Packages

puli-mcp-server is an MCP (Model Context Protocol) server package intended to expose capabilities to AI agents via the MCP interface. Based on the name alone and without README/repo details, the exact tools and behaviors cannot be verified.

A Python-based MCP server that exposes VOICEVOX text-to-speech capabilities (e.g., generic speaker speak, a specific Metan Aska-style tool, and a speakers list) by wrapping the VOICEVOX Web API using FastMCP.

MCP server package intended to expose SignNow (eSignature) capabilities to AI agents via the Model Context Protocol, enabling programmatic signing/document workflows through agent tool calls.

taskify-mcp-server provides an MCP (Model Context Protocol) server that exposes Taskify-related functionality to AI agents via MCP tools/operations.

tdd-mcp-server is an MCP (Model Context Protocol) server intended to help with Test-Driven Development workflows by exposing MCP tools/resources that agents can call.

vcosmos-mcp-server is an MCP (Model Context Protocol) server package intended to expose Vercel Cosmos (Cosmos DB) related capabilities to AI agents via the MCP interface.

Provides an MCP server (Hospital Data MCP Server) that exposes access to an included, entirely fictional hospital dataset via Model Context Protocol. It supports both SSE (server-sent events) and STDIO transports and includes guidance for running and testing with the MCP Inspector.

claude-colony is a CLI tool that orchestrates multiple Anthropic Claude Code agent instances in parallel using a tmux-based workflow. Agents coordinate through a file-based @mention protocol and run as full Claude Code instances, optionally using team presets and agent prompt files under .claude/agents/.

Fail2ban is a host-based intrusion prevention tool that monitors log files (e.g., for SSH failures) and automatically bans IP addresses that match configured patterns/rules, using configurable ban actions and whitelists.

Jackett is an application (typically self-hosted) that aggregates multiple torrent indexer sites and exposes them via a local interface compatible with torrent clients. It handles subscribing/enabling individual indexer definitions and searching across them, returning results to the requesting client.

A Go-based MCP server that connects to Jira (using a username + API key) to manage and track Jira issues. It can run in stdio mode and also supports an SSE transport.

Provides a Kubernetes-focused Model Context Protocol (MCP) server that exposes operations for managing Kubernetes resources and retrieving/searching/exporting pod logs via HTTP endpoints.

laravel-echo-server is a self-hosted WebSocket server that relays Laravel broadcast events (from Echo) to clients via the Pusher protocol (or compatible clients).

Provides an MCP server that connects an MCP client (e.g., Claude/Cursor) to the browser automation capabilities of browser-use, allowing agents to control a browser through the MCP client while reusing the LLM already configured in that MCP client.

A Python-based repository intended to provide/market a “Model Context Protocol (MCP) Marketplace” of multiple MCP server implementations from Volcengine (and many third parties). The README describes selecting MCP servers from a marketplace, installing them into an MCP client via URLs/JSON, and lists many server categories (compute, storage, databases, etc.)—but does not include concrete implementation details for the root “mcp-server” package itself.

Provides a demo of a Model Context Protocol (MCP) server and client built with Spring Boot and Spring AI. The server exposes REST endpoints for managing medical patients and reports and integrates Spring AI MCP for context-rich interactions with an AI model; the client consumes the server and provides a client-side UI/endpoints for structured requests/responses.

An MCP server intended to automatically generate CSDN blog posts (CSDN 自动发帖).

mcp-shield is a CLI security scanner that inspects installed MCP server configurations/tools and reports potential prompt-injection/tool-poisoning style vulnerabilities, suspected data-exfiltration channels, tool shadowing/behavior modification, and cross-origin escalation risks. It can optionally use an Anthropic Claude API key to enhance analysis.

Redis MCP server exposing Redis management/control tools via an MCP interface implemented as SSE (Spring Boot + spring-ai MCP webmvc starter). Supports basic key operations: set/get/delete and pattern-based key listing (with optional expiration for set).

An MCP server package that exposes “rules” functionality to an AI agent via the Model Context Protocol (MCP).