Built-in tools

You can build your own custom tools, but some capabilities are common enough that Anthropic ships them pre-built. You don't write the code. You don't host the sandbox. You just declare the tool, and Anthropic runs it.

Server tools: declared by you, run by Anthropic

Anthropic provides server tools that run on their infrastructure. You don't execute these — Anthropic does. That means you don't need an agent loop for these calls. Claude calls the tools on its own, and the result comes back inside the same response.

The main ones are:

• Web search — searches the internet and returns results with citations
• Code execution — writes and runs Python in a sandbox
• Web fetch — retrieves full content from URLs

Two server tools in one file

Let's check out some of the big ones in one file: two messages.create calls, one with web search and one with code execution.

import anthropic

client = anthropic.Anthropic()

# Call 1: web search — Anthropic runs the search server-side
search_response = client.messages.create(
    model="claude-opus-5",
    max_tokens=1024,
    tools=[{"type": "web_search_20260209", "name": "web_search"}],
    messages=[
        {"role": "user", "content": "What is Anthropic's latest model release? Answer in one sentence."}
    ],
)

for block in search_response.content:
    if block.type == "server_tool_use":
        print(f"Tool call: {block.name} — {block.input}")
    elif block.type == "text":
        print(block.text)

# Call 2: code execution — Claude writes and runs Python in a sandbox
code_response = client.messages.create(
    model="claude-opus-5",
    max_tokens=1024,
    tools=[{"type": "code_execution_20260120", "name": "code_execution"}],
    messages=[
        {"role": "user", "content": "Calculate the mean and standard deviation of [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]"}
    ],
)

for block in code_response.content:
    if block.type == "server_tool_use":
        print(f"Tool call: {block.name} — {block.input}")
    elif block.type == "bash_code_execution_tool_result":
        print(f"stdout: {block.content.stdout}")
    elif block.type == "text":
        print(block.text)

Two things to notice:

1. There's no agent loop here. We don't switch on stop_reason. We don't push tool results back. Anthropic runs the tool server-side, and the response already contains the result.