IDE, git, 린트, 코드 분석. 서버 8,489개를 사용량이 많은 순으로 보여 줍니다. 각 항목은 게시자의 페이지로 연결됩니다.
Canonical types, formatters, and search client for the Dexter x402 ecosystem. Shared by all MCP servers, the SDK, and the ChatGPT widget.
MCP server for Databrain embedded analytics - connect databases, create datamarts, configure embeds, and generate frontend code
Self-hosted, governed MCP gateway for AI data access: policy enforcement, PII masking, a signed receipt per access once a receipt sink is configured (conarium-init sets one), and coverage reconciliati
MCP server that lets AI agents inspect your own PC and Android device read-only with osquery, ClamAV, Wazuh and adb (runs the Python server; needs Python 3.11+)
Khala channels for Claude Code, Codex and Cursor sessions: the khala MCP server, delivery hooks and local channels.
Enterpret's fork of onlyflowstech/servicenow-mcp. 17 tools over the ServiceNow Table API; adds a SERVICENOW_OAUTH_BEARER env mode so a broker-supplied (Nango) OAuth token is used for auth.
Web UI for browsing and managing Claude Code marketplace plugins
Experimental: MCP interceptor server (SEP-2624 draft) that labels tool results and checks tool calls with ADTL trust labels
MCPScraper CLI: live web pages as clean Markdown, text or HTML in your terminal, through the MCPScraper API. The commands follow the live API spec.
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.
MCP server for crawling and indexing web documentation - works with any website
Local-first AI coding CLI with embedded model router, multi-agent orchestration, and codebase indexing
Measure the per-turn token cost of AI coding-agent instruction files (AGENTS.md, CLAUDE.md, Cursor, Copilot, Cline, Roo, Kiro, Windsurf and more) for every agent that reads them.
Origin MCP server (stdio): search, timeline, sources, and remember/correct/forget for any MCP-capable agent.
Impressão digital da superfície de um servidor MCP: initialize (instructions + capabilities) + tools/resources/prompts + quem responde sem token, travados ao lado da versão — mudou sem subir a versão
Stay sharp while your AI does the work — learn what you don't know yet from the tasks your agent completes, with in-context coaching, all local, all free
Audit an MCP server and get a scored, actionable quality report in seconds. Node wrapper for the Python mcpscore CLI.
MCP server for the EngrAmo spaced-repetition flashcard platform
Gym Master in your terminal: chat with Gym Master AI on your workspace data, call the API, manage keys and webhooks
Motif revenue attribution: one init in the browser with region-aware consent, identify users, send signups from your backend with one idempotent call, backfill past signups from a CSV, add the tracker
MCP server for the Hetzner Cloud API — manage servers, networks, volumes, and more
Free A2A services and Envar account-balance seller gates
Mule MCP Server for Cursor and Windsurf IDE integration
Struct AI CLI
The hub where your AI agents connect. Multi-terminal Claude Code agent communication via MCP.
Local artifact exchange for heterogeneous LLM agents via HTTP and MCP.
Official CLI & MCP bridge for Veynod — a shared blackboard and MCP control plane for multi-agent teams.
Tapline host: lets AI agents see and drive your own React Native / Expo app on a test phone on the same Wi-Fi (MCP server and CLI).
agentproto/mcp-runtime — AIP-32 MCP provider specialisation. Sugar over @agentproto/driver for Model Context Protocol servers (stdio/SSE/HTTP transports). v0.1 ships frontmatter-driven dispatch; full
Open-source CLI, MCP, skills, templates, workflows, recipes, and evals layer for giving AI agents reliable access to protected web data through Zenrows cloud infrastructure.
Reference agent that consumes the Knowledge Context Protocol end-to-end — a deterministic, fail-closed navigation planner plus optional LLM synthesis.
Myrmo SDK: shared memory of solved errors for AI agents. Look up fixes other agents already found for an error, report what worked, and publish the hard ones.
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
Visual feedback as agent work packets. Stakeholders drop pins on your live app; your AI coding agent reads each pin (selector, screenshot, DOM, thread, acceptance criteria) via MCP and ships the fix.
MCP proxy that checks each routed tools/call against your rules before forwarding it, and signs a record. Open source (Apache-2.0).
Knowledge base of markdown records with standing, supersession and trace: library, CLI, and MCP server over one command set