mouse-operation previews). Includes a macOS-only helper to keep the display awake before automation.

Python-based voice AI client ported from xiaozhi-esp32, providing a full AI voice assistant experience with smart home IoT integration, multimodal capabilities, and MCP tool support — without requiring specialized hardware.

quick-data-mcp is an MCP server (Python) intended to let an AI agent perform agentic analytics on user-provided .json and .csv files via MCP Tools/Resources/Prompts, configured through an .mcp.json file pointing at a local directory.

airbyte-api-server is an Airbyte component that exposes an API surface for interacting with Airbyte (commonly used to control/run syncs and manage operations). It typically serves as the API layer behind Airbyte’s server/worker stack rather than being a standalone data connector service.

An MCP server for integrating with Azure DevOps, exposing tools that let an agent interact with Azure DevOps resources (e.g., projects, work items, pipelines/releases) via the Model Context Protocol.

MCP server that exposes Prisma/ORM operations to an MCP-capable AI agent, enabling the agent to inspect schema and perform database actions through Prisma tooling.

A MCP (Model Context Protocol) server package named "patersr-strands-mcp-server". From the name alone, it is intended to expose a set of MCP tools/actions to an AI agent, likely related to the "Patersr" and "Strands" domains/resources.

polygon-mcp-server is an MCP (Model Context Protocol) server that exposes Polygon blockchain-related capabilities to MCP-compatible AI agents, allowing them to query/act on Polygon data via MCP tools.

MCP (Model Context Protocol) server that exposes Elasticsearch operations (via Starsky iFlow integration) to LLM/AI agents through MCP tools, enabling querying and indexing/search workflows against an Elasticsearch backend.

toolhive-cloud-ui is a Next.js web UI that lets you visualize MCP (Model Context Protocol) servers running in your infrastructure, surfacing metadata and providing copy-ready endpoints to speed up AI agent integrations. It relies on toolhive-registry-server as a backend implementing the MCP Registry API and uses OIDC-based authentication (with an OIDC mock and MSW mock API for local development).

TriageMCP is an MCP server intended to perform basic static triage of Windows PE (Portable Executable) files using tooling such as pefile and YARA, returning analysis results to an LLM-driven workflow.

zellij-mcp-server is an MCP server that exposes Zellij (terminal multiplexer) functionality as MCP tools/operations so AI agents can interact with a user's Zellij session/workspace via the MCP protocol.

Provides an Axum-based MCP server (compiled to WebAssembly in the README) that exposes an HTTP JSON-RPC endpoint (/api/counter in the example) and implements at least a sample tool named "counter" with operations like increment, decrement, and get_value.

Brave ("brave") is a browser-oriented package/tooling that implements Brave Search integration. It provides an API client/adapter layer for searching the web using Brave Search, intended for programmatic use by applications and agents.

A Shopify-integrated, AI-powered commerce chatbot that provides customer support and product discovery using hybrid retrieval (FAISS + Elasticsearch) and can perform agentic shopping actions (e.g., create/update cart and customer-related actions) through Shopify GraphQL APIs, with session persistence via Redis and chat history via MongoDB. Includes a Shopify Theme Extension for UI embedding and a FastAPI backend with Docker-based deployment. Mentions an MCP server in the architecture diagram but provides no MCP server endpoint or tooling details in the README.

HasMCP-CE (HasMCP Community Edition) converts existing API endpoints described by OpenAPI/Swagger (and/or manually selected endpoints) into an MCP (Model Context Protocol) server that can be run self-hosted. It provides OAuth2 authentication options, endpoint toggling per MCP server, optional proxy header handling to the upstream API, token management, and logging/analytics for MCP tool calls.

mail-mcp-server is a Java/Spring AI MCP Server example that exposes email-related capabilities as MCP tools (notably: find contact email by name, and send an email via Spring Boot’s mail integration). It is intended to be used by an MCP Host/Client (e.g., via Spring AI’s MCP client) to let an LLM trigger these tools.

Provides an MCP (Model Context Protocol) server setup for Graphiti-based knowledge graph extraction and storage in Neo4j. It adds a CLI that generates a root MCP server plus multiple project-specific MCP servers (via Docker Compose) so multiple knowledge graphs can share the same Neo4j database while staying isolated by project configuration.

parse-server is a Node.js server that implements the Parse API spec (Parse backend) so you can build Parse-style applications. It persists data via supported database adapters (e.g., MongoDB) and supports Parse features like classes/objects, queries, file storage, push, and Cloud Code (depending on configuration).

prometheus-server is a Prometheus server component that scrapes metrics and provides time-series storage/querying and alerting support when paired with the broader Prometheus ecosystem.