MCP server
122.089 server dari registry resmi, GitHub, dan npm. Filter berdasarkan kategori, transport, dan bahasa.
122.089 server dari registry resmi, GitHub, dan npm. Filter berdasarkan kategori, transport, dan bahasa.
Tempel repo GitHub-nya dan kami akan mencantumkannya setelah review singkat.
Submit serverMCP server that gives AI coding assistants a dependency map of your codebase: impact analysis, a visual atlas, and live pulse.
Pi-agent wrapper around codebase-memory-mcp: derived code knowledge (call graphs, blast radius) over a harness-owned trust boundary
Scan codebases for LLM/AI SDK usage, exposed API tokens, and hardcoded secrets.
$claude mcp add ai-scanner-mcp -- npx -y ai-scanner-mcpAnalyze any codebase — get architecture, file roles, execution flows, and agent context.
$claude mcp add revibe-mcp -- npx -y revibe-mcp🧠 MCP server giving AI assistants (Gemini, Claude, Cursor, Windsurf, Copilot) deep codebase understanding — 10 tools + persistent memory. Install: npx @giauphan/codeatlas-mcp
🚀 Supercharge your AI agents! A cross-platform CLI & Model Context Protocol (MCP) server that parses full codebases into token-efficient, LLM-ready context files. Save tokens, reduce hallucinations, and give your AI the
代码库考古 MCP server:8 个只读工具(pickaxe / blame / 决策日志 / 改动热点),让 coding agent 能查代码的历史与决策
Local code intelligence that reads your entire codebase. Secrets stay on your machine, period.
MCP server that scans your codebase: TODOs, complexity, file stats, dependencies, health grade. Zero config.
Define software features as YAML blueprints. Extract patterns from any codebase, API docs, or document. Generate complete implementations for any framework. 16 production-ready blueprints included.
Persistent memory and codebase knowledge graph for AI coding assistants — delivered as a single MCP server.
$claude mcp add context-mcp -- npx -y context-mcp-serverClaude Code plugin that turns your own project into an ad-video campaign: it reads the codebase, interviews you briefly, then generates a fal.ai-ready workflow.json with chained scenes and consistent characters — no mode
Non-invasive MCP bridge that augments DevSpace grep/glob/ls results with codebase-memory context.
Tell a Next.js codebase's claims from its behaviour: Prisma models nothing queries, env vars nothing reads, locales that drifted. CLI + MCP server for coding agents. Zero dependencies.
Todo app built end to end by AI coding agents from Linear tickets, with automated tests, 4 GitHub Actions workflows and a custom MCP server that lets LLMs answer questions about the codebase.
One local map of your codebase for AI coding agents: session brief, blast radius, file-anchored memory that flags stale notes, cleanup leads. A local MCP server and CLI. No network, one dependency.