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.
Bounded Scala compiler, build, test, type, effect, symbol, and SemanticDB evidence for agents.
MCP server for the Weeek Public API: tasks, comments, attachments
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.
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
Generates MCP server code from OpenAPI specifications
Portable, governed, model-agnostic memory for AI agents: facts are invalidated rather than overwritten, raw text is the immutable source of truth, erasure on a governed handle runs through policy and
MCP server for Auxilo. Your agent stops solving the same problem twice: auto-extracted learnings, free self-unlocks, and earnings when other agents unlock yours.
Finds the Git commits that explain why code is the way it is: semantic and full-text history search.
Compiler-backed Angular template answers, component contracts and version facts for AI agents
Co-browse for coding agents: pick elements in the browser, write a note, Send — the context lands in the agent's chat. MCP server with 6 tools.
MCP server for AI agents: signed, verifiable Pulse Verity Index crypto prices and private API feedback
Japanese UI + UX correctness for AI coding agents — typography, forms, keigo, JLReq checks.
Audit-grade timestamped logs for every AI conversation
Per-SDK verdict matrix for signed A2A Agent Cards: which signatures verify in each SDK.
DeepSeek Harness bridge for the full local-shell-mcp tool surface and per-session Live Workspace.
Let AI coding agents (Claude Code, Codex, ...) message each other through a relay you host.
Official TypeScript SDK for the GunSpec.io firearms specification database API
Generative UI for Angular: a json-render renderer that streams AI-generated JSON specs into real Angular components with signals. Works with AG-UI agents and CopilotKit, MCP Apps and the Vercel AI SDK
Pair with a Steam Deck running the Decky Toolkit plugin, deploy Decky plugins and give coding agents the device's MCP tools over stdio.
Provides tools for searching Google Workspace documentation and much more.
Extended Google Contacts + People MCP server via gogcli — auth + Contacts + Workspace directory (People API)
No-KYC managed MCP for AI agents: sandboxed TypeScript trading SDK, isolated sub-accounts, futures.
Compiler-precise code property graph for C, Python, and TypeScript, navigable over MCP.
57 tools for AI-powered iOS Simulator automation — tap, swipe, type, screenshots, and more.
Index your codebase's domain knowledge. 20x fewer tokens, 10x faster.
Agent-friendly CLI and SDK for exploring and calling OpenAPI, GraphQL, and MCP APIs
Test generation, mocks, coverage analysis for AI agents
Serve open-computer-use and open-browser-use's own MCP tools to remote clients (pi, Claude Code, Codex), over Tailscale or SSH with a token and an app allowlist.
Toàn bộ thư mục
IDE, git, lint và phân tích mã. 8,505 máy chủ, dùng nhiều nhất xếp trước. Mỗi máy chủ mở ra trang của nhà phát hành.