# Prismic MCP for AI Agents AI Agent Connect > Prismic lets you bridge your headless CMS directly into your AI workflow. Instead of jumping back and forth between your CMS dashboard and your code editor, you can ask your agent to find specific content, check your custom types, or pull full document data. It's built for anyone who needs to treat content as data while building modern web experiences. ## Overview - **Category:** loved-by-devs - **Price:** Free - **Endpoint:** https://edge.vinkius.com/vk_preview_jK6sO72lQezxjBKP0hCujVjdqiy2aRnElcL2Nsu8/ai-agent-connect - **Tags:** cms, content-modeling, api-first, web-development, document-query, json-schema ## Description Imagine you're halfway through building a frontend component and you need to know the exact structure of a blog post or a landing page. Usually, you'd have to switch tabs, log into your CMS, and dig through the UI to find the right document. This Connector changes that. By connecting your headless CMS to your workspace, your agent becomes a live extension of your content repository. You can ask it to find every document tagged with "summer-sale" or pull the full JSON for a specific page ID to see exactly how the slices are organized. It takes the guesswork out of content modeling because you can explore your repository's schema, languages, and custom types without ever leaving your chat. If you're looking for a way to make your content more accessible to your dev tools, Vinkius makes it easy to plug this in and start querying your live data immediately. It turns your CMS from a siloed dashboard into a searchable knowledge base for your agent. Instead of guessing what a content field contains or if a certain tag exists, you can just ask. It's the difference between hunting for data and having it served to you. Whether you're trying to verify translations for a French site or just need to see what custom types are available for a new project, the information is always one prompt away. This means fewer mistakes in your code and a much faster way to verify that the content in the CMS matches what you're actually building on the frontend. ## Tools ### search_filtered_locale Perform a search that specifically targets documents in a single locale. Use this to find content for a specific language. ### get_repo_metadata Retrieve high-level info about your repository like master refs and languages. This gives your agent context on the repository structure. ### get_document_by_id Fetch the full content of a specific document using its unique ID. This is the fastest way to get the exact JSON for a specific page. ### get_query_form_schema Look up the schema for a specific query form like everything. This helps you understand what fields are available for a content type. ### list_i18n_languages See all the languages and locales currently configured in your repository. This helps you quickly identify which versions of a page are available for different regions. ### list_global_tags Get a full list of every tag used across your entire Prismic repository. Use this to check for existing tags before creating new ones. ### list_custom_types See all the custom types you've defined in your Prismic repository. This is great for understanding your content model at a glance. ### list_documents_by_tag Find every document that has a specific tag assigned to it. This makes it easy to group and find related content quickly. ### list_documents_by_type Pull a list of all documents belonging to a specific custom type. This helps you see the volume of content for a specific model. ### query_prismic_documents Search for documents using raw predicates with built-in pagination and locale filtering. This is the most powerful way to find specific content. ## Prompt Examples **Prompt:** ``` List all the custom types in my Prismic repo. ``` **Response:** ``` I found 4 custom types in your repository: 'homepage', 'blog_post', 'author', and 'navigation'. Would you like me to fetch a few documents of type 'blog_post' to check out the structure? ``` **Prompt:** ``` Can you fetch the document JSON for the ID 'ZbHwWxEAACUAx9'? ``` **Response:** ``` Here is the full JSON payload for document 'ZbHwWxEAACUAx9'. It is a 'page' type with the slug 'about-us'. I can generate a Next.js component to map this slice structure if you'd like. ``` **Prompt:** ``` Search for all documents tagged with 'seo' and 'landing'. ``` **Response:** ``` I performed a search using Prismic predicates for the tags 'seo' and 'landing'. The API returned 12 documents. They are mostly of type 'article'. Want to see the titles of the first 5 results? ``` ## Capabilities ### Search content by tags Find every document in your repository that shares a specific tag or category. ### Fetch full document JSON Retrieve the complete data payload for a specific document ID to see its full structure. ### List all custom types Get a full list of the content models and custom types defined in your CMS. ### Filter content by locale Target your search to a specific language or region like en-us or fr-fr. ### View repository metadata See high-level repository details including master refs and active languages. ### Retrieve query form schemas See the underlying schema for specific query forms to understand how data is organized. ## Use Cases ### Building components with real data A developer needs to know the JSON structure of a Product page to build a new React component. They use get_document_by_id to fetch the real payload. ### Auditing tags for outdated content A content manager needs to find all documents tagged with promo to check for expired dates. They use list_documents_by_tag to find them in seconds. ### Verifying translations for regional pages An SEO lead wants to see the slug and copy for a French landing page without logging into the dashboard. They use search_filtered_locale to check the content. ### Checking content model availability A developer wants to see all available custom types to ensure they aren't creating duplicate content models. They use list_custom_types to see the full list. ## Benefits - Stop context-switching by using query_prismic_documents to find content directly in your chat. - Build components faster by using get_document_by_id to see the exact JSON structure your agent needs to map. - Audit your content faster with list_global_tags to see every tag used across your entire repository. - Simplify multi-language management by using list_i18n_languages to see all active locales. - Understand your content model instantly with list_custom_types and get_query_form_schema. - Speed up SEO audits by using search_filtered_locale to check specific page copy in different regions. ## How It Works The bottom line is you get a live, searchable connection to your Prismic content directly inside your AI client. 1. Subscribe to the Prismic MCP and enter your Repository Name 2. Add your optional Access Token for secure connection 3. Ask your agent to find, list, or fetch any content from your CMS ## Frequently Asked Questions **Can the Prismic MCP help me build frontend components faster?** Yes, it lets your agent fetch the actual JSON from your CMS. You can see exactly how your data is structured so you don't have to guess when building your components. **Can I use this to find specific content in my Prismic repository?** You can. Your agent can search by tags, types, or specific locales to find exactly what you're looking for without you having to navigate the dashboard. **Does the Prismic MCP allow me to edit my CMS content?** No, this Connector is for reading and querying content. It helps you find and analyze data, but it doesn't have the permissions to change or delete your documents. **How does this help with multi-language content?** It makes it much easier. You can use it to list all configured languages or perform searches that are filtered to a specific locale like fr-fr or en-us. **Can my AI agent see my content schema?** Yes, it can. The Connector allows your agent to list all your custom types and even retrieve the query form schemas, making it easier to understand your content model. **Is this good for auditing my tags and content types?** It's perfect for that. You can ask your agent to list every global tag or custom type to find duplicates or outdated content models in seconds. **How do I start extracting content from my Prismic repository?** Subscribe, enter your Prismic Repository Name, and if your repository is private, grab an Access Token from **Settings → API & Security**. No manual SDK setups or GraphQL integrations — just connect and start querying your custom types and documents directly through your AI agent. **Can my AI agent help me build Next.js components matching my Custom Types?** Yes! Ask your agent to query a specific document ID or list custom types. It will retrieve the exact JSON payload returned by the Prismic API. Based on that structure, the agent can instantly generate your Next.js/React component props, mock data, and TS interfaces natively inside Cursor. **What happens when I need to find all blog posts tagged with 'announcement' in French?** Just ask your AI agent. It uses the `search_filtered_locale` tool and Prismic predicates to filter documents precisely by type, tag, and language code without requiring you to manually craft complex API query strings or write ad-hoc fetch scripts. **Does it support deep repository insights for large content websites?** Absolutely. You can list all custom types, pull an array of all global tags, and verify all configured languages for multi-lingual websites. It acts as an instant audit tool for publishers, content operations teams, and architects managing extensive CMS architectures.