IDE、git、リント、コード解析。 8,526 件のサーバーを利用の多い順に掲載しています。それぞれ公開元のページが開きます。
Ask a human before your MCP tool does something irreversible — elicitation on both protocol revisions, with a two-call confirmation token for clients that cannot be asked
Hosted long-term memory for AI agents over MCP. Write and read memories from Claude Code, Cursor, VS Code and ChatGPT; rating a recalled memory as helpful or misleading re-ranks what comes back next.
Rockhopper MCP server — expose file metadata, versions, reviews, and comments to AI tools
Python SDK MCP server: offline catalog + 2,752 precomputed A-share/HK/US metrics for AI agents.
AgentRQ workspace client — drive an AgentRQ workspace from the command line, using the workspace's own .mcp.json
전자정부 표준프레임워크(eGovFrame) 프로젝트·CRUD 스캐폴딩과 검증된 공통컴포넌트 완전 조립 MCP 서버
MCP server for JLC/EasyEDA component sourcing, library fetching, and conversion to KiCad format
One command. Every AI tool understands your project instantly.
MCP server for Babelize: let AI coding agents analyze, translate, check and review your app with the local Babelize engine. mcprush.com-363ba77d1f63a2f91edcef68
A Model Context Protocol (MCP) server that provides search and crawl functionality using Search1API
Mechanically validated frontend aesthetics for coding agents: an evidence-ranked palette library, OKLCH harmony generation, WCAG 2.2 + APCA contrast gates, color-blind simulation and AI-slop detection
Local MCP bridge for maind.dev — wraps any MCP-compatible client (Claude Code, Cursor, Devin Desktop, formerly Windsurf) and pins your API key to a single device via the maind device authorization flo
Give coding agents real eyes: one tool call returns a screenshot PNG plus the accessibility tree and page text; segment_height paginates long pages into readable tiles.
Access any API via its OpenAPI specification, with full JSON Schema support for parameters and request bodies.
TypeScript SDK for Ratel — context engineering platform for AI agents. BM25 tool retrieval, MCP ingestion, framework-neutral capability tools.
Document exchange for coding agents across services: versioned Markdown store, pub-sub notifications with structured diffs and lifecycle stage tracking.
Coordinate parallel coding agents: TTL file claims across git worktrees, hooks blocking colliding edits, presence, handoff notes and searchable lessons.
Working MCP server for Groove HQ, updated for the current API and tested against a live account: search and read tickets, send email replies, add notes, and manage contacts.
Local daemon that pre-indexes a codebase into a SQLite catalog and serves AST-compressed snapshots on every query to reduce token usage.
Drive Suresoft COVER EE from a coding agent: coverage builds, coverage lookup, toolchain recovery.
Couple this computer to WorkTrust: approve a code in your browser, and every AI app here reports what you built. Metadata only, no dependencies.
CLI and MCP server: send files and text between a terminal or an AI agent and your own phone or computer. Paired once, end-to-end encrypted, direct between the devices.
One seat for all your projects and tasks: a local record of what is done, what is next and when it ships - read by you and your coding assistant
WebMCP plugin for FrontMCP - expose an in-browser FrontMCP server's tools to browser agents through document.modelContext
MCP server for Cursor, Claude Code and Copilot. One place to improve AI-built apps: fix bugs, smooth user journeys and clean up the code.
MCP server providing access to the Flightradar24 API for real-time and historical flight data
Local-first memory layer and protocol for AI coding agents. Markdown source of truth, SQLite FTS5 index, zero cloud.
Lighthouse-style CLI for auditing websites for AI agents, LLM crawlers, MCP clients, llms.txt, WebMCP, OpenAPI, and Schema.org readiness
MCP Server for enhance IntelliJ IDEA abilities
Prebuilt Levelrail CLI binary for linux/amd64. Installed automatically by levelrail-cli, do not install directly.
Checks what local coding agents such as Claude Code, Codex and Cursor really did: files changed, commands run and test results read from test output, not the agent's word. Read-only.
Model Context Protocol server for Excalidraw diagrams.
Runtime and skill library for coding agents: C4 workflow gates, guarded command execution and reasoning engines like Tree of Thoughts and 5 Whys.
Local full-text search over zsh, bash and fish history, with secret redaction and optional capture of cwd, exit code and duration.
Relay that lets AI agents call the MCP tools of a web page open in a browser tab
MCP server for OpenRouter — 21 tools: chat with 300+ LLMs, analyze & generate images/audio/video, TTS/STT, embeddings, reranking, structured decisions, async completions, response caching