Docs search: tools / page 9 of 18 / Source Intelligence

onboarding Claude Developer Platform · in the page managed-agents/onboarding …by URL and authenticate your agent to take action on your behalf. * **Tools:** Extend your agent's capabilities using a pre-built agent toolset and MCP tools. * **Skills:** Attach Anthropic or custom…

permission-policies Claude Developer Platform · in the page managed-agents/permission-policies …ed-agents/permission-policies description: Control when agent and MCP tools execute. featureMetadata: topic: title: Managed Agents url: https://platform.claude.com/docs/en/managed-agents/ove…

reference Claude Developer Platform · in the page managed-agents/reference …sandboxes) only, your integration is responsible for providing `agent_toolset` results. The SDK helpers and CLI do this automatically. | </Tab> <Tab title="Agent events"> | Type…

spawn.sh: called once per claimed work item Claude Developer Platform · in the page managed-agents/self-hosted-sandboxes …r: managed-agents-2026-04-01 --- By default, Managed Agents executes tools and code inside [Anthropic-managed cloud sandboxes](https://platform.claude.com/docs/en/managed-agents/cloud-sandboxes-refer…

self-hosted-sandboxes-security Claude Developer Platform · in the page managed-agents/self-hosted-sandboxes-security …external hosts. Restrict outbound traffic to only the endpoints your tools require. * **Service key storage and rotation.** The environment service key (`ANTHROPIC_ENVIRONMENT_KEY`) authorizes pollin…

session-operations Claude Developer Platform · in the page managed-agents/session-operations …# Updating the agent configuration You can update a session's `agent.tools` and `agent.mcp_servers`, including permission policies and per-tool web settings such as [domain filters](https://platform.…

sessions Claude Developer Platform · in the page managed-agents/sessions …the agent's latest version). Then include any of `model`, `system`, `tools`, `mcp_servers`, or `skills` with the values the session should use. Each overridable field follows the same three rules:…

skills Claude Developer Platform · in the page managed-agents/skills …in the [Agent Skills](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview) overview. Skills reach your agent in two ways: attach them through the agent's `skills` array, or [l…

Or, for the Project Glasswing model with the same capabilities: Claude Developer Platform · in the page models/fable-5-1/migration-guide …led [Claude API skill](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/claude-api-skill#migrating-to-a-newer-claude-model). It works for any current Claude model as the target: ``…

whats-new-fable-5-1 Claude Developer Platform · in the page models/fable-5-1/whats-new-fable-5-1 …with [strict tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-tool-use), or move the schema to [structured outputs](https://platform.claude.com/docs/en/build-with-claude/…

introducing-claude-fable-5-and-claude-mythos-5 Claude Developer Platform · in the page models/fable-5/introducing-claude-fable-5-and-claude-mythos-5 …r) * The [memory tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool) * [Code execution](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool)…

Or, for the model with the same capabilities and no access approval requirement: Claude Developer Platform · in the page models/fable-5/migration-guide …led [Claude API skill](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/claude-api-skill#migrating-to-a-newer-claude-model). It works for any current Claude model as the target: ``…

From Haiku 3.5 Claude Developer Platform · in the page models/haiku-4-5/migration-guide …led [Claude API skill](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/claude-api-skill#migrating-to-a-newer-claude-model). It works for any current Claude model as the target: ``…

migration-guide Claude Developer Platform · in the page models/opus-5-5/migration-guide …led [Claude API skill](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/claude-api-skill#migrating-to-a-newer-claude-model). It works for any current Claude model as the target: ``…

whats-new-opus-5-5 Claude Developer Platform · in the page models/opus-5-5/whats-new-opus-5-5 …with [strict tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-tool-use), or move the schema to [structured outputs](https://platform.claude.com/docs/en/build-with-claude/…

migration-guide Claude Developer Platform · in the page models/sonnet-5-5/migration-guide …led [Claude API skill](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/claude-api-skill#migrating-to-a-newer-claude-model). It works for any current Claude model as the target: ``…

overview Claude Developer Platform · in the page models/sonnet-5-5/overview …ning on Claude Sonnet 5: * [Turn off up-front thinking with `between_tools`](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5#turn-off-up-front-thinking). * [Forced tool use…

whats-new-sonnet-5-5 Claude Developer Platform · in the page models/sonnet-5-5/whats-new-sonnet-5-5 …ning on Claude Sonnet 5: * [Turn off up-front thinking with `between_tools`](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5#turn-off-up-front-thinking). * [Forced tool use…

overview Claude Developer Platform · in the page release-notes/overview …ays. To turn off up-front thinking, send `thinking: {"type": "between_tools"}` instead of `"disabled"`, at `high` effort or below. Forced tool use (`tool_choice` types `any` and `tool`) returns a 400…

claude-fable-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-fable-5 …in Powerpoint (a slides agent). Claude Cowork can use all of these as tools. Claude's product knowledge ends here; it has no documentation access, details may have changed, and it doesn't give instru…

claude-fable-5-1 Claude Developer Platform · in the page release-notes/system-prompts/claude-fable-5-1 …in Powerpoint (a slides agent). Claude Cowork can use all of these as tools. Claude is also accessible via Claude Tag, a Slack-based "multiplayer" interface that allows anyone to tag @Claude in and de…

claude-opus-4-7 Claude Developer Platform · in the page release-notes/system-prompts/claude-opus-4-7 …in Powerpoint - a slides agent. Claude Cowork can use all of these as tools. Claude does not know further details about Anthropic's products or their capabilities, as it does not have access to their…

claude-opus-4-8 Claude Developer Platform · in the page release-notes/system-prompts/claude-opus-4-8 …in Powerpoint (a slides agent). Claude Cowork can use all of these as tools. Claude is also available in Claude Design, an interface with a canvas and design tools that Claude can use to make things i…

claude-opus-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-opus-5 …in Powerpoint (a slides agent). Claude Cowork can use all of these as tools. Claude is also accessible via Claude Tag, a Slack-based "multiplayer" interface that allows anyone to tag @Claude in and de…

claude-opus-5-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-opus-5-5 …in Powerpoint (a slides agent). Claude Cowork can use all of these as tools. Claude is also accessible via Claude Tag, a Slack-based "multiplayer" interface that allows anyone to tag @Claude in and de…

claude-sonnet-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-sonnet-5 …in Powerpoint (a slides agent). Claude Cowork can use all of these as tools. Claude's product knowledge ends here; it has no documentation access, details may have changed, and it doesn't give instru…

claude-sonnet-5-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-sonnet-5-5 …in Powerpoint (a slides agent). Claude Cowork can use all of these as tools. Claude is also accessible via Claude Tag, a Slack-based "multiplayer" interface that allows anyone to tag @Claude in and de…

increase-consistency Claude Developer Platform · in the page test-and-evaluate/strengthen-guardrails/increase-consistency …n data analytics and visualization. Offers intuitive, self-service BI tools with a freemium model, appealing to startups and enterprise teams alike.</overview> <swot> <strengths> - U…

mitigate-jailbreaks Claude Developer Platform · in the page test-and-evaluate/strengthen-guardrails/mitigate-jailbreaks …ee [Handle tool calls](https://platform.claude.com/docs/en/agents-and-tools/tool-use/handle-tool-calls) for the `tool_result` format. * **Tell Claude what the content is and where it came from.** In…

Set up Claude Code for your organization Claude Code CLI · in the page admin-setup …anagement (MDM) system, or a file on disk. The settings control which tools, commands, servers, and network destinations Claude can reach. This page walks through the deployment decisions in order. E…

Escalate hard decisions with the advisor tool Claude Code CLI · in the page advisor …ure as a [server tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool), available to both subscription and API-billed accounts. You choose which model acts as the advisor,…

How the agent loop works Claude Code CLI · in the page agent-sdk/agent-loop …SDK is a standalone package that gives you programmatic control over tools, permissions, cost limits, and output. Both the TypeScript and Python SDKs bundle a native Claude Code binary, so most inst…

Use Claude Code features in the SDK Claude Code CLI · in the page agent-sdk/claude-code-features …setting_sources=["user", "project"], allowed_tools=["Read", "Edit", "Bash"], ), ): if isinstance(message, AssistantMessage): for block…

Configure your agent Claude Code CLI · in the page agent-sdk/configuration …ere the spellings differ: * **`model`**: picks the model * **`allowedTools` / `allowed_tools`**: pre-approves a read-only tool list * **`maxTurns` / `max_turns`**: caps the turn count * **`cwd`**: se…

Track cost and usage Claude Code CLI · in the page agent-sdk/cost-tracking …tion. A single call can involve multiple steps: Claude responds, uses tools, gets results, and responds again. Each call produces one [`result`](/docs/en/agent-sdk/typescript#sdkresultmessage) message…

Rewind file changes with checkpointing Claude Code CLI · in the page agent-sdk/file-checkpointing …kpointing tracks file modifications made through the [Write](/docs/en/tools-reference#write-tool-behavior), [Edit](/docs/en/tools-reference#edit-tool-behavior), and [NotebookEdit](/docs/en/tools-refer…

Intercept and control agent behavior with hooks Claude Code CLI · in the page agent-sdk/hooks …e|Edit"` matcher (step 3) so the callback only fires for file-writing tools. When triggered, the callback receives the tool's input (step 4), checks if the file path targets a `.env` file, and returns…

Hosting the Agent SDK Claude Code CLI · in the page agent-sdk/hosting …If your agents use [MCP servers](/docs/en/agent-sdk/mcp) or external tools, they need outbound access to those endpoints as well. For production, route outbound traffic through an egress proxy that e…

Migrate to Claude Agent SDK Claude Code CLI · in the page agent-sdk/migration-guide …t-sdk/python) for Python-specific documentation * Learn about [Custom Tools](/docs/en/agent-sdk/custom-tools) and [MCP Integration](/docs/en/agent-sdk/mcp)

Modifying system prompts Claude Code CLI · in the page agent-sdk/modifying-system-prompts …style. Start from the `claude_code` preset for CLI or IDE-like coding tools where a human watches and steers the work. Write your own prompt for agents with a different surface, identity, or permissio…

Observability with OpenTelemetry Claude Code CLI · in the page agent-sdk/observability …gents in production, you need visibility into what they did: * which tools they called * how long each model request took * how many tokens were spent * where failures occurred The Agent SDK can exp…

Agent SDK overview Claude Code CLI · in the page agent-sdk/overview …plication that completes a task by planning its own steps and calling tools that read files, run commands, or edit code. The Agent SDK gives you the same tools, [agent loop](/docs/en/agent-sdk/agent-l…

Configure permissions Claude Code CLI · in the page agent-sdk/permissions # Configure permissions > Control how your agent uses tools with permission modes, hooks, and declarative allow/deny rules. The Claude Agent SDK provides permission controls to manage how Claude use…

Quickstart Claude Code CLI · in the page agent-sdk/quickstart …u find.", options=ClaudeAgentOptions( allowed_tools=["Read", "Edit", "Glob"], # Auto-approve these tools permission_mode="acceptEdits", # Auto-approve file edit…

Securely deploying AI agents Claude Code CLI · in the page agent-sdk/secure-deployment …ike traditional software that follows predetermined code paths, these tools generate their actions dynamically based on context and goals. This flexibility is what makes them useful, but it also means…

Work with sessions Claude Code CLI · in the page agent-sdk/sessions …async def main(): options = ClaudeAgentOptions( allowed_tools=["Read", "Edit", "Glob", "Grep"], ) async with ClaudeSDKClient(options=options) as client: # First query: c…

Extend agents with skills Claude Code CLI · in the page agent-sdk/skills …Agent Skills overview](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview). ## How skills work with the Agent SDK When using the Claude Agent SDK, skills are: * **Defined as…