Kontor MCP — MCP-free core library: detect, parse, validate, generate, convert EN 16931 e-invoices (XRechnung, ZUGFeRD)
Publish a server.json to the MCP registry from CI: retries the registry's transient failures and skips a version it already lists. A GitHub Action and an npm package.
Local, client-agnostic message bus for AI CLI sessions with group threads
An MCP server that lets an agent discover the afora catalog, edit afora.json, validate it, generate the code and check the result.
Clipoox from the terminal: sign in once, then call any Clipoox MCP tool (Timeline, media, AI generation, 3D Shot, SEO) from scripts.
Automatically resume Claude Code, Codex CLI, Grok, Qwen Code, Kimi CLI, OpenCode, Antigravity, and Cursor CLI sessions when 5-hour or weekly usage limits reset—on macOS, Linux and Windows, with or wit
Atbash safety judge exposed as a standalone MCP server
Read .sketchframe design files from the command line or an MCP server: outlines, layer details, screenshots, tokens and annotations for AI agents
Native repository intelligence for coding agents: 66 MCP operations backed by typed evidence graphs, impact, architecture, local CI restrictions, APIs, Git, search, semantic links, n8n workflows, Dify
MCP server for IMAP/SMTP email access with environment-based configuration
MCP server providing Solidity smart contract security analysis tools, OWASP knowledge base, and development utilities for AI agents
Sync your DeepSeek Harness (DSH) configuration between machines over a private git or WebDAV channel: settings, plugins, MCP servers, skills, agent presets and provider credentials. DSH 配置远程同步插件(私有通道,
Nuxt module for apps hosted on wervt: database, live data, MCP and runtime setup.
l8bin (pronounced LiteBin) MCP server — deploy and operate your self-hosted projects from any MCP client. Wraps the l8b CLI, installing the platform binary on first use.
Model Context Protocol server for the cat-factory public API (/api/v1): a thin facade that exposes the published operations as MCP tools, generated from the same OpenAPI spec the SDKs are, over the ha
Knowledge infrastructure SDK for AI agents - universal references, multi-tier caching, storage abstraction, and sync
Sai MCP server — drive your Sai computer-use agent from Claude Code, Codex, or Cursor.
Zambo tools for Vercel AI SDK agents: AI tools on one endpoint. Every call returns a verifiable execution receipt (AER-1, IETF Internet-Draft draft-zambo-aer1-26). Free: 20 calls + 1 wrap-up free ever
TSPL command-line tool: learns your code, plans changes with you, builds, tests and opens pull requests
Typed AI framework for TypeScript: provider routing and failover, durable agent graphs and workflows, retrieval over any vector store, MCP, evals, guardrails, and cost control
InsideOut MCP server for infrastructure design, Terraform generation, deployment, and inspection
Stunt Double Studio: create actors and checklists, run them in a local Chrome on your own model connection or from your coding agent, and keep every run as files in your project
MCP server for OmniaCSS: lets AI assistants (Claude, Cursor, Copilot …) check, look up and search OmniaCSS classes, variants, color tokens, OmniaUI components and blocks (with their HTML) and docs, an
An AI agile team for your repository: test-first AI workers in isolated Git worktrees, behind the checks, code review and security scans you approve.
Canonical MCP/OAuth scope metadata for Motorical — descriptions, Public API scope mapping, implied-read rules, and declarative tool/resource membership. One source of truth consumed by motorical-backe
OmniQA: agentic test framework and product knowledge base. SDK, runner and CLI.
Universal LLM API client for 174 providers — chat, streaming, tools, embeddings, search, OCR, plus an OpenAI-compatible proxy and an MCP server.
An agentic harness on the command line: connects to remote or local models and lets them use tools and skills.
MCP server for reading, editing, and comparing Word (.docx) and OpenDocument (.odt) files with tracked changes. For Claude, Gemini CLI, Cursor, and any MCP client. Apache-2.0 licensed.
The Agentic Readiness Scanner engine: fetcher, target resolver, parsers, checks, runner, scoring and reporters, with the catalog and visual system bundled in.
ESLint for AI slop. 40 rules for catching AI-generated code smells in JS/TS and Python.
Runtime library for bnbagent-studio seller agents on BNB Chain (config, wallet, audit, ERC-8004/8183, x402 or MPP over B402, Pieverse, read-only chain tools).
Runtime verification for AI coding agents. MCP server that lets Claude Code verify code changes work end-to-end via Playwright + OpenTelemetry. Embedded OTel collector by default — no Docker, no SigNo
Model Context Protocol (MCP) server and Claude Desktop extension for Hardcharger, GizmoData's DuckDB 2.0 server
Personal AI coding agent runtime: IDE-grade code editing, isolated Git worktree subagents, time-traveling stream rules, and a dual-direction OpenAPI and OpenClaude gateway.
Drive an MCP server over real stdio against a real backend, and prove every tool was exercised
Toàn bộ thư mục
IDE, git, lint và phân tích mã. 8,728 máy chủ, dùng nhiều nhất xếp trước. Mỗi máy chủ mở ra trang của nhà phát hành.