Connect Writer MCP for AI Agents

You upload your internal manuals and reports to the MCP. The system creates a Knowledge Graph from that data, allowing your agent to query it directly using RAG. This means the AI answers questions based only on what you provide, eliminating guesswork.

Yes. You can define multi-step workflows—like processing a form and sending an alert—using no-code agents within the MCP. The agent manages the entire sequence, handling both immediate and delayed results.

It's much more secure and precise. Unlike general models that pull from public web knowledge, this MCP forces the AI to reference your specific internal documents or structured graphs first. You get answers with clear source context.

You upload the file, and the agent can use specialized vision tools to read text from images and PDFs. It converts that visual data into structured knowledge you can then query for insights.

Yes. The MCP gives developers direct access to the underlying models and tools, allowing them to programmatically manage document pipelines (like creating graphs) and integrate complex logic into their custom applications.

Use the list_models tool. It will return a list of all active models in your Writer account, such as palmyra-x5 or palmyra-med.

Yes. First, use upload_file to add your documents, then create_graph and add_file_to_graph to build a Knowledge Graph for RAG-based querying.

Yes, the chat_completion tool accepts a messages array, allowing you to maintain full context for multi-turn dialogues with the model.