ConfigCat
for LuumenAI

Read flag state across environments, then change rollouts as approved steps

Connect ConfigCat and your agent can read the whole flag surface: products, configs, environments, and the full evaluation formula behind any flag. Ask what a flag resolves to in production, or which targeting rules are in play, and get an answer from the live service. Changes to values, metadata, and new flags are previewed first and applied after you approve. Luumen authenticates with an API key.

The ConfigCat toolbox

10 tools: 5 read, 5 write. Reads answer instantly. Writes require approval by default. Everything is logged.

  • ReadGet Product ContextReturn a ConfigCat Product's configs, environments, segments, and tags, including the identifiers and evaluation versions needed to manage flags and targeting.
  • ReadGet Environment Setting Value V2Get one Config V2 flag or setting's complete evaluation formula in an Environment, including its optimistic-concurrency version.
  • ReadList Account HierarchyList accessible ConfigCat organizations and products so an agent can resolve the IDs needed by product-scoped tools.
  • ReadList Environment Values V2Return every Config V2 feature flag and setting evaluation formula for one Config and Environment, preserving ordered targeting rules and concurrency versions while omitting parent objects and…
  • ReadList Flags and SettingsList feature flags and settings in one Config, including IDs, keys, types, tags, and metadata needed by value operations.
  • WriteCreate Flag or SettingCreate a feature flag or typed setting in a Config. Approval by default
  • WriteDelete Flag or SettingPermanently delete one ConfigCat feature flag or setting by ID. Approval by default
  • WritePatch Environment Setting Value V2Update selected typed fields of one Config V2 evaluation formula while preserving every field the caller omits. Approval by default
  • WriteReplace Environment Setting Value V2Completely replace one Config V2 flag or setting evaluation formula in an Environment. Approval by default
  • WriteUpdate Flag MetadataPartially update a flag or setting's name, hint, or complete tag assignment without resetting untouched metadata. Approval by default

One prompt, start to finish

What a governed ConfigCat run looks like inside Luumen.

Questions

How does LuumenAI connect to ConfigCat?

Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.

Can LuumenAI change things in ConfigCat on its own?

Read actions answer immediately. Anything that writes — create flag or setting, delete flag or setting, patch environment setting value v2, replace environment setting value v2, and more — is shown as a plan and requires approval by default, including the 1 action classified as destructive. Administrators configure that per tool, so you decide exactly which actions can ever run unattended.

Who gets access to the integration?

You decide. Actions are granted per agent, skill, and team, and per environment — production is not staging. Read access can be broad while writes stay narrow.

Is there an audit trail?

Every call to ConfigCat — read or write, approved or declined — is recorded with the actor, the input, and the result, and can be linked to the ticket or change record.

Put ConfigCat to work with Luumen

Connect in minutes. Every action scoped, approved, and audited from day one.