IDE、git、リント、コード解析。 8,507 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。
Multiplayer mode for AI coding agents. Your team's Claude Code, Codex and Cursor agents brainstorm and review together, share one master prompt and task board, and never edit each other's files.
Open-source command center for governed AI coding agents with built-in onboarding, hard gates, MCP, and shareable run receipts.
The Texuli MCP server for local agents: npx -y @texuli/mcp runs every Texuli operation over stdio.
OCX CLI - OpenCode extension manager with portable, isolated profiles. Your setup, anywhere.
Everything that runs on the sandbox origin: the MCP Apps sandbox relay and the in-frame runtime for shared state, comment anchors, and presence.
Latch MCP host — connect to MCP servers as tools, with a per-tenant SSRF allowlist and vault-brokered auth.
Cascading content protection engine — PII detection, secret scanning, prompt injection defense
MCP server for GolemUI dynamic forms: gives AI coding assistants schema validation and form generation for GolemUI form definitions. Open source (MIT).
Cross-harness communication and shared work-state for coding agents through MCP.
Work Orders and Work Reports for AI agents: a typed SDK, validator and lifecycle desk. The MCP server is in agent-work-layer-mcp.
InnerWarden Community: open-source guardrail for AI coding agents. Screens the shell commands and MCP/tool calls your agent runs and returns allow / review / deny, before it runs.
MCP server for Bide & Musique. Search the collection of forgotten French songs by performer or by title. No API key required.
Ask your coding agent for a video of your web app: promo clips, narrated tutorials, lessons and docs GIFs from a YAML storyboard.
React and Next.js bug report widget and hooks. One place to improve AI-built apps: fix bugs, smooth user journeys and clean up the code.
JWT bearer-token authorization for Toolgrain MCP servers.
Model Context Protocol server for FerrFleet: agents, runs, skills
MCP server for Toggl Track integration with time tracking and reporting
Zero-boilerplate, lightweight and fast MCP server toolkit. Skip the weight of `@modelcontextprotocol/sdk` and start shipping MCP servers in minutes with minimal code.
Clarx MCP server — score agent manifests, validate clarx-manifest.json, generate CI workflows, and (with a Clarx token) pull scan findings and remediation prompts into your IDE.
LSP-backed IDE intelligence plus concurrency-safe, transactional edits for AI coding agents.
Model Context Protocol implementation for TypeScript
Model Context Protocol implementation for TypeScript
Tells your coding agent what teammates' agents are changing in the repo, before it edits.
GraphQL MCP server for AI assistants
MCP server for CODESYS V3.5: read, write, compile and simulate Structured Text through a persistent CODESYS session
The TasKadence MCP server for clients that start a local process: a stdio proxy to the remote server (npx -y @taskadence/mcp).
Model Context Protocol server for Markdown Tidy (mdtidy.com) — tidy, convert, save, and share Markdown from any AI agent.
Order human-run real-device app tests from your coding agent; verified bugs return as fix prompts.
An MCP interface into the Bright Data toolset
The **Model Context Protocol (MCP) client** for the [AI SDK](https://ai-sdk.dev/docs) lets you connect to MCP servers and use their tools with AI SDK functions like `generateText` and `streamText`.
Cloud and zero-trust agentic workflow marketplace for skills, agents, rules, MCP references, and compliance-aware architecture.
Keeps an AI coding agent on its plan across context compression, with a live local dashboard.
A step auditor for matrix algebra, stochastics and algebra. Checks every step of a derivation, exactly, with counterexamples and fixes.
Shared memory, impact analysis, and guardrail hooks for AI coding agents — authored once, emitted as native config for Claude Code, Codex, Cursor, Gemini, Aider, and more.
MCP server that gives coding agents persistent project understanding via a knowledge graph
Scores your code across 12 areas, with findings, fix prompts, and re-assessment in your AI agent