Storyblok for AI agents
Storyblok is a headless CMS with a visual editor that lets teams manage and deliver content, such as pages and components, across websites and apps. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in Storyblok.
Fetch a page item for review
Retrieve a specific page item's content before an agent suggests edits to a marketing team.
Query content types via GraphQL
Pull a list of content type items, such as blog posts, to check what exists before publishing more.
Look up a datasource read-only
Fetch entries from a datasource, such as a dropdown of categories, without modifying anything in the space.
10 Storyblok actions, graded by risk.
Every Storyblok action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
10Look things up. Allowed by default.
- storyblok.get_appGet Extension/App
- storyblok.get_page_itemGet Page Item
- storyblok.query_page_itemsQuery page items via GraphQL
- storyblok.get_datasource_entriesGet Datasource Entries
- storyblok.get_graphql_rate_limitGet GraphQL Rate Limit
- storyblok.list_graphql_content_type_itemsList GraphQL Content Type Items
- storyblok.retrieve_tagsRetrieve Tags via GraphQL
- storyblok.retrieve_links_graphqlRetrieve Links via GraphQL
- storyblok.fetch_graphql_content_itemFetch GraphQL Content Item
- storyblok.fetch_content_type_items_graphqlFetch Content Type Items (GraphQL)
write
0Create and change things. Allow, or ask the user first.
- No write actions.
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Storyblok in three steps.
- 01Your users connect StoryblokThey sign in to Storyblok on Arc0 Connect, under your brand, and approve the access you ask for.
- 02You set the rulesReads run, and writes like “updates” can wait for the user to approve.
- 03Any agent can actYour agent calls Storyblok through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('storyblok', { read: 'allow', write: 'ask', destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Storyblok connects.
Users sign in to Storyblok on Arc0 Connect and approve the scopes you request. Build with Arc0’s Storyblok OAuth app, or bring your own so the Storyblok consent screen names you. Tokens refresh automatically, and you can export them whenever you want.
The same Storyblok connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key · OAuth 2.0
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Storyblok from any agent.
Storyblok and Arc0, answered.
Can I use Storyblok with Claude, ChatGPT or Cursor?
Yes. Connect Storyblok to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Storyblok actions you allow.
How do users connect Storyblok?
Users sign in to Storyblok on Arc0 Connect and approve the scopes you request. Build with Arc0’s Storyblok OAuth app, or bring your own so the Storyblok consent screen names you. Tokens refresh automatically, and you can export them whenever you want.
Which Storyblok actions can my agent take?
10 in total: 10 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.
Can I make my agent read-only in Storyblok?
Yes. Allow read actions and deny writes in the Storyblok policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Storyblok too?
Yes. The same Storyblok connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Storyblok into your agent.
Your users connect Storyblok once, under your brand. Your agent gets 10 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan