Stdio MCP server for safe-db: inspect schema and run a gated SELECT.
Durable project memory as markdown pages on disk, searchable without a server
wim: real-time, end-to-end encrypted messaging between AI agent sessions across machines and accounts
ReviewTrace MCP server - record and recall code review knowledge from Claude Code, Codex, and other coding agents
Production errors your coding agent can read: search, stack traces, context, trends, resolve.
Model Context Protocol server exposing Airlock gateway tools (stdio)
Auto-starting stdio MCP server that bridges Claude Code to Unreal Engine editors via UE's Python Remote Execution. Launcher per session; singleton HTTP daemon fans in to share the UE connection.
Local supply-chain CVE scanner via OSV/NVD. Scans deps and IDE extensions. No upload.
MCP server for stealth browser automation via Camoufox — 104 tools, Chrome DevTools MCP-level power with anti-bot stealth
Read-only MCP server exposing the Matos UI registry and design-system knowledge (Surface Philosophy, Motion Tokens) to AI coding agents.
A paid remote MCP for AI SDK data query MCP, built to return verdicts, receipts, usage logs, and aud
OneHome (CoreLogic) MCP server for Claude — developed and maintained by AI (Claude Code)
MCP server: filesystem, shell diagnostics, Microsoft Graph (stdio, no API key — use env + optional per-call graph token).
MCP server that parses JS/TS source into an AST using a selectable parser (babel, acorn, typescript, espree, @typescript-eslint/parser) — astexplorer.net as an MCP tool.
Enterprise debugging for Node.js/TypeScript with 25+ tools: breakpoints, profiling, hang detection
MCP server for beckon — drive local tunnels from an AI coding agent
A paid remote MCP for AI SDK benchmark dashboard, built to return verdicts, receipts, usage logs, an
Lightweight coordination layer for multiple AI agents working on the same codebase simultaneously.
Local Git via MCP: status, log, diff, file history, branches, and gated stage/commit. Pure-JS.
MCP server that helps AI agents explore OpenAPI specs, search endpoints, and generate TypeScript types.
Give your AI coding agent the real numbers behind any web page: sizes, spacing, type, colors and the animation timings a screenshot can't carry. Bridges the Design Toolkit browser extension to Claude
A paid remote MCP for AI SDK eval dashboard, built to return verdicts, receipts, usage logs, and aud
A living architecture map for any codebase, any language, any coding agent. See what every change does to the structure, and stop it crossing the lines you drew.
A paid remote MCP for AI SDK MCP gateway registry, built to return verdicts, receipts, usage logs, a
The Frontshelf CLI: technical SEO audits for humans and their coding agents.
Model Context Protocol implementation for TypeScript
Bounded Scala compiler, build, test, type, effect, symbol, and SemanticDB evidence for agents.
MCP server for the Weeek Public API: tasks, comments, attachments
Turn any GraphQL API into MCP tools. Zero config, zero code.
Turn any OpenAPI/Swagger spec into MCP tools. Zero config, zero code.
The best prompt and the best model for the job, tested and improved by your coding agent.
Practice library for coding agents: skill search/invoke, seed patches, scout, reflect, ADR writer
Persistent, structured project memory for AI coding agents, stored locally in SQLite.
Project-scoped CodeGraph for DeepSeek Harness: launches codegraph's MCP server through npx, shares one instance per project root across sessions, selects the global codegraph version, and injects its
Paid remote MCP for agent code search routing MCP, structured receipts, audit logs, and reviewer-rea
Author-side conformance, safety & spec-migration linter for MCP (Model Context Protocol) servers — eslint for your MCP server. Checks tool annotations, schema hygiene, tool-poisoning/injection pattern
Direktori lengkap
IDE, git, linting, dan analisis kode. 8,620 server, yang paling banyak dipakai lebih dulu. Masing-masing membuka halaman penerbit.