Consult7 is a Model Context Protocol (MCP) server that enables AI agents to consult large context window models via OpenRouter for analyzing extensive file collections—entire codebases, document repositories, or mixed content that exceed the agent's local context limits. It collects files from the specified absolute paths (with optional wildcards in filenames), assembles them into a single context, and sends them to a chosen model with your query. The model's response is then fed back directly to the agent. Consult7 supports a wide range of OpenRouter models (500+ models) and dynamic context windows, including flagship Gemini 3 Pro with up to 1M tokens and other models like Gemini 2.5 Pro/Flash, Claude Sonnet, Claude Opus, Grok, etc. It provides three performance modes—fast, mid, and think—to balance speed and reasoning. Optional output_file allows saving the result to disk and returns a concise message. It includes a CLI and Python API, usage examples, and mnemonics to reference model+mode combos, with automatic file ignore rules and size limits based on model context windows.