MCP server and CLI for automated GitHub PR management, review resolution, and workflow optimization
Software development, review and analysis.
MCP server and CLI for automated GitHub PR management, review resolution, and workflow optimization
120-module QA gate. Give Claude eyes (screenshots), ears (Sentry errors), and hands (verify fixes).
List the tools your AI agent can call, ranked by how dangerous they are, and which are unguarded.
Model Context Protocol (MCP) server that enables your MCP client (e.g., Claude Desktop, Cline, Roo Code, Cursor, Windsurf, etc.) to interact with GitHub repositories using your GitHub personal access token.
MCP Selenium WebDriver Server — AI-powered browser automation with hexagonal architecture. 66 tools for navigation, interaction, screenshots, assertions, cookies, tabs, HTTP API, recording, batch execution, and raw WebDriver access.
MCP server for an OpenAPI sports betting odds API for coding agents, with bookmaker comparison, arbitrage, positive EV, line movement, and mock mode tools.
Local structured analysis of deployed EVM runtime bytecode
Auth infrastructure for coding agents. User pools, secrets vault, token management. As easy as git.
Multi-language code graph memory system for LLMs
A knowledge graph of your codebase, exposed as an MCP server — so AI coding agents stop re-deriving structure from grep and Read on every request.
Local-first MCP memory and code intelligence that helps coding agents recall repo context, decisions, failures, and review impact.
DeepSeek Harness guardrail that limits how many files an AI coding agent can edit per turn
A plain-text documentation format with explicit brace scoping — deterministic parsing, AI-agent efficiency, and 10-50x token savings vs Markdown.
Context-aware code retrieval MCP server — ranked, gated results for AI coding agents
Travel platform for coding agents: hotels, tours, bookings, 13 AI experts. 21 tools, stdio.
Gives an AI agent a disposable email and a real UK phone number to test signup flows.
MCP server that gives AI agents (Claude, Cursor, Copilot) deep understanding of your codebase patterns, conventions, and architecture. Query patterns, security boundaries, call graphs in real-time.
Pi-Telegram: Bridge Telegram bots to pi coding agent via RPC
Reference implementation of veridelta/1 — proof-carrying verification deltas for coding-agent development loops
Common QA MCP — one product-neutral MCP that routes test-case lifecycle requests to Walnut or SimplifyQA for any AI client. Launch over stdio via npx; install the Walnut QA agent with `init-agents`.