Gives an LLM agent direct control of iOS and Android apps over one MCP interface, across simulators, emulators, and real devices. Reads the native accessibility tree to pick elements deterministically, using screenshot coordinates only as fallback.
Turns any GitHub repo into a remote MCP server, giving AI assistants live, searchable access to that project's docs and code so they stop hallucinating outdated APIs. No install: point your IDE at gitmcp.io/owner/repo.
Collects 40+ importable n8n workflows from the AI Agents A-Z YouTube channel, each tied to one video episode — spanning content generation, social-media posting, and short-video and narrated-story pipelines, plus companion Docker MCP/REST servers.
Lets an LLM read, search, and send your personal WhatsApp messages, contacts, and media through MCP. A Go bridge speaks to WhatsApp's web multidevice API and stores the full history in local SQLite, so data stays on your machine until a tool is invoked.
Open-source AI platform for knowledge workers: describe a multi-step task (reports, monitoring, workflows) and get back finished docs, dashboards, or apps from agents wired to your own data. Swap agents and LLMs freely; self-host anywhere.
Exposes enterprise databases to AI agents as vetted, query-restricted tools instead of raw connection strings. One MCP server fronts 20+ engines and centralizes connection pooling, IAM auth, and OpenTelemetry tracing, with prebuilt SQL tools.
Exposes a local MCP server that lets LLMs (e.g., Claude Desktop) query decompiled Android app context from a modified JADX GUI—supporting class/method retrieval, resources, xrefs, and debugger hooks for interactive reverse engineering workflows.
Lets AI assistants query market data and execute/manage trades on MetaTrader 5 using natural language. Implements the MCP bridge with multiple transports (stdio/SSE/HTTP), a WebSocket quote streamer, and local-credentials-first design for prototyping AI-driven trading integrations.
Turns natural-language requirements into a dependency-aware graph of atomic, testable dev tasks for AI coding agents. Adds cross-session memory and a plan-reflect loop that forces the agent to think through each step before writing code.
Official Go implementation of the Model Context Protocol for building MCP servers and clients. Tool handlers are type-safe, with JSON schemas inferred from Go structs via generics. Ships stdio, command, streamable-HTTP, SSE, and in-memory transports.
Exposes Pipedream Connect's 2,800+ APIs and 10,000+ pre-built actions to AI agents as MCP tools. OAuth stays server-side, so models act on a user's behalf without seeing their tokens. Ships HTTP/Streamable, SSE, and stdio transports.
Orchestrates a lead agent, isolated parallel sub-agents, long-term memory, and sandboxes for long-horizon tasks — minutes to hours of deep research, coding, and content creation. LangChain/LangGraph-based with extensible skills; v2 is a full rewrite.