Consult LLM

This MCP server enables AI assistants to consult more powerful language models (OpenAI's o3, Google's Gemini 2.5 Pro, and DeepSeek Reasoner) for complex problem-solving tasks that exceed the capabilities of the primary assistant. The implementation accepts markdown files as prompts along with relevant code files as context, optionally including git diff output to show uncommitted changes, then forwards the combined prompt to the specified model and returns the response with detailed cost tracking. It's particularly valuable for scenarios requiring advanced reasoning, code review, architecture decisions, or complex debugging where the primary assistant needs to escalate to more capable models, with comprehensive logging and support for multiple API providers through a unified interface.