- MCP (Model Context Protocol) is a promising development for connecting tools in an LLM-agnostic way, but real-world support varies significantly among major providers.
- Anthropic (Claude) offers seamless MCP integration out of the box, but its API is expensive and token consumption can be high for simple use cases.
- OpenAI provides remote MCP support but the author encountered a 'Session terminated' error and could not get it working, indicating it needs more testing.
- Google Gemini's MCP support is limited to enumerating local tools in JavaScript and Python SDKs, lacking true remote implementation and requiring client-side heavy lifting.
- There is a market opportunity for a provider hosting open-weight models (like Qwen3 or GPT-OSS) to deliver a polished, integrated MCP experience on hosted API endpoints.