Trust Reports
Independent Trust Reports for public GitHub repos — security, code quality, license, and completeness scored 0–100. Maintainers can claim their listing in 30 seconds.
Top scoring · Verified
Provides a list of reserved identifiers for JavaScript
unist utility to find a node after another node
Parse HTTP Content-Type header according to RFC 7231
utility to get the position of a node
utility to get the plain text content of an mdast node
The smallest and fastest command-line coloring package on the internet
Fast, elegant SSH connection manager with a TUI dashboard and MCP server
An MCP server (and a CLI) that lets an LLM query your databases in natural language through a business semantic layer — glossary, metric definitions, data dictionary, knowledge base, and example queries — grounded against your real schema.
MCP Toolbox for Databases is an open source MCP server for databases.
Search & analytics data as infrastructure — MCP server for Google Search Console, Bing Webmaster Tools, and GA4, designed for AI agents and automation.
MCP server for virtual phone number verification - SMS activations for AI agents via Claude, Cursor, VS Code Copilot and more...
Make your meetings accessible to AI Agents
A Kubernetes MCP (Model Control Protocol) server that enables interaction with Kubernetes clusters through MCP tools.
MCP Server for LocalStack
DICOMweb Model Context Protocol (MCP) server implementation
BioMCP: Biomedical Model Context Protocol
DreamGraph is a graph-governed conceptual development environment (CDE) that turns plans, architecture decisions, and project knowledge into auditable execution through a persistent cognitive graph.
Awesome ModelContextProtocol resources - A curated list of MCP resources
Govern & Secure your AI
ScienceClaw is a personal research assistant built with LangChain DeepAgents and AIO Sandbox infrastructure, adopting a completely new architecture beyond OpenClaw. It offers stronger security, better transparency, and a more user-friendly experience.
Give Claude/Cursor email powers. 27 MCP tools — inbox, send, reply, contacts, search. Free, no signup.
Vibecoding 系列教程：从环境搭建到多智能体协作，涵盖 MCP、Skills、Agent 分工治理
An AI co-worker with its own computer. Self-evolving, persistent memory, MCP server, secure credential collection, email identity. Built on the Claude Agent SDK.
Plugin for IntelliJ IDEA that gives special support for Minecraft modding projects.
🦖 Serverless AI Agent Framework with Geo-distributed Edge AI Infra.
✨ Agentic chat experience in your terminal. Build applications using natural language.
Yet another WebUI for Nginx
Go language library for reading and writing Microsoft Excel™ (XLAM / XLSM / XLSX / XLTM / XLTX) spreadsheets
AI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨
🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
CLI server for Zotero 7/8/9 — let AI manage your library. 70+ CLI commands for search, import, PDF, BibTeX, notes, and more. Works with Claude, Cursor, ChatGPT.
🪐 面向 AI 的多音乐平台的 API 代理 • 网易云 • QQ音乐 • 酷狗 • 酷我 🎻 Multi-platform music API agent for AI • NetEase • QQ Music • KuGou • Kuwo
A collection of Model Context Protocol (MCP) servers, clients and developer tools by IBM.
AINL helps turn AI from "a smart conversation" into "a structured worker." It is designed for teams building AI workflows that need multiple steps, state and memory, tool use, repeatable execution, validation and control, and lower dependence on long prompt loops. AINL is a compact, graph-canonical, AI-native programming system for (READ: README)
AI-Native Risk Intelligence Systems, OpenDeRisk——Your application system risk intelligent manager provides 7* 24-hour comprehensive and in-depth protection.
Build autonomous AI agents in Python.
The open-source memory and observability layer for AI agents — persistent memory, loop detection, hash-chained audit trails, and a live dashboard, automatic on pip install.
MCP Python Tutorial
VSCode Extension with an MCP server that exposes semantic tools like Find Usages and Rename to LLMs
A model context protocol server to work with JetBrains IDEs: IntelliJ, PyCharm, WebStorm, etc. Also, works with Android Studio
MCP server for the Registrum Companies House API
MCPR enables AI agents to participate in interactive R sessions for professional analysis workflows.
Model Context Protocol server exposing system prompt files and summaries.
A powerful MCP (Model Context Protocol) Server that audits npm package dependencies for security vulnerabilities. Built with remote npm registry integration for real-time security checks.
Deterministic policy language for AI agents. Z3 + TLA+ dual-engine formal verification. Runtime enforcement <1ms.
MCP server for Agent Trust Stack — cryptographic provenance and reputation scoring for autonomous AI agents. Install: pip install agent-trust-stack-mcp
The web data layer for AI agents — fetch, search, crawl, extract, screenshot, and monitor the web with 50+ domain extractors and MCP.
The license-first image layer for AI agents and humans. 24 federated providers · CC0/CC-BY/PD-first · MCP native · Chrome extension · Python + TS SDKs.
MCP server for GOV.UK — search, content drill-down, organisations, and postcode lookup. 5 tools, no API key, hosted on Fly.io.
Search infrastructure for AI agents: free by default, MCP-ready, LLM-context aware, and production-grade when needed.
OTTASIA MCP server — answer "where can I watch X in Y" for 30 Asian and Middle Eastern streaming markets, callable from Claude Desktop.
The first multi-source MCP server for Philippine civic data: earthquakes, weather, typhoons, procurement, population, poverty
Turn any web page into traceable, citable evidence for AI agents.