Get started

ConfigCat for AI agents

ConfigCat manages feature flags, letting a team control feature rollouts and configuration values across environments without redeploying code each time. 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.

Connect ConfigCatSee the 10 actions ↓
Developer toolsAPI keyMCP + RESTconfigcat.com
AUDIT LOG · CONFIGCATPOLICY: acme-support
09:41:07 · claude · u_8f2read
configcat.list_settings
List Flags and Settings✓ allowed · 212ms
09:41:08 · claude · u_8f2read
configcat.get_product_context
Get Product Context✓ allowed · 164ms
09:41:09 · claude · u_8f2write
configcat.create_setting
Create Flag or Setting✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
configcat.delete_setting
Delete Flag or Setting✕ blocked · policy: deny
EVERY CONFIGCAT CALL, ON THE RECORD
01 · USE CASES

What agents do in ConfigCat.

01

Check a flag's current value

Check a feature flag's current value in an environment before deciding to change it.

02

Turn on a flag in an environment

Update a flag's value in a specific environment to roll out a feature to users.

03

Confirm before deleting a flag

Confirm before deleting a flag, since any code still checking it would default to off.

02 · ACTIONS

10 ConfigCat actions, graded by risk.

Every ConfigCat 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.

  • configcat.list_settings
    List Flags and Settings
  • configcat.get_product_context
    Get Product Context
  • configcat.get_setting_value_v2
    Get Environment Setting Value V2
  • configcat.list_account_hierarchy
    List Account Hierarchy
  • configcat.list_environment_values_v2
    List Environment Values V2

write

4

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

  • configcat.create_setting
    Create Flag or Setting
  • configcat.update_setting_metadata
    Update Flag Metadata
  • configcat.patch_setting_value_v2
    Patch Environment Setting Value V2
  • configcat.replace_setting_value_v2
    Replace Environment Setting Value V2

destructive

1

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

  • configcat.delete_setting
    Delete Flag or Setting
03 · HOW IT WORKS

ConfigCat in three steps.

  1. 01Your users connect ConfigCatThey add their ConfigCat api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “create Flag or Setting” can wait for the user, and “delete Flag or Setting” can be denied outright.
  3. 03Any agent can actYour agent calls ConfigCat 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('configcat', {
  read: 'allow',
  write: 'ask',        // create_setting
  destructive: 'deny',  // delete_setting
})

# 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 ConfigCat connects.

Users add their ConfigCat 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 ConfigCat 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 ConfigCat from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
06 · RELATED

More developer tools apps.

GitHub896 actionsSupabase129 actions0CodeKit8 actionsAbly25 actionsAbstract3 actionsAddressfinder17 actionsAddresszen2 actionsAlchemy36 actions
ALL DEVELOPER TOOLS APPS →
07 · FAQ

ConfigCat and Arc0, answered.

Q01

Can I use ConfigCat with Claude, ChatGPT or Cursor?

Yes. Connect ConfigCat 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 ConfigCat actions you allow.

Q02

How do users connect ConfigCat?

Users add their ConfigCat 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 ConfigCat actions can my agent take?

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

Q04

Can I stop my agent from deleting things in ConfigCat?

Yes. Actions like “delete Flag or Setting” 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 ConfigCat too?

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

Get started

Plug ConfigCat into your agent.

Your users connect ConfigCat once, under your brand. Your agent gets 10 actions behind your policies, with every call on the record.

Connect ConfigCatBrowse all apps →

Free to build · MCP + REST · Audit log on every plan