Official Technical Resources: Anthropic (page 18)
Official Technical Resources · Anthropic: 269 entries in total; this page lists entries 256–269.
Connect to external tools with MCP
Configure MCP servers to extend your agent with external tools. Covers transport types, tool search for large tool sets, authentication, and error handling.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: Agent Identity, Authorization, and Secrets · Privacy and Data Compliance
Link last checked: 2026-09-24
Scale to many tools with tool search
Scale your agent to thousands of tools by discovering and loading only what's needed, on demand.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: Tool Calling · AI Agent
Link last checked: 2026-09-24
Subagents in the SDK
Define and invoke subagents to isolate context, run tasks in parallel, and apply specialized instructions in your Claude Agent SDK applications.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: AI Agent · Agent Memory
Link last checked: 2026-09-24
Modifying system prompts
Choose between the `claude_code` preset and a custom system prompt, and customize behavior with CLAUDE.md, output styles, append, or a fully custom prompt.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: Model Selection and Cost · Prompt Engineering
Link last checked: 2026-09-24
Extend agents with skills
Control which skills Claude can invoke in Claude Agent SDK sessions, dispatch commands by name, and author skills your sessions discover
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: Agent Identity, Authorization, and Secrets · Privacy and Data Compliance
Link last checked: 2026-09-24
Plugins in the SDK
Load custom plugins to extend Claude Code with skills, agents, hooks, and MCP servers through the Agent SDK
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: Tool Calling · AI Agent
Link last checked: 2026-09-24
Configure permissions
Control how your agent uses tools with permission modes, hooks, and declarative allow/deny rules.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: Agent Identity, Authorization, and Secrets · Privacy and Data Compliance
Link last checked: 2026-09-24
Intercept and control agent behavior with hooks
Intercept and customize agent behavior at key execution points with hooks
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: Tool Calling · AI Agent
Link last checked: 2026-09-24
Rewind file changes with checkpointing
Track file changes during agent sessions and restore files to any previous state
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: AI Agent · Agent Memory
Link last checked: 2026-09-24
Track cost and usage
Learn how to track token usage, estimate costs, and configure prompt caching with the Claude Agent SDK.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: LLM Inference Optimization · Model Evaluation and Benchmarks
Link last checked: 2026-09-24
Observability with OpenTelemetry
Export traces, metrics, and events from the Agent SDK to your observability backend using OpenTelemetry.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: LLM Inference Optimization · Model Evaluation and Benchmarks
Link last checked: 2026-09-24
Hosting the Agent SDK
Deploy the Agent SDK in production: subprocess architecture, session persistence, scaling, observability, and multi-tenant isolation for Docker, Kubernetes, and sandbox providers.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: Agent Identity, Authorization, and Secrets · Privacy and Data Compliance
Link last checked: 2026-09-24
Securely deploying AI agents
A guide to securing Claude Code and Agent SDK deployments with isolation, credential management, and network controls
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: AI Agent · Agent Memory
Link last checked: 2026-09-24
Legal and compliance
Legal agreements, compliance certifications, and security information for Claude Code.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Anthropic's own implementation and claims. Recheck the page status and version before use.
Related concepts: Agent Identity, Authorization, and Secrets · Privacy and Data Compliance
Link last checked: 2026-09-24