Search npm packages, get live registry data, and compare alternatives. No API key needed.
Scaffold VTEX IO apps, Node services and GraphQL, look up Store Framework block props, search docs
Model Context Protocol SDK instrumentation for telemetry.dev: instruments MCP v2 transports and emits OpenTelemetry spans.
Simple to write, built to hold: domain-first TypeScript backends whose guarantees live in the runtime, for people and AI agents alike.
Define Effect action contracts once and project them onto HTTP, MCP, Effect RPC, native Toolkits, and CLIs.
Shared memory for AI coding agents. A writer on every note (stamped by the server for token callers; a config label for local stdio apps), injection-linted writes, undo for replacements and edits. Sel
Every page of your site on one zoomable wall: desktop and phone captures, sandboxed live HTML, and element-anchored comments your coding agent can read.
Codebase knowledge graph — architectural awareness for AI coding agents via MCP
A design harness for AI coding agents: design systems, design principles, icons and UI review.
Secure encoding-aware filesystem tools with atomic writes, legacy encodings, and typed errors
Static security scanner for MCP servers, agent skills and npm/PyPI packages. Runs the skilltotal Python engine through uvx, pipx or an installed Python.
Vault for .env files and credentials with scoped, audited MCP access for coding agents.
Parallel coding agents claim a file before editing, so none overwrites another.
Antora extensions and macros developed for Redpanda documentation.
Converse MCP Server - Converse with other LLMs with chat and consensus tools
Nyx5/1 — mail and ledger for AI agents: agent@domain addresses, a store-and-forward mailbox, and a ledger where a claim costs something. One command to join, escrow released only against a determinist
An MCP server for Openware UI: gives Claude Code, Codex, Cursor and other AI tools the setup, every component's examples and props, every block's code, and the design tokens.
Agente de programación para la terminal que usa IAs gratuitas y salta a otro proveedor cuando uno se agota
Open-source human-in-the-loop QA runner: an AI agent works the test sheet, a person signs off.
MCP Server for Mearl - enables AI to interact with Chrome browser requests and logs
AI-powered code review engine with configurable rules, design patterns, and boundary-aware evaluation
Stops your coding agent from deleting, leaking or dropping things. Records everything else.
SceneScout — exploratory UI testing for AI coding agents. An MCP server that gives any agent (Claude Code, Cursor, VS Code Copilot, Codex, Gemini CLI and others) a structured view of a running web app
Zero-dependency safety gatekeeper, test oracle generator, and multi-agent coordination protocol for autonomous coding agents — Google Jules, Claude Code, Codex and Gemini CLI.
Harness for running Claude Code / OpenCode agents in the cloud or on your laptop, controlled from Telegram or Jira.
Conversation memory SDK — query meeting transcripts, decisions, and action items from any AI agent or application
Local-first, state-centric memory for coding agents. MCP server + CLI.
TypeScript authoring for A2UI and MCP Apps. Build agent UIs server-side and emit either wire format.
Interactive business cards for the terminal — npx yourname
Read-only Exeris context for AI agents: ADRs, SDK contract, build output, kernel diagnostics.
React views and a deck CLI for turning one structured story into an article, scrollytelling page, slide deck, narrated video or PowerPoint.
Model Context Protocol server for Matrix42 — lets AI assistants explore the API, read the data model, search the service desk, and act on tickets
Markdown-vault agent memory with a derived, brain-inspired graph index (hippocampal indexing, spreading activation, bi-temporal facts).
MCP server exposing a local omlx inference server (chat, structured output, model status) so coding agents can delegate bulk work to a local model.
MCP server for Chain Daddy: search tickers, launch a token or verify ownership of one, and run its creator store
Benchmark AI coding agent skills, plugins and CLAUDE.md files: run Claude Code, Codex or OpenCode with and without them and measure pass rate, cost, false "done" claims and test tampering. Works with
Toàn bộ thư mục
IDE, git, lint và phân tích mã. 8,616 máy chủ, dùng nhiều nhất xếp trước. Mỗi máy chủ mở ra trang của nhà phát hành.