Claim◆Article
LLM now supports server-side tools from multiple providers, including OpenAI's CodeInterpreter and WebSearch, and Anthropic's WebSearch, WebFetch, CodeExecution, and MCP integration.
Server-side tools like code execution and web search are now invocable directly from LLM prompts across OpenAI and Anthropic providers, including Anthropic MCP calls against remote servers. ✦ AI generated
Simon Willison · Simon Willison's Weblog · 2026-08-04 · original ↗
LLM calls can now use server-side tools from various providers. OpenAI provide a code execution environment as a server-side tool; LLM can now run prompts that benefit from that like so: llm --tool CodeInterpreter 'Show current python and SQLite versions' OpenAI also gets a WebSearch tool. The llm-anthropic plugin adds WebSearch, WebFetch, CodeExecution, and AnthropicMCP, which looks like this: llm -m claude-sonnet-5 -T 'AnthropicMCP("https://datasette.simonwillison.net/-/mcp")' \ 'how many rows in the blog_blogmark table?' That causes Anthropic to execute MCP calls against my new datasette-mcp plugin as part of a single request/response interaction with their API.
Read full article ↗excerpt · fair-use quotation
- ·LLM 调用可使用来自多家提供商的服务端工具
- ·OpenAI 提供 CodeInterpreter 代码执行环境
- ·OpenAI 还提供 WebSearch 网络搜索工具
- ·Anthropic 插件新增 WebSearch、WebFetch 等多种工具
- ·AnthropicMCP 工具支持远程服务器调用
- ·可在一个请求响应交互中执行 MCP 调用
- ·示例：通过 MCP 查询远程数据集
- ·扩展了 LLM 的能力边界
Around this claim
This moment responds to
gives example → LLM is evolving into an agent framework, driven by Datasette Agent's needs, with tool chains that can pause for human approval and resume from stored message history — and the agent concept may be baked into the core library next.Simon Willison · Simon Willison's Weblogextends → Server-side tools for WebSearch, WebFetch, CodeExecution, and AnthropicMCP are now available through LLM's -T interface or Python tools=, replacing the previous -o web_search* options.llm-anthropic maintainer · Simon Willison's Weblog