Anthropic Messages API

What authentication does the Anthropic Messages API use?

Anthropic's documentation lists two alternatives and requires one of them: an API key in the X-API-Key header, or an Authorization bearer token holding a short-lived access token. Every call also carries a required anthropic-version header that pins the API behaviour, plus an optional anthropic-beta header for preview features. Through Jentic the API key is stored encrypted by your own Jentic One instance and injected at execution time, so the raw key never enters the agent's prompt context.

Can I count tokens before sending a message to Claude?

Yes. POST /messages/count_tokens accepts the same messages and system prompt shape as POST /messages and returns the token count. Anthropic documents token counting as free to use but subject to its own requests-per-minute rate limit, held separately from the message-creation limit, so counting does not draw down your sending budget. Use it to keep a request inside the selected model's context window or inside a cost cap.

What are the rate limits for the Anthropic Messages API?

The OpenAPI spec does not declare explicit rate limits. Anthropic's documentation measures Messages API limits as requests per minute, input tokens per minute, and output tokens per minute for each model class, set at the organisation level and varying by usage tier. Exceeding one returns a 429 naming the limit that was exceeded, along with a retry-after header indicating how long to wait, so back off on 429 responses and check your tier in the Claude Console.

How do I send a message to Claude through Jentic?

Install Jentic One from its GitHub repo, import the Anthropic Messages API from the API Directory, and store your API key once. Then search Jentic for 'send a message to Claude'. Jentic returns POST /messages with the full messages, system, and tools schema. Execute it with your model id and conversation history; your Jentic One instance injects the X-API-Key at call time.

Does the Messages API support tool use and streaming?

Yes. POST /messages accepts a tools array and returns tool_use blocks the agent dispatches and feeds back via tool_result messages. The same endpoint supports server-sent event streaming when the request enables it, so chat surfaces can render tokens as they arrive.

Why are anthropic-version and anthropic-beta declared as security headers in the spec?

Anthropic requires the anthropic-version header on every Messages call and uses anthropic-beta to gate preview features. This specification models them as apiKey security schemes to signal that clients must send them alongside X-API-Key, even though they are not secrets in the credential sense. Treat the requirement as coming from Anthropic's documentation rather than from the schemes themselves: Anthropic's official specification declares no security schemes at all and marks anthropic-version as an ordinary optional header.

Is there an Anthropic Messages API MCP server?

You do not need an MCP server to give your agent the Anthropic Messages API. Jentic connects it directly from the API Directory: import it, store your API key once, and your agent calls it without loading another server's tool definitions into its context.

Can I limit what my agent is allowed to do with the Anthropic Messages API?

Yes. This specification exposes two operations, sending a message and counting tokens, and your rules decide which of them the agent may call. The Messages API carries the conversation content in the request body rather than a resource id in the URL path, so rules bound which operations run rather than which individual conversations.