Feature Flag
ConfigCat MCP connector
The ConfigCat connector brings feature flag settings, configs, environments, segments and change requests into Elaichi, so Claude, ChatGPT, Cursor and the Elaichi Agent can read and update them inside each person's own ConfigCat access, with every call logged.
-
How it connects. Connects with an API key. The credential goes into a vault nobody reads back.
-
One address. https://api.elaichi.ai/mcp, the same for every user.
-
Their own access. An agent never gets more than the person it acts for.
How to connect
How to connect ConfigCat to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect ConfigCat once
-
Open Connections, choose Add connection, and pick ConfigCat.
-
Optionally set Share with to give a team access, then press Connect.
-
Paste a ConfigCat API key. One person generates a token in ConfigCat and pastes it once. Everyone else works through Share with, and never sees it.
The credential is vaulted. Nobody reads it back, not even the AI.
Add connection
Choose a connector.
In your AI client
Point it at one endpoint
Everyone in the organization uses the same address, and each person only ever reaches what their own account allows.
ConfigCat 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.
ConfigCat 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 today. The plugin directory lives at chatgpt.com/plugins.
ConfigCat 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.
Connect ConfigCat 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.
Use cases
What teams do with ConfigCat through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
Engineering
Clear the change request queue
List the ConfigCat change requests still waiting on a product, read what each one proposes, and approve the ones that are ready without opening a browser tab for each.
-
Product
See every flag in a config
Ask for all the settings in a ConfigCat config and get a plain list of what is live, so a product review starts from the real state rather than a stale spreadsheet.
-
QA
Stand up a new test environment
Create a fresh ConfigCat environment for a release candidate, then check which configs and settings it carries before the test run starts.
-
Platform
Keep proxy profiles up to date
Pull up a ConfigCat proxy profile by name, update the parts that changed, and retire the profiles nobody uses anymore.
-
Customer success
Build a segment for a beta cohort
Create a ConfigCat segment for the customers who asked for early access, so the engineering team can target a flag at exactly those accounts.
-
Release management
Map products, configs and environments
List every ConfigCat product in the organization with its configs and environments, and spot the ones that are missing a staging or production environment.
Try asking
- “Which ConfigCat change requests are still waiting for approval?”
- “List every setting in the Mobile App production config.”
- “Create a Beta customers segment in the Checkout product.”
Compare
Elaichi vs Zapier MCP vs Composio for ConfigCat
All three can connect ConfigCat 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 ConfigCat tools | Allow or restrict single ConfigCat 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 ConfigCat 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 | $15 per user per month. | 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.
AI tools
ConfigCat tools for your AI agents
124 tools are ready to call through Elaichi's MCP endpoint the moment you connect ConfigCat, governed by the same roles, restrictions, and audit log as everything else in Elaichi.
No tools match your search.
See it in Elaichi
What connecting ConfigCat gets you
6 screens from the product, each doing one job for your ConfigCat account.
The agent
Ask about any feature flag in plain language.
Get answers from live ConfigCat configs, environments and change requests, no dashboard digging.
- configs
- environments
- segments
- change requests
Ask Elaichi to work across your apps.
Which ConfigCat change requests are still waiting for approval?
List every setting in the Mobile App production config.
Create a Beta customers segment in the Checkout product.
Also runs in Claude, ChatGPT or Cursor
MCP clients
One ConfigCat endpoint for every MCP client.
Claude, ChatGPT and Cursor share one governed endpoint, no SDK and no shared API key.
Copy the endpoint
Tool catalog
124 ConfigCat tools, ready without writing code.
Settings, configs, environments, segments, products and change requests covered, no custom code required.
- Get single ConfigCat change request by ID
- Update a ConfigCat change request by ID
- ConfigCat change requests approve
- Get single ConfigCat proxy profile by ID
Toolboxes
Every team gets its own ConfigCat toolbox.
Scope what Engineering, Product and QA can reach in ConfigCat, team by team.
- Engineering
- Product
- QA
- Platform
Shared connections
Share one ConfigCat connection, never the key.
Teammates work through the connection while the API key stays with whoever connected it.
- Engineering
- Product
- QA
- Platform
Audit log
Know who changed which flag, and when.
Every ConfigCat call lands in an append-only log with actor, action, type and resource.
- When
- Who
- What happened
- Type
Launching soon
From answering questions to doing the work
A person no longer has to ask. A trigger starts the work, inside the same permissions and the same audit log as everything else. Automations and live dashboards are launching soon, on the Black plan.
Automations
A schedule turns pending change requests into action.
Pending ConfigCat change requests are fetched, grouped, drafted into a digest, approved, then posted back.
ConfigCat digest
Run 418 · started 2 minutes ago · on behalf of Emily Carter
-
✓
Schedule
Every weekday at 8:00 AM
0.2s -
✓
Fetch configs
ConfigCat
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 Michael Brennan
Approve Deny -
Post the digest
ConfigCat
Queued
Collections and dashboards
ConfigCat health, computed on a schedule, no model.
Four metrics, a 14 day chart of settings created, and a breakdown by team.
ConfigCat health
Refreshed 4 minutes ago · every 15 minutes · from the configs collection
Configs
1,284 ↓ 12%
Environments
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Configs created
Last 14 days
By team
Share of activity
Engineering 34%
Product 27%
QA 21%
Platform 18%
Related connectors
More from the catalog
FAQ
Frequently asked questions
How do I connect ConfigCat to Claude?
Connect ConfigCat in Elaichi first, which asks for a ConfigCat API key and nothing else, so there is no OAuth application to register and no client ID or secret to generate. Then in Claude go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp as the endpoint. Claude signs you in through Elaichi and your ConfigCat products, configs and change requests are available from the next conversation.
Does ConfigCat work with ChatGPT and Cursor as well as Claude?
Yes. Once ConfigCat is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any other MCP client and the Elaichi Agent. You connect ConfigCat once and every client picks it up.
What can an AI agent actually do with my ConfigCat data?
An agent can list your ConfigCat products, configs, environments and segments, show every setting in a config, and pull up a single change request or proxy profile by ID. It can also create environments, configs and segments, update or approve change requests, and update or delete proxy profiles and products. Short concrete asks, like naming the product and environment you mean, get better results than long sentences.
Does connecting ConfigCat give the AI access to every product and environment?
No. Every call runs inside the access of the person who signed in, so the AI sees the ConfigCat organizations, products and environments that person's API key already reaches and nothing more. Elaichi can narrow that further with roles and restrictions, and it can never widen it beyond what ConfigCat itself allows.
Can I stop an agent from deleting or changing things in ConfigCat?
Yes. Restrictions in Elaichi apply per action, so you can leave reading ConfigCat settings and change requests open while blocking deletes of products or proxy profiles, or blocking approvals entirely. A restricted action is never advertised to Claude, ChatGPT or any other client, so no prompt can reach it.
What happens to a ConfigCat connection when someone leaves?
Offboarding a person in Elaichi ends their access to ConfigCat at once, in every client they used. A shared ConfigCat connection keeps working for everyone else on the team. If you want ConfigCat gone altogether, disconnecting it once in Elaichi removes it from Claude, ChatGPT, Cursor and every other client at the same time.
Does the ConfigCat MCP connector work with Gemini, Codex, Claude Code or other MCP clients?
Yes. ConfigCat 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, 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 ConfigCat?
Yes. Both let Claude, ChatGPT or Cursor use ConfigCat. 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 ConfigCat call.
How is Elaichi different from Composio for ConfigCat?
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 ConfigCat: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.
Put ConfigCat in front of your team
14 days on Gold, no credit card. Connect it once and pick what each team can call.
- Works with
-
and any other MCP client, or the Elaichi Agent.
- When the trial ends
- Nothing is deleted. Connections, roles and the audit log stay where they are, so subscribing picks up exactly where you left off.