apicheats.dev Cheat sheet Raw .md
POST

Try POST /v1/agents — Claude API

Claude playground

Create Agent

Credentials

Kept in this tab only. Requests go through apicheats.dev's same-origin proxy straight to api.anthropic.com; the proxy stores and logs nothing about them.

Headers

Body application/json

9 body fields
  • name · required · string — Human-readable name for the agent.
  • model · required · string — Model identifier. Accepts the [model string](https://platform.claude.com/docs/en/about-claude/models/overview#latest-models-comparison), e.g. `claude-opus-5`, or a `model_config` object for additional configuration control
  • description · optional · string — Description of what the agent does.
  • system · optional · string — System prompt for the agent.
  • tools · optional · object[] — Tool configurations available to the agent. Maximum of 128 tools across all toolsets allowed.
  • mcp_servers · optional · object[] — MCP servers this agent connects to. Maximum 20. Names must be unique within the array. Every server must be referenced by an `mcp_toolset` in `tools`; unreferenced servers are rejected. See the [MCP connector guide](https://platform.claude.com/docs/en/managed-agents/mcp-connector).
  • skills · optional · object[] — Skills available to the agent.
  • metadata · optional · object — Arbitrary key-value metadata. Maximum 16 pairs, keys up to 64 chars, values up to 512 chars.
  • multiagent · optional · object — Multiagent orchestration configuration. Currently supports the `coordinator` topology with a roster of 1-20 agents.