LaunchDarkly for AI agents

LaunchDarkly is a feature management platform engineering teams use to control feature flags, rollouts, and experiments in production without redeploying code. 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.

Developer toolsOAuth 2.0MCP + RESTlaunchdarkly.com
AUDIT LOG · LAUNCHDARKLYPOLICY: acme-support
09:41:07 · claude · u_8f2read
launchdarkly.list_teams
List Teams✓ allowed · 212ms
09:41:08 · claude · u_8f2read
launchdarkly.get_ips
Get IPs✓ allowed · 164ms
09:41:09 · claude · u_8f2write
launchdarkly.create_team
Create Team✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
launchdarkly.delete_team
Delete Team✕ blocked · policy: deny
EVERY LAUNCHDARKLY CALL, ON THE RECORD
01 · USE CASES

What agents do in LaunchDarkly.

01

Check a feature flag's status

Look up a flag's targeting rules and environment status before a release discussion.

02

Submit a flag change for approval

Create an approval request to change a flag's rollout, since flag changes affect production traffic.

03

Create a new experiment

Set up a new experiment tied to a feature flag to test a rollout variant.

02 · ACTIONS

248 LaunchDarkly actions, graded by risk.

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

read

125

Look things up. Allowed by default.

  • launchdarkly.get_ips
    Get IPs
  • launchdarkly.get_root
    Get Root
  • launchdarkly.get_tags
    Get Tags
  • launchdarkly.get_team
    Get Team
  • launchdarkly.get_token
    Get Access Token
  • launchdarkly.get_branch
    Get Branch
  • launchdarkly.get_layers
    Get Layers
  • launchdarkly.get_member
    Get Account Member
  • launchdarkly.get_metric
    Get Metric
  • launchdarkly.get_tokens
    Get Tokens
  • launchdarkly.list_teams
    List Teams
  • launchdarkly.get_holdout
    Get Holdout
  • launchdarkly.get_members
    Get Members
  • launchdarkly.get_project
    Get Project
  • launchdarkly.get_segment
    Get Segment
  • launchdarkly.get_webhook
    Get Webhook
+ 109 MORE

write

88

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

  • launchdarkly.create_team
    Create Team
  • launchdarkly.create_layer
    Create Layer
  • launchdarkly.update_layer
    Update Layer
  • launchdarkly.create_metric
    Create Metric
  • launchdarkly.create_holdout
    Create Holdout
  • launchdarkly.create_members
    Create Members
  • launchdarkly.create_project
    Create Project
  • launchdarkly.create_segment
    Create Segment
  • launchdarkly.create_webhook
    Create Webhook
  • launchdarkly.create_workflow
    Create Workflow
  • launchdarkly.create_flag_link
    Create Flag Link
  • launchdarkly.create_iteration
    Create Experiment Iteration
  • launchdarkly.update_flag_link
    Update Flag Link
  • launchdarkly.create_experiment
    Create Experiment
  • launchdarkly.create_extinction
    Create Extinction Events
  • launchdarkly.create_repository
    Create Repository
+ 72 MORE

destructive

35

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

  • launchdarkly.delete_team
    Delete Team
  • launchdarkly.delete_token
    Delete Access Token
  • launchdarkly.delete_member
    Delete Account Member
  • launchdarkly.delete_metric
    Delete Metric
  • launchdarkly.delete_project
    Delete Project
  • launchdarkly.delete_segment
    Delete Segment
  • launchdarkly.delete_webhook
    Delete Webhook
  • launchdarkly.delete_branches
    Delete Branches from Code Reference Repository
  • launchdarkly.delete_workflow
    Delete Workflow
  • launchdarkly.delete_flag_link
    Delete Flag Link
  • launchdarkly.delete_repository
    Delete Repository
  • launchdarkly.delete_custom_role
    Delete Custom Role
  • launchdarkly.delete_destination
    Delete Data Export Destination
  • launchdarkly.delete_environment
    Delete Environment
  • launchdarkly.delete_feature_flag
    Delete Feature Flag
  • launchdarkly.delete_metric_group
    Delete Metric Group
+ 19 MORE
03 · HOW IT WORKS

LaunchDarkly in three steps.

  1. 01Your users connect LaunchDarklyThey sign in to LaunchDarkly on Arc0 Connect, under your brand, and approve the access you ask for.
  2. 02You set the rulesReads run, writes like “create Team” can wait for the user, and “delete Team” can be denied outright.
  3. 03Any agent can actYour agent calls LaunchDarkly 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('launchdarkly', {
  read: 'allow',
  write: 'ask',        // create_team
  destructive: 'deny',  // delete_team
})

# 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 LaunchDarkly connects.

Users sign in to LaunchDarkly on Arc0 Connect and approve the scopes you request. Build with Arc0’s LaunchDarkly OAuth app, or bring your own so the LaunchDarkly consent screen names you. Tokens refresh automatically, and you can export them whenever you want.

The same LaunchDarkly 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 · OAuth 2.0
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use LaunchDarkly from any agent.

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

LaunchDarkly and Arc0, answered.

Q01

Can I use LaunchDarkly with Claude, ChatGPT or Cursor?

Yes. Connect LaunchDarkly 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 LaunchDarkly actions you allow.

Q02

How do users connect LaunchDarkly?

Users sign in to LaunchDarkly on Arc0 Connect and approve the scopes you request. Build with Arc0’s LaunchDarkly OAuth app, or bring your own so the LaunchDarkly consent screen names you. Tokens refresh automatically, and you can export them whenever you want.

Q03

Which LaunchDarkly actions can my agent take?

248 in total: 125 read, 88 write and 35 destructive, such as “create Team”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in LaunchDarkly?

Yes. Actions like “delete Team” 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 LaunchDarkly too?

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

Get started

Plug LaunchDarkly into your agent.

Your users connect LaunchDarkly once, under your brand. Your agent gets 248 actions behind your policies, with every call on the record.

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