Product Development
AppFollow MCP connector
Connect AppFollow to Elaichi and Claude, ChatGPT, Cursor, or the Elaichi Agent can read app store reviews, reply to them, tag them, and track reply speed, all inside each person's own AppFollow access.
-
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 AppFollow to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect AppFollow once
-
Open Connections, choose Add connection, and pick AppFollow.
-
Optionally set Share with to give a team access, then press Connect.
-
Paste an AppFollow API key. One person generates a token in AppFollow 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.
AppFollow 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.
AppFollow 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.
AppFollow 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 AppFollow 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 AppFollow through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
Support
Reply to new one-star reviews
Pull up the reviews that came in overnight, draft a reply in the right tone, and post it to AppFollow without leaving the conversation. Mark each review as handled once the reply goes out.
-
Product
Read the week's review themes
Ask for the AI summary of reviews on a given app and see which complaints and requests are growing. Check the semantic tags to find out whether sign-in, crashes, or pricing is driving the noise.
-
Engineering
Link crash complaints to the bug tracker
Find reviews that mention a crash or a broken screen, attach a bug tracker reference to each one in AppFollow, and add a note so the next person knows it is already being looked at.
-
Marketing
Pull featured reviews for a launch
List the featured reviews for an app and collect the quotable ones for a store page, a release note, or a social post.
-
Community
Triage reviews after an update
After a release, tag incoming reviews, set their status, and report the ones that break store rules so the backlog is clean before the weekly standup.
-
Operations
Check reply speed across apps
Ask how many reviews got a reply last month and how long it took, per app, then set up new apps, collections, and user accounts in AppFollow as the team grows.
Try asking
- “Summarize this week's one-star reviews for our iOS app”
- “Draft replies to unanswered reviews mentioning login problems”
- “How fast did support reply to reviews last month?”
Compare
Elaichi vs Zapier MCP vs Composio for AppFollow
All three can connect AppFollow 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 AppFollow tools | Allow or restrict single AppFollow 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 AppFollow 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
AppFollow tools for your AI agents
43 tools are ready to call through Elaichi's MCP endpoint the moment you connect AppFollow, 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 AppFollow gets you
6 screens from the product, each doing one job for your AppFollow account.
The agent
Ask about your app reviews in plain language.
Answers come from live AppFollow reviews, summaries, and reply stats, not a stale export.
- reviews
- apps
- collections
- users
Ask Elaichi to work across your apps.
Summarize this week's one-star reviews for our iOS app
Draft replies to unanswered reviews mentioning login problems
How fast did support reply to reviews last month?
Also runs in Claude, ChatGPT or Cursor
MCP clients
Use AppFollow from Claude, ChatGPT, or Cursor.
One governed endpoint for the whole organization, no SDK and no shared API key.
Copy the endpoint
Tool catalog
43 AppFollow tools, ready with no code.
Reviews, replies, tags, summaries, apps, collections, and users, covered without writing a connector.
- List all AppFollow collections
- Create a AppFollow collection
- AppFollow collections bulk delete
- List all AppFollow apps
Toolboxes
Every team gets its own AppFollow toolbox.
Support handles replies, product reads summaries, admins manage apps and users, each scoped.
- Support
- Product
- Engineering
- Marketing
Shared connections
Share one AppFollow connection without sharing the key.
Teammates reply to reviews through a shared connection and never see the API key.
- Support
- Product
- Marketing
- Engineering
Audit log
Every AppFollow reply and tag is logged.
See who replied to which review, when, and what changed, in an append-only log.
- 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 new reviews into a digest.
New AppFollow reviews are fetched, grouped, drafted into a digest, approved, then posted back.
AppFollow digest
Run 418 · started 2 minutes ago · on behalf of Emily Carter
-
✓
Schedule
Every weekday at 8:00 AM
0.2s -
✓
Fetch reviews
AppFollow
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
AppFollow
Queued
Collections and dashboards
AppFollow review health, computed on a schedule.
Four metrics, 14 days of new reviews, and a team breakdown, with no model involved.
AppFollow health
Refreshed 4 minutes ago · every 15 minutes · from the reviews collection
Reviews
1,284 ↓ 12%
Apps
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Reviews created
Last 14 days
By team
Share of activity
Support 34%
Product 27%
Marketing 21%
Engineering 18%
Related connectors
More from the catalog
FAQ
Frequently asked questions
How do I connect AppFollow to Claude?
Two steps. In Elaichi, open the AppFollow connector and paste your AppFollow API key, which you copy from your AppFollow account settings; 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. Sign in with your Elaichi account and AppFollow is available in the chat.
Does AppFollow work with ChatGPT and Cursor as well as Claude?
Yes. Once AppFollow 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 AppFollow once and every client picks it up.
What can an AI agent actually do with my AppFollow data?
With AppFollow connected, an agent can list reviews for an app, read the AI summary and semantic tags for a period, draft and post replies, update tags, statuses, and notes, attach bug tracker references, and report reviews that break store rules. It can also tell you how many reviews got a reply and how quickly, and set up apps, collections, and users in AppFollow. Short, concrete asks such as "reply to the new two-star reviews on the Android app" work better than long instructions.
Does connecting AppFollow give the AI access to every app and collection?
No. Every call to AppFollow runs under the person who signed in, so the agent sees only the apps, collections, and reviews that person can already see in AppFollow. Elaichi can narrow that further with restrictions, but it can never widen it beyond what the person's own AppFollow account allows.
Can I stop an agent from deleting or changing things in AppFollow?
Yes. Restrictions in Elaichi apply per action, so you can allow reading AppFollow reviews and posting replies while blocking anything that deletes apps, collections, or users. A restricted action is never advertised to Claude, ChatGPT, or any other client, so no prompt can reach it.
What happens to an AppFollow connection when someone leaves?
Offboarding that person in Elaichi ends their access to AppFollow through every client at once. If they had shared an AppFollow connection with a team, it keeps working for everyone else. If you want AppFollow gone entirely, disconnecting it once in Elaichi removes it from Claude, ChatGPT, Cursor, and every other client.
Does the AppFollow MCP connector work with Gemini, Codex, Claude Code or other MCP clients?
Yes. AppFollow 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 AppFollow?
Yes. Both let Claude, ChatGPT or Cursor use AppFollow. 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 AppFollow call.
How is Elaichi different from Composio for AppFollow?
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 AppFollow: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.
Put AppFollow 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.