Skip to main content
Your agent decides what to say; Doconda turns it into the document. There are three ways to connect it, depending on your stack:

MCP server

For any MCP client: Claude, Cursor, Codex, LangChain, CrewAI, smolagents, n8n. No code to write.

SDK tools

doconda.tools(): tools ready for function calling with Claude, OpenAI, Gemini, Mistral, Bedrock, Vertex AI or the AI SDK.

REST API

For everything else: an HTTP request with your API key.

The tools

Whether through MCP or the SDK, your agent gets the same tools: Each tool returns a short summary (status and links), designed so the agent can pass it on to the user without using up context. Errors also come back as a result, with a code the agent can understand and fix: if a field is missing, it says so.

By stack

Everything the agent does counts as if you did it yourself with the API: same project, same region, same price.