Flotiq for AI agents

Flotiq is a headless content management system for defining content types, managing content, and handling media through an API, used by developers building custom front ends. 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.

Files and storageAPI keyMCP + RESTflotiq.com
AUDIT LOG · FLOTIQPOLICY: acme-support
09:41:07 · claude · u_8f2read
flotiq.list_content_types
List Content Types✓ allowed · 212ms
09:41:08 · claude · u_8f2read
flotiq.search_content
Search Content✓ allowed · 164ms
09:41:09 · claude · u_8f2write
flotiq.create_content_object
Create Content Object✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
flotiq.delete_content_object
Delete Content Object✕ blocked · policy: deny
EVERY FLOTIQ CALL, ON THE RECORD
01 · USE CASES

What agents do in Flotiq.

01

Publish a content object

Set a content object's publication status once an editor approves it for release.

02

Search content by keyword

Search content objects to find an entry matching a keyword from an editor's request.

03

Confirm before deleting content

Require approval before deleting a content object, since it can be referenced by a live page.

02 · ACTIONS

10 Flotiq actions, graded by risk.

Every Flotiq action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

5

Look things up. Allowed by default.

  • flotiq.search_content
    Search Content
  • flotiq.get_content_type
    Get Content Type
  • flotiq.get_content_object
    Get Content Object
  • flotiq.list_content_types
    List Content Types
  • flotiq.list_content_objects
    List Content Objects

write

4

Create and change things. Allow, or ask the user first.

  • flotiq.create_content_object
    Create Content Object
  • flotiq.update_content_object
    Update Content Object
  • flotiq.batch_upsert_content_objects
    Batch Upsert Content Objects
  • flotiq.set_content_object_publication
    Set Content Publication

destructive

1

Delete, cancel or archive. Ask first, or deny outright.

  • flotiq.delete_content_object
    Delete Content Object
03 · HOW IT WORKS

Flotiq in three steps.

  1. 01Your users connect FlotiqThey add their Flotiq api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “create Content Object” can wait for the user, and “delete Content Object” can be denied outright.
  3. 03Any agent can actYour agent calls Flotiq through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('flotiq', {
  read: 'allow',
  write: 'ask',        // create_content_object
  destructive: 'deny',  // delete_content_object
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Flotiq connects.

Users add their Flotiq 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 Flotiq 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
05 · WORKS WITH

Use Flotiq from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

Flotiq and Arc0, answered.

Q01

Can I use Flotiq with Claude, ChatGPT or Cursor?

Yes. Connect Flotiq 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 Flotiq actions you allow.

Q02

How do users connect Flotiq?

Users add their Flotiq 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.

Q03

Which Flotiq actions can my agent take?

10 in total: 5 read, 4 write and 1 destructive, such as “create Content Object”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Flotiq?

Yes. Actions like “delete Content Object” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.

Q05

Can my own backend call Flotiq too?

Yes. The same Flotiq connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Flotiq into your agent.

Your users connect Flotiq 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