Anthropic computer use

Computer use

Anthropic computer use is a client-side toolset in the Claude API that lets a model see a desktop through screenshots and act with mouse and keyboard calls. The application that sends the request runs every action in an environment it controls, such as a container or virtual machine, and returns the result. Anthropic publishes a reference implementation with a Dockerfile, an agent loop and a web interface in its claude-quickstarts repository.

One tool entry declares the whole toolset; earlier tool versions need beta headers. Anthropic recommends a dedicated virtual machine or container with minimal privileges.

Pinout

  • MCP server: not checked yet
  • HTTP API: supported, verified
  • command line: supported, verified
  • Python SDK: supported, verified
  • TypeScript SDK: supported, verified
  • OpenAPI description: not checked yet
Where each pin comes from
InterfaceStatusSource we readRead on
MCP serverNot checked yet——
HTTP APISupported, verifiedComputer use tool, API usage (tool_use blocks)
Command lineSupported, verifiedComputer use tool, quick start (ant messages create)
Python SDKSupported, verifiedComputer use tool, SDKs (Python toolset class, beta)
TypeScript SDKSupported, verifiedComputer use tool, SDKs (TypeScript toolset class, beta)
OpenAPI descriptionNot checked yet——

Facts

Facts about Anthropic computer use
Tool typecomputer_toolset_20260801; the page says the request needs no beta header. Computer use tool, API usage, read .
Member actions17 member tools, including screenshot, zoom, clicks, drag, scroll, type and key. Computer use tool, toolset members, read .
SDKs and CLIPython and TypeScript SDKs include a computer toolset class (beta); the quick start also shows an ant messages create command. Computer use tool, SDKs and quick start, read .
Reference implementationanthropics/claude-quickstarts, folder computer-use-demo: Dockerfile, tool implementations, agent loop and web interface. Computer use tool, reference implementation, read .
Reference implementation licenseMIT. claude-quickstarts repository, license, read .
PlatformsClaude API, Amazon Bedrock, Claude Platform on AWS, Claude Models on Google Cloud, Microsoft Foundry. Computer use tool, platform availability, read .
PricingBilled under standard tool use pricing in USD; declaring the toolset adds about 4,500 input tokens to a request. Pricing page, computer use section, read .
Last commit. GitHub API, latest commit on the default branch of anthropics/claude-quickstarts, read .

Call example

client = anthropic.Anthropic()

response = client.messages.create(
    model="claude-opus-5-5",
    max_tokens=1024,
    tools=[
        {"type": "computer_toolset_20260801"},
        {"type": "text_editor_20250728", "name": "str_replace_based_edit_tool"},
        {"type": "bash_20250124", "name": "bash"},
    ],
    messages=[{"role": "user", "content": "Save a picture of a cat to my desktop."}],
)
print(response)

Limits

  • The page states the toolset is not currently available in Claude Managed Agents.
  • Every action runs in an environment the developer operates; the page recommends a dedicated virtual machine or container.
  • Long agent loops accumulate screenshots as input tokens.

Strengths

  • A single tool entry declares all member actions.
  • A reference container implementation is published under the MIT license.
  • The toolset is offered on several cloud platforms besides the Claude API.

Pricing

PricingBilled under standard tool use pricing in USD; declaring the toolset adds about 4,500 input tokens to a requestPricing page, computer use section, read 16 Nov 2026

As written on Anthropic computer use's own page on the read date. Prices change: check there before you pay.

Alternatives to Anthropic computer use

All computer use tools for agents
  1. MCP server that lets AI agents operate Windows applications.

    Computer use
  2. Open-source drivers and sandboxes that let AI agents use computers.

    Computer use
  3. Gemini API tool where the model reads screenshots and returns UI actions.

    Computer use
  4. Simular's open-source framework for computer-use agents, plus a hosted API.

    Computer use

Last check: . Method: public repository and docs read automatically, page and day written down. Next check due within 90 days. How we check

Is this your tool? Write to hello@agent-tools.directory from an address on its domain to correct a pin or a fact.