How to connect Prismic to Claude

Claude is Anthropic's AI assistant, available on the web, in the desktop app, and on mobile. Cowork is its agent for knowledge work, and it runs on all of those surfaces too. Connected to your apps, Claude can work with your files and services to accomplish complex tasks on your behalf.

This guide walks you through the easiest and most secure way to connect your Prismic account to Claude via Composio Connect, enabling it to find all blog posts tagged 'launch', get latest articles ordered by publish date, fetch document details by Prismic ID, and more such actions on your behalf without compromising your account security.

Setup is the same on Claude Web, Desktop, and Cowork, and you only need to do it once. The connector is tied to your account, so it's available in all three.

Connecting Prismic to Claude Web, Desktop, and Cowork

Two ways to add the Composio connector. Pick whichever you prefer.

1. Add with one click

Click the button. Claude opens with the Composio connector filled in. Click Add, then go to step 2.

Add to Claude

Add manually

In Claude Desktop, click Customize in the left sidebar, then select Connectors and click the + icon at the top.

Click Add custom connector and paste in the Composio MCP server URL:

The Prismic MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Prismic account. It provides structured and secure access to your content repository, so your agent can search, retrieve, filter, and organize content, as well as gather repository details—all without manual coding.

• Full-text and predicate-based search: Instantly ask the agent to find documents using keywords, tags, or advanced predicates for highly targeted content discovery.
• Retrieve documents by custom fields or type: Fetch content based on custom fields, document types, or tags, making it easy to surface exactly what you need from your CMS.
• Get and sort documents with advanced ordering: Let your agent return documents ordered by fields like date or title, supporting content workflows where order matters.
• Fetch detailed repository metadata: Have the agent pull repository settings, available refs, types, and supported languages for a comprehensive view of your content environment.
• Access integration fields and enriched content: Retrieve documents including data from integration fields, so your agent can work with richer, more connected content structures.