Prismic for AI agents
Prismic is a headless CMS that lets developers and content teams manage and deliver content across platforms. Marketing and engineering teams use it to keep website content editable and structured. 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 Prismic.
Search documents with full text
Find content documents matching a keyword before updating or referencing them.
Query documents by type
Pull all documents of a given custom type to power a page or listing.
Check repository info read-only
Look up a repository's configuration before building an integration against it.
5 Prismic actions, graded by risk.
Every Prismic action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
0Look things up. Allowed by default.
- No read actions.
write
5Create and change things. Allow, or ask the user first.
- prismic.types_api_get_typesPrismic: Get Custom Types
- prismic.tags_api_get_all_tagsGet Prismic Tags
- prismic.repository_api_get_infoGet Prismic Repository Info
- prismic.content_api_query_documentsPrismic: Query Documents
- prismic.content_api_get_documents_with_fulltext_searchGet Prismic Documents with Fulltext Search
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Prismic in three steps.
- 01Your users connect PrismicThey add their Prismic api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “prismic: Get Custom Types” can wait for the user to approve.
- 03Any agent can actYour agent calls Prismic through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('prismic', { read: 'allow', write: 'ask', // types_api_get_types destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Prismic connects.
Users add their Prismic api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same Prismic 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
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Prismic from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Prismic and Arc0, answered.
Can I use Prismic with Claude, ChatGPT or Cursor?
Yes. Connect Prismic 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 Prismic actions you allow.
How do users connect Prismic?
Users add their Prismic api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which Prismic actions can my agent take?
5 in total: 0 read, 5 write and 0 destructive, such as “prismic: Get Custom Types”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Prismic?
Yes. Allow read actions and deny writes in the Prismic policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Prismic too?
Yes. The same Prismic connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Prismic into your agent.
Your users connect Prismic once, under your brand. Your agent gets 5 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan