Kontent.ai for AI agents
Kontent.ai is a headless CMS that stores structured content and delivers it through an API to power websites and apps in any framework. 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 Kontent.ai.
Look up a content item
Read a content item and its language variants before referencing it in another system.
List content types in a project
List the content types defined in a project to understand its schema, read-only.
Check a language variant's fields
Pull a specific language variant of an item to verify translated field values.
7 Kontent.ai actions, graded by risk.
Every Kontent.ai action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
7Look things up. Allowed by default.
- kontent_ai.get_languageGet Language
- kontent_ai.list_languagesList Languages
- kontent_ai.get_content_itemGet Content Item
- kontent_ai.get_types_elementGet Content Type Element
- kontent_ai.list_content_itemsList Content Items
- kontent_ai.list_content_typesList Content Types
- kontent_ai.get_language_variantGet Language Variant
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.
Kontent.ai in three steps.
- 01Your users connect Kontent.aiThey add their Kontent.ai api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “updates” can wait for the user to approve.
- 03Any agent can actYour agent calls Kontent.ai through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('kontent_ai', { 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 Kontent.ai connects.
Users add their Kontent.ai 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 Kontent.ai 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 Kontent.ai from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Kontent.ai and Arc0, answered.
Can I use Kontent.ai with Claude, ChatGPT or Cursor?
Yes. Connect Kontent.ai 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 Kontent.ai actions you allow.
How do users connect Kontent.ai?
Users add their Kontent.ai 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 Kontent.ai actions can my agent take?
7 in total: 7 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.
Can I make my agent read-only in Kontent.ai?
Yes. Allow read actions and deny writes in the Kontent.ai policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Kontent.ai too?
Yes. The same Kontent.ai connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Kontent.ai into your agent.
Your users connect Kontent.ai once, under your brand. Your agent gets 7 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan