Nils Durner's Blog Ahas, Breadcrumbs, Coding Epiphanies

OpenAI-based Chatbot interface updated

My Chatbot interface for OpenAI models (Live demo) has gotten a few improvements lately:

  • Tool-Use presentation:
    Screenshot: new presentation of tool-use instances
  • Support for MCP Servers (aka “Model Context Protocol)
    • registration to be done in mcp_registry.json, loosely follows the Visual Studio syntax
    • MCP Servers to be used can be selected/deselected like traditional tools
      Screenshot: MCP Server selection
    • Remote MCP Server integrations are handled from the OpenAI backend directly: example with the gitmcp MCP server for oai_chat:
      Screenshot: oai_chat with gitmcp
    • Local MCP Server integrations (stdio) are not routed through OpenAI, but are called locally. Web search with Exa:
      Screenshot: inquiry through Exa.ai
      (their remote MCP server appeared flaky recently, so I decided to make sure the MCP server run locally works)
    • (not available on HuggingFace live demo)
  • UnrestrictedPython: as an opposite to the RestrictedPython that allows the LLM to execute code in a sandbox, setting the environment variable CODE_EXEC_UNRESTRICTED_PYTHON=1 lifts the sandbox and allows arbitrary code execution. Know the risks.
  • Reasoning tokens are now fed back into reasoning models. OpenAI claim performance improvements that way, e.g. on SWE-bench of 3%
  • sets the OpenAI API token to use automatically if OPENAI_API_TOKEN is set
    • … either through the environment or .env

Philipp Schmidt, AI Developer Experience at Google DeepMind, recently announced his “Code Sandbox MCP”, a simple code interpreter for AI agents. This is based on the LLM Sandbox project. Either could be an avenue for future improvement.