Contentful Graphql for AI agents
Contentful's GraphQL API queries content stored in Contentful directly, letting a developer pull exactly the fields a page needs in one request. 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 Contentful Graphql.
Query content with GraphQL
Run a GraphQL query against a space to pull exactly the content fields a page needs.
Fetch a persisted query
Run a saved persisted query instead of sending the full query text each time.
Get a management token
Get a CMA token before switching from reading content to editing it directly.
2 Contentful Graphql actions, graded by risk.
Every Contentful Graphql action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
1Look things up. Allowed by default.
- contentful_graphql.get_cma_tokenGet CMA Token
write
1Create and change things. Allow, or ask the user first.
- contentful_graphql.graph_ql_content_api_persisted_queryGraphQL Content API Persisted Query
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Contentful Graphql in three steps.
- 01Your users connect Contentful GraphqlThey add their Contentful Graphql api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “graphQL Content API Persisted Query” can wait for the user to approve.
- 03Any agent can actYour agent calls Contentful Graphql through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('contentful_graphql', { read: 'allow', write: 'ask', // graph_ql_content_api_persisted_query destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Contentful Graphql connects.
Users add their Contentful Graphql 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 Contentful Graphql 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 Contentful Graphql from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Contentful Graphql and Arc0, answered.
Can I use Contentful Graphql with Claude, ChatGPT or Cursor?
Yes. Connect Contentful Graphql 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 Contentful Graphql actions you allow.
How do users connect Contentful Graphql?
Users add their Contentful Graphql 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 Contentful Graphql actions can my agent take?
2 in total: 1 read, 1 write and 0 destructive, such as “graphQL Content API Persisted Query”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Contentful Graphql?
Yes. Allow read actions and deny writes in the Contentful Graphql policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Contentful Graphql too?
Yes. The same Contentful Graphql connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Contentful Graphql into your agent.
Your users connect Contentful Graphql once, under your brand. Your agent gets 2 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan