Anthropic (Claude)
Generate AI responses with Claude. Chat completions, content generation, analysis, and more. BYOK — bring your own Anthropic API key.
setup_integration or the Dashboard Vault — they're encrypted
with AES-256-GCM and never exposed.
Required Credentials
Get your API key at docs.anthropic.com →
Endpoints (2)
Send a message to Claude and get a response. Supports system prompts, multi-turn conversations, and model selection.
| Field | Type | Required | Description |
|---|---|---|---|
model |
string | ✓ Yes | Claude model: "claude-sonnet-5" (balanced), "claude-haiku-4-5-20251001" (fast/cheap), "claude-opus-4-8" (most capable). |
max_tokens |
integer | ✓ Yes | Max response tokens (1-4096). Higher = longer responses. |
messages |
array | ✓ Yes | Conversation messages. Example: [{"role": "user", "content": "Explain quantum computing in 2 sentences"}]. |
system |
string | No | System prompt to set Claude's behavior. Example: "You are a helpful travel guide for Amsterdam." |
List available Claude models with their capabilities and context window sizes.
No input parameters required.
MCP Tool Names
When using this integration through an AI assistant (Claude, ChatGPT, Cursor, etc.), the endpoints are available as MCP tools:
| Endpoint | MCP Tool Name |
|---|---|
| create-message | anthropic_create_message |
| list-models | anthropic_list_models |
Website