MCP server for interacting with CodeRabbit AI reviews on GitHub pull requests. Enables LLMs to analyze, implement, and resolve CodeRabbit suggestions programmatically.
Checker-resolved architecture graph over MCP for coding agents, backed by ttsc's in-process TypeScript-Go compiler.
Search and read the Flowie Exchange API docs and OpenAPI contract. No sign-in needed.
Windows terminal sessions for agents: spawn, type, wait without polling, lean reads, screenshots.
The FrontMCP CLI: create, run, test and build MCP servers, and install FrontMCP skills for coding agents
Shows coding agents which .env file each variable comes from, and which variables are missing or invalid for each mode, without exposing secret values.
Test, debug, and validate MCP servers — health checks, OAuth conformance, tool-surface diffing, and structured triage from the terminal or CI
AI Agent Network CLI — Local-first multi-agent orchestration across 6 runtimes (Claude Code CLI / Claude Agent SDK / Codex SDK / Codex app-server / Grok Build ACP / OpenCode CLI) and 8+ LLM providers.
TypeScript SDK for the MCP Registry API — includes types, a ready-to-use client, and deterministic fingerprint computation for enterprise allowlist enforcement.
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
CLI for the Coinbase Developer Platform API
A set of Sass variables, mixins, and functions for generating palettes, typography, and elevations used by Ignite UI components.
MCP server for the Tech-Lead Stack: agent skills and workflows for tech leads, PMs and HR.
SDK for building OAuth-protected Remote MCP servers on Cloudflare Workers with pluggable auth adapters (Supabase already implemented).
High-performance job queue for Bun and AI agents. Memory or one-file SQLite, optional PostgreSQL 15–18 multi-broker persistence, cron, retries, DLQ, and MCP.
Model Context Protocol server providing Taiga UI documentation search and scaffolding tools.
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.
Generic MCP stdio proxy that offloads large tools/call results to an artifact store (memory by default) and returns small previews + retrieval tool.
TypeScript framework for building MCP servers: tools, resources and prompts as decorated classes, with transports, sessions, auth and dependency injection
MCP server for the Vorlek API — email tools, catalog discovery, and operation lookup across SendGrid, Mailchimp, and Klaviyo.
mu: most of what a coding agent decides isn't code. mu hands 41 kinds of yes/no calls to a small judge model: fewer wasted tokens, fewer approvals on autopilot, fewer runs that stop halfway. Built on
Model Context Protocol (MCP) server exposing BetterKey vehicle data and commands to AI agents.
XSUAA / OAuth authentication + BTP principal propagation for Model Context Protocol (MCP) servers built on Express and @modelcontextprotocol/sdk.
StoryShelf MCP server: let AI agents read builds, diffs and AI insights, and comment on reviews.
MCP server for Hostinger API
The asks.world MCP server (https://asks.world): people and AI agents post paid tasks; a verifier checks each answer against the requirements, and approval pays. Read the board, answer asks and post yo
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.
MCP server exposing full Chrome DevTools Protocol debugging: breakpoints, stepping, call stacks, eval, and source maps. Also supports tab control, JS execution, screenshots, and network monitoring.
Project-scoped MCP server for Jira — issues, comments, sprints, transitions and attachments over the Jira REST API, narrowed to a single project instead of everything the account can access
MCP server for x64dbg debugger - 23 mega-tools for AI-powered reverse engineering and debugging
gu: the coding agent in your terminal. It reads your repo, makes the change and runs the tests, with your own models (Ollama or any OpenAI-compatible provider). Free installs keep the agent, its API a
Security linter for MCP JSON-RPC messages — detects nested field injection, validates receipt structure, zero dependencies
Local, version-locked documentation packages for AI agents, indexed in SQLite and served over MCP.
Build AI agents on the Openhex platform. Programmable agent loop, tools, hooks, sessions, MCP, and an embeddable React chat UI — the same runtime that powers Openhex agents, as a library.
MCP-native, model-agnostic control for agents over one tool surface. Eight engines in three families: five browsers including real Safari and Chrome on an Android device, native apps on an Android emu
Structured typecheck, lint and format diagnostics, script guidance and dependency upgrade advice for coding agents, in any Node repo.
Annuaire complet
IDE, git, linting et analyse de code. 8,793 serveurs, les plus utilisés en premier. Chacun ouvre la page de l'éditeur.