Feature Flag
LaunchDarkly MCP connector
The LaunchDarkly connector brings feature flags, AgentControl configs and observability data into Claude, ChatGPT, Cursor, Microsoft Copilot and the Elaichi Agent, so each person works with LaunchDarkly under their own access and every change is logged.
- Connects over OAuth
- Free 14-day trial
- No credit card
Which flags are on in production but off in staging?
Working in LaunchDarkly with Elaichi
-
Looked in LaunchDarkly
How to connect LaunchDarkly to Claude, ChatGPT, Cursor or Microsoft Copilot
Step by step, for each AI app
LaunchDarkly MCP connector for Claude
-
1
Open Customize, then Connectors.
-
2
Press Add.
-
3
Name it, paste the MCP server URL, then Continue.
https://api.elaichi.ai/mcp -
4
Sign in and approve.
On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.
LaunchDarkly MCP connector for Claude Code
-
1
In a terminal, run
claude mcp addwith the endpoint.https://api.elaichi.ai/mcp -
2
Start Claude Code and run
/mcp. -
3
Pick elaichi, then sign in and approve in the browser.
Terminal
$ claude mcp add --transport http elaichi --scope user https://api.elaichi.ai/mcp
Use --scope project instead to share it with the repository through .mcp.json.
LaunchDarkly MCP connector for ChatGPT
-
1
Open Plugins, then press the + button.
-
2
Name it and paste the endpoint into Server URL.
https://api.elaichi.ai/mcp -
3
Leave Authentication on OAuth, then tick the risk acknowledgement.
-
4
Press Create, then sign in and approve.
Works on the web. The plugin directory lives at chatgpt.com/plugins.
LaunchDarkly MCP connector for Cursor
-
1
Open
~/.cursor/mcp.json. -
2
Add the endpoint under
mcpServers.https://api.elaichi.ai/mcp -
3
Reload Cursor, then sign in and approve.
~/.cursor/mcp.json
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
Set up per machine, so repeat it on each computer you work from.
LaunchDarkly MCP connector for Microsoft Copilot
-
1
In Copilot Studio, open your agent, then Tools, Add a tool, New tool and Model Context Protocol.
-
2
Paste the endpoint into Server URL, choose OAuth 2.0, then Dynamic discovery, and press Create.
https://api.elaichi.ai/mcp -
3
Create a new connection, sign in and approve, then press Add to agent.
-
4
Under Channels, open Teams and Microsoft Copilot and make the agent available in Microsoft Copilot.
- Server URL
- https://api.elaichi.ai/mcp
- Authentication
- OAuth 2.0
- Type
- Dynamic discovery
Microsoft Copilot was called Microsoft 365 Copilot. Keep the tool on end-user credentials, so each person signs in as themselves.
Connect LaunchDarkly to any MCP client
-
1
Add the endpoint as a remote MCP server.
https://api.elaichi.ai/mcp -
2
Sign in and approve.
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
The Elaichi Agent already has these tools, with nothing to set up.
What teams do with LaunchDarkly through Elaichi
Ask in plain English. Each person’s AI can do only what they’re allowed to, and every action it takes in LaunchDarkly is logged.
-
Engineering
Check what is live before a deploy
Ask which flags are on in production but still off in staging, and who changed them last, before shipping anything that depends on them.
-
Product
Roll a feature out to one segment
Turn a flag on for the beta segment or a single customer in LaunchDarkly, then widen the rollout once feedback comes back.
-
Release
Find stale flags ready for cleanup
List flags that have been fully on or fully off for months across every environment, and hand engineering a cleanup list.
-
Support
Confirm what a customer can see
Check whether a customer is targeted by a flag before replying to a ticket, instead of asking an engineer to look it up.
-
AI platform
Tune an AgentControl config in place
Review an AgentControl config in LaunchDarkly, adjust the model or prompt variation, and record why it changed.
-
SRE
Read observability data after a toggle
Pull error and session data from LaunchDarkly for the hour after a flag went on, and decide whether to roll it back.
Try asking
- “Which flags are on in production but off in staging?”
- “Turn on the new checkout flag for the beta segment.”
- “Show error rates since the pricing page flag went live.”
What connecting LaunchDarkly gets you
5 screens from Elaichi, each doing one job for your LaunchDarkly account.
Ask Elaichi to work across your apps.
Which flags are on in production but off in staging?
Turn on the new checkout flag for the beta segment.
Show error rates since the pricing page flag went live.
Also runs in Claude, ChatGPT, Cursor or Microsoft Copilot
The agent
Ask which LaunchDarkly flags are live.
Plain questions, answered from live flags, environments and AgentControl configs in LaunchDarkly.
Copy the endpoint
AI apps
One endpoint reaches LaunchDarkly from any client.
Claude, ChatGPT, Cursor and Microsoft Copilot share one governed endpoint, with no SDK and no shared API key.
Toolboxes
Each team gets its own LaunchDarkly toolbox.
Release engineers manage flags while support reads targeting, each scoped by toolbox.
Shared connections
Teammates use LaunchDarkly without seeing a credential.
One person connects LaunchDarkly, shares it with teams, and nobody else handles a token.
Audit log
Every flag change names who made it.
When, who, what happened and which flag, in an append-only audit log.
From answering questions to doing the work
A trigger starts the work, inside the same permissions and the same audit log as everything else. Workflows, collections and live dashboards come with the Black plan.
LaunchDarkly digest
Run 418 · started 2 minutes ago · on behalf of Emily Carter
-
✓
Schedule
Every weekday at 8:00 AM
0.2s -
✓
Fetch flags
LaunchDarkly
1.4s -
✓
Group by owner
Transform
0.1s -
✓
Draft the digest
Agent step
Ran with 4 tools, returned a structured summary
6.2s -
Approve the digest
Needs approval
Assigned to Jake Morgan
Approve Deny -
Post the digest
LaunchDarkly
Queued
Workflows
A schedule starts flag cleanup, a person approves.
Stale flags are fetched, grouped, drafted into a digest, approved, then posted to LaunchDarkly.
LaunchDarkly health
Refreshed 4 minutes ago · every 15 minutes · from the flags collection
Flags
1,284 ↓ 12%
Segments
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Flags created
Last 14 days
By team
Share of activity
Platform 34%
Web 27%
Mobile 21%
Product 18%
Collections and dashboards
LaunchDarkly flag health, computed without a model.
Four metrics, fourteen days of flags created and a breakdown by team, refreshed on schedule.
Why connect LaunchDarkly's MCP server through Elaichi
LaunchDarkly builds and runs this MCP server. Elaichi sits in front of it, so LaunchDarkly's tools follow the same sign-in, access rules and audit log as every other connector your organization uses. Calls an AI client makes to LaunchDarkly's server directly, outside Elaichi, get none of this.
-
One address for every AI client
Claude, ChatGPT, Cursor and Microsoft Copilot reach LaunchDarkly's tools at the same Elaichi address as every other connected app. Nobody adds LaunchDarkly's server to each client one by one.
-
Each person signs in as themselves
Each person signs in to Elaichi as themselves. Members connect with their own LaunchDarkly sign-in, and a connection someone shares runs on its owner's account. The credential stays in Elaichi's separate credential service, and the AI client holds only its Elaichi sign-in.
-
Rules checked before a call leaves
Restrictions on a role or a person, for the whole connector or a single tool, are checked before a call reaches LaunchDarkly's server. By default, a tool LaunchDarkly does not mark read-only or non-destructive counts as destructive, and over MCP it still runs under the "Use your connected apps" consent.
-
One audit log for every app
Each call that runs is recorded with the person, the tool, the connection and the AI client that made it, in the same audit log as every other app.
-
Tool issues go to LaunchDarkly
LaunchDarkly builds and runs these tools, and Elaichi staff do not curate them, so a report about how a tool behaves goes to the LaunchDarkly team.
For IT and engineering
Elaichi vs Zapier MCP vs Composio for LaunchDarkly
All three can connect LaunchDarkly to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay.
| What to check | Elaichi | Zapier MCP | Composio |
|---|---|---|---|
| Where the AI connects |
One address for the whole organization.
https://api.elaichi.ai/mcp
|
A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. |
| Control over LaunchDarkly tools | Allow or restrict single LaunchDarkly tools, per role or user. | App and action restrictions on the account. | Role permissions, down to the action. |
| Record of calls | One audit entry per LaunchDarkly call. | A History tab of tool calls. | A log of every tool call. |
| Single sign-on | SAML or OIDC, plus SCIM, on Gold. | SAML on Enterprise. | SAML and OIDC on Enterprise. |
| Price | Free for one person; $15 per user per month on Gold. | 2 tasks per successful call. | Billed per tool call. |
Sources: Zapier MCP docs, security, usage; Composio docs, gateway, enterprise, pricing. Checked September 2026.
Longer take: Zapier MCP alternative and when you don't need an MCP gateway.
Questions, answered
How do I connect LaunchDarkly to Claude?
First connect LaunchDarkly in Elaichi, where you sign in to your LaunchDarkly account over OAuth and approve the access, with no OAuth application to register and no client ID or secret to generate. Then open Claude, go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Claude asks you to sign in to Elaichi, and from then on it works with LaunchDarkly as you.
Does LaunchDarkly work with ChatGPT and Cursor as well as Claude?
Yes. Once LaunchDarkly is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, Microsoft Copilot, any other MCP client and the Elaichi Agent. You connect LaunchDarkly once and every client picks it up.
What can an AI agent actually do with my LaunchDarkly data?
It can tell you which feature flags are on in each environment, turn a flag on or off for a segment, review and adjust AgentControl configs, and read observability data such as errors after a rollout. What it can reach depends on what your LaunchDarkly account has set up. Short concrete asks, like naming the flag and the environment, get better results than long sentences.
Does connecting LaunchDarkly give the AI access to every project and environment?
No. Access follows the person who signed in, so the AI sees only the LaunchDarkly projects, environments and flags that person already has permission to see. Elaichi can narrow that further, for example to read-only or to one environment, but it can never widen what LaunchDarkly itself allows.
Can I stop an agent from deleting or changing things in LaunchDarkly?
Yes. In Elaichi, restrictions on the LaunchDarkly connection work per action, so you can allow reading flags while restricting changes, deletions or edits to AgentControl configs. A restricted action still appears in Elaichi's tool search, flagged as restricted, but Claude, ChatGPT, Cursor or Microsoft Copilot cannot run it, whatever the prompt says.
What happens to a LaunchDarkly connection when someone leaves?
Offboarding that person in Elaichi ends their access to LaunchDarkly through every client at once. If they shared a LaunchDarkly connection with a team, it keeps working for everyone else. Disconnecting LaunchDarkly once in Elaichi removes it from Claude, ChatGPT, Cursor, Microsoft Copilot and every other client.
Does the LaunchDarkly MCP connector work with Gemini, Codex, Claude Code or other MCP clients?
Yes. LaunchDarkly is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, Microsoft Copilot, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.
Is Elaichi an alternative to Zapier MCP for LaunchDarkly?
Yes. Both let Claude, ChatGPT or Cursor use LaunchDarkly. Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every LaunchDarkly call.
How is Elaichi different from Composio for LaunchDarkly?
Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to LaunchDarkly: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.
Put LaunchDarkly in front of your team
14 days of Black, no credit card. Connect it once and pick what each team can call.
When the trial ends, nothing is deleted. You move to the free Personal plan, and connections, roles and the audit log stay where they are.
Add one link to your AI app
The same link for everyone on your team.
https://api.elaichi.ai/mcp
ChatGPT
Claude
Cursor
Microsoft Copilot