Production-ready library for converting OpenAPI specifications into MCP tool definitions
Model Context Protocol implementation for TypeScript
bce — the blueprint conformance engine. Author an EngineeringBlueprint and gate code against it with deterministic scores, fail-closed verdicts, and re-derivable evidence. TypeScript/JavaScript AST ex
Fast code intelligence for AI coding agents — installs a verified native runtime set
Shiplight CLI for running and debugging .test.yaml files
MCP Connector for DeepSeek Harness: a data marketplace connecting enterprise, financial, legal, patent and research data. Manage authorization, search tools and troubleshoot MCP connections. Supports
Zero-config background service manager, auto-discovery daemon & dashboard launcher for AI agent ecosystems (pxpipe, ocx, hindsight, headroom)
Deco CMS — Self-hostable MCP Gateway for managing AI connections and tools
Request capture SDK for AI traffic attribution and agent feedback collection
Auth-aware Convex component that exposes selected Convex functions as MCP tools.
Ruff Python linting for AI agents, pay-per-call via x402 ($0.005 USDC on Base).
Let your coding agent read and write your product boards, plans and tasks in Fulveo.
The TestSprite MCP plugin brings fully automated software testing into your coding workflow. It connects your IDE's AI assistant (like Cursor or Copilot) with TestSprite's intelligent testing engine t
Launch coding agents (Claude Code, Codex) on boat.dev sandboxes: the armada command line.
Azure DevOps reference server for the Model Context Protocol (MCP)
AI-controlled email operations control plane for campaigns, contacts, segments, analytics, and multi-provider sending via MCP.
Give spare Claude Code or Codex usage to open source. Your agent opens pull requests. No money.
Shinjuku Shield, private x402 payments on Solana: the self-custody wallet CLI and its MCP server. Shield, pay, and unshield USDC from any MCP agent, under caps you set.
Persistent local memory for MCP-compatible AI coding agents, stored per repository in SQLite.
Local-first, agent-native control plane for ComfyUI — MCP server + autonomous sidebar agent that drives your live graph in natural language on ANY LLM: Claude/ChatGPT/Gemini on your subscription (no A
Access control for AI agents. Set what Claude Code, Codex, Gemini, Cursor and any MCP server are allowed to do, review risky actions before they run, and keep every action on the record.
Set up PassionCode.ai on a computer with one command: the apps from their verified releases, their MCP servers for every coding agent and the PassionCode.ai skills. Check and repair it with the same c
Velaro MCP server — connect Claude and other AI agents directly to your Velaro account: KB, workflows, bots, conversations, contacts, routing, and more.
A Bun-native, drop-in command-compatible alternative to Microsoft playwright-cli for AI agents.
The shinjuku command: runs the Shinjuku Shield wallet (npm shinjuku-shield) at this exact version. Pay x402 URLs and AI answers privately from a shielded USDC balance on Solana.
Run your coding agent's commands on machines you own: a sandboxed job slot, not an SSH login.
Independent, unofficial CLI to create and edit CapCut projects — build drafts from scratch, add video/audio/text, subtitles, timing, speed, volume, templates, cut long-form to shorts. No API needed. N
Verified generative visualization for React and agents, with deterministic chart validation, repair, rendering evidence, and MCP.
Strict zod schemas + parsers for GGUI marketplace artifact manifests — ggui.gadget.json (gadget bundles) and ggui.blueprint.json (cached UI blueprints).
SocratiCode — MCP server for local codebase indexing, semantic search, and code dependency graphs. All private, all local via Docker.
In-app NativeScript devtools agent — exposes a running NS app's view tree + screenshots to the @gjsify/devtools-mcp bridge over the V8 CDP inspector (org.gjsify.Devtools method registry)
OAuth 2.1 authorization helper for TMCP with MCP specification compliance
GitHub security scanning, code audit, and workflow automation for repositories.
Commercial computer runtime connecting local coding agents to GrantTap on Mac, iPhone, iPad and Apple Watch.
Claude Code experience for the pi coding agent: reads your .claude config (rules, commands, skills, hooks, output styles, MCP servers, agents) and adds todo, checkpoints, memory, web, subagents, and g
Scan APIs for OWASP Top 10, LLM, and GraphQL security vulnerabilities.
Direktori lengkap
IDE, git, linting, dan analisis kode. 8,623 server, yang paling banyak dipakai lebih dulu. Masing-masing membuka halaman penerbit.