Integration · Developer
AI agents for LaunchDarkly
Find feature flags and their status in each environment, turn a flag on or off, create a flag, see what a user would get and read the audit log, on LaunchDarkly's commercial, EU or federal instance, with an access token.
- Actions
- 10
- Read
- 8
- Write
- 2
Actions
What your agents can do in LaunchDarkly
10 actions. Each one is a tool your agents can call and a step your workflows can run.
Read 8
Look things up. Nothing changes.
List projects
Lists LaunchDarkly projects as items: each with its key, name, tags and ID; totalCount is the number of projects.
List feature flags
Lists a project's feature flags as items, with totalCount.
Get a feature flag
Reads one flag by key: name, description, kind, variations.
Get a flag's status in each environment
Reads how a flag is being used in every environment of its project.
See which variations a user gets
Evaluates a project's flags for one context (a user, organization or device) in one environment, without counting as real traffic.
List segments
Lists a project's segments in one environment as items.
Read the audit log
Lists audit log entries, newest first: who changed what and when (flag toggles, rule edits, new flags, member changes).
Check the access token
Reads who the connection acts as: the account ID, the token's name and ID, its kind (personal or service), the member ID and its scopes.
Write 2
Create, change or send.
Turn a flag on or off
Turns a flag's targeting on or off in one environment, with a comment for the audit log.
Create a feature flag
Creates a flag in a project with a key and name.
A person can approve first
Any write action can be set to wait for a person's approval before it runs, so an agent asks before it changes anything.
Connection
How it connects
Connect it once in the console, then give it to the agents and workflows that need it.
Paste an API key from your LaunchDarkly account.
What you enter
- Access token
Settings
- LaunchDarkly instance
Kept safe
- Credentials are stored encrypted with your organization's own keys.
- They are opened only by the process that makes the call, at the moment it runs, and never go into a prompt or the browser.
- Calls go only to the tool's own servers.
Ideas
Ideas to start with
Starting points made only from the actions above. Mix them with any other tool your agents can use.
- 01
Ask about your LaunchDarkly data
Ask a question in plain words. The agent can list projects, list feature flags or get a feature flag in LaunchDarkly, then answers with what it found.
- 02
Let an agent update LaunchDarkly
Have the agent turn a flag on or off or create a feature flag in LaunchDarkly as part of a larger task. Turn on approval and a person signs off on each change first.
- 03
Share what it finds in Slack
Give one agent LaunchDarkly and Slack: it can list projects in LaunchDarkly and post a summary to a Slack channel in the same run.
Works well with
More Developer tools
- GitHub4 actionsOpen and comment on issues, and start GitHub Actions workflows, in the repositories a personal access token can reach.
- GitLab4 actionsOpen and comment on issues, and start CI/CD pipelines, in the GitLab.com projects an access token can reach.
- Bitbucket3 actionsComment on and read pull requests, and start Bitbucket Pipelines, in the Bitbucket Cloud repositories your Atlassian API token can reach.
- Sentry3 actionsList, read, resolve and ignore error issues in a sentry.io organization, in its US or EU (Germany) data region.
- Datadog2 actionsPost events to the Datadog Event Explorer and send custom metric points, on any Datadog site, with an API key.
- PagerDuty4 actionsOpen, acknowledge and resolve PagerDuty incidents, add notes to them, and see who is on call for a schedule.
FAQ
LaunchDarkly and MyDeepAgents
Can MyDeepAgents connect to LaunchDarkly?
Yes. The LaunchDarkly connector has 10 actions: 8 read and 2 make changes. Your agents can call them as tools, and your workflows can run them as steps.
How do I connect LaunchDarkly?
Paste an API key from your LaunchDarkly account. You'll need: Access token. The connection also asks for: LaunchDarkly instance. Credentials are stored encrypted with your organization's own keys and are opened only at the moment of a call.
Can an agent change data in LaunchDarkly without asking?
Only if you let it. Each of the 2 actions that change data can be set to wait for a person's approval before it runs.
Can I use LaunchDarkly in workflows as well as agents?
Yes. Every LaunchDarkly action also works as a step in a workflow, and the same connection serves your agents and your workflows.
Early access
Put LaunchDarkly to work
Connect it in a few minutes, give an agent the actions it needs, and decide which changes wait for a person.