Exposes local Python tools via a persistent Streamable HTTP endpoint, allowing an OpenAI Agents SDK notebook to discover and invoke them while using Groq for reasoning and tool selection.
Enables autonomous agents and multi-agent frameworks to discover and execute modular, class-based tools over SSE with a standardized response contract.
Enables agents to discover and securely invoke heterogeneous backend tools over unified SSE using JSON-RPC 2.0, with dynamic tool filtering, RBAC, quotas, and audit logging.
Exposes a local llama.cpp server's chat, completion, tokenization, model listing, and health endpoints as tools, enabling MCP hosts such as Claude Code to delegate prompts and text processing to a local model.