Unipile MCP connector
Connect Unipile to Elaichi and Claude, ChatGPT, Cursor and any MCP client can browse Unipile's API endpoints, read their details, and run requests against your messaging accounts as you, 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 Unipile to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect Unipile once
-
Open Connections, choose Add connection, and pick Unipile.
-
Optionally set Share with to give a team access, then press Connect.
-
Paste an Unipile API key. One person generates a token in Unipile 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.
Unipile 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.
Unipile 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.
Unipile 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 Unipile 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 Unipile through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
Engineering
Find the right Unipile endpoint fast
Ask which Unipile endpoint lists chats for a LinkedIn account and get the endpoint, its parameters and an example back in plain language, without opening the reference docs.
-
Sales
Pull up a conversation before a call
Ask for the last messages exchanged with a prospect across the LinkedIn and email accounts connected in Unipile, so the rep walks into the call already caught up.
-
Recruiting
Check replies across every inbox
Ask which candidates answered this week across the messaging accounts in Unipile and get one list back instead of checking each account by hand.
-
Support
Reproduce a customer's failing request
Look up the endpoint a customer is calling, confirm the required fields, and run the same request through Unipile to see what actually comes back.
-
Product
Map what Unipile can do before building
Search the Unipile endpoint catalog by keyword, read what each one accepts and returns, and decide what the next feature can rely on.
-
Operations
Confirm connected accounts and settings
Ask which messaging accounts are connected in Unipile and what server variables are set for your workspace, then catch anything that has drifted.
Try asking
- “Find the Unipile endpoint for listing chats on a LinkedIn account.”
- “Pull the last ten messages from our sales inbox in Unipile.”
- “Show me what fields the Unipile send message endpoint needs.”
Native MCP
Why connect Unipile's MCP server through Elaichi
Unipile builds and runs this MCP server. Elaichi sits in front of it, so Unipile'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 Unipile's server directly, outside Elaichi, get none of this.
-
One address for every AI client
Claude, ChatGPT and Cursor reach Unipile's tools at https://api.elaichi.ai/mcp, the same address as every other connected app. Nobody adds Unipile'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 Unipile 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 Unipile's server. By default, a tool Unipile does not mark read-only or non-destructive counts as destructive, and over MCP it needs the "Delete data and remove access" 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 Unipile
Unipile builds and runs these tools, and Elaichi staff do not curate them, so a report about how a tool behaves goes to the Unipile team.
Compare
Elaichi vs Zapier MCP vs Composio for Unipile
All three can connect Unipile 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 Unipile tools | Allow or restrict single Unipile 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 Unipile 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
Unipile tools for your AI agents
5 tools are ready to call through Elaichi's MCP endpoint the moment you connect Unipile, governed by the same roles, restrictions, and audit log as everything else in Elaichi. Unipile builds and runs these tools.
No tools match your search.
See it in Elaichi
What connecting Unipile gets you
6 screens from the product, each doing one job for your Unipile account.
The agent
Ask about Unipile endpoints in plain language.
Get endpoint details, server variables and live request results without reading the docs.
- endpoints
- requests
- server variables
- accounts
Ask Elaichi to work across your apps.
Find the Unipile endpoint for listing chats on a LinkedIn account.
Pull the last ten messages from our sales inbox in Unipile.
Show me what fields the Unipile send message endpoint needs.
Also runs in Claude, ChatGPT or Cursor
MCP clients
Unipile in Claude, ChatGPT and Cursor at once.
One governed endpoint, no SDK and no shared API key handed around.
Copy the endpoint
Tool catalog
All 5 Unipile tools, no code written.
Browse, search and run Unipile API endpoints from any MCP client.
- List API Endpoints
- Get Endpoint Details
- Search API Endpoints
- Execute API Request
Toolboxes
Every team gets its own Unipile toolbox.
Sales, recruiting and engineering each see only the Unipile actions they need.
- Engineering
- Sales
- Recruiting
- Support
Shared connections
Share Unipile without sharing the API key.
One person connects, teams work through it, and nobody else sees the credential.
- Engineering
- Sales EMEA
- Sales US
- Recruiting
Audit log
Every Unipile request is on the record.
Who ran which endpoint, when, and against what, 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 runs the Unipile work itself.
Messages are fetched, grouped and summarized, a person approves, then it posts back.
Unipile digest
Run 418 · started 2 minutes ago · on behalf of Emily Carter
-
✓
Schedule
Every weekday at 8:00 AM
0.2s -
✓
Fetch endpoints
Unipile
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
Unipile
Queued
Collections and dashboards
Unipile request health, computed without a model.
Four metrics, a 14 day chart and a team breakdown, refreshed on schedule.
Unipile health
Refreshed 4 minutes ago · every 15 minutes · from the endpoints collection
Endpoints
1,284 ↓ 12%
Requests
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Endpoints created
Last 14 days
By team
Share of activity
Engineering 34%
Sales EMEA 27%
Sales US 21%
Recruiting 18%
FAQ
Frequently asked questions
How do I connect Unipile to Claude?
Two steps. In Elaichi, add Unipile and paste your Unipile API key when asked, there is no OAuth application to register and no client ID or secret to generate. Then in Claude open Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Sign in to Elaichi when prompted and Unipile is available in Claude.
Does Unipile work with ChatGPT and Cursor as well as Claude?
Yes. Once Unipile is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any MCP client and the Elaichi Agent. You connect Unipile once and every client picks it up.
What can an AI agent actually do with my Unipile data?
An agent can list and search the endpoints in the Unipile API, read what each one needs and returns, check your server variables, and run requests against your connected messaging accounts, for example fetching recent chats or messages. Short concrete asks like "list the chats on our LinkedIn account" work better than long sentences.
Does connecting Unipile give the AI everything in my messaging accounts?
No. Every request to Unipile runs under the API key and person who signed in, so the agent can only reach the accounts and endpoints that key already covers. Elaichi can narrow that further by restricting which actions are allowed, and it never widens access beyond what Unipile itself permits.
Can I stop an agent from sending messages or changing things in Unipile?
Yes. Restrictions in Elaichi work per action, so you can allow browsing endpoints and reading details while blocking the ability to run requests against Unipile. A restricted action is left out of the AI client's tool list entirely and cannot be called, whatever the prompt says.
What happens to a Unipile connection when someone leaves?
Offboarding that person in Elaichi ends their access to Unipile at once, across Claude, ChatGPT, Cursor and every other client. A shared Unipile connection keeps working for everyone else on the team. If you want it gone entirely, disconnecting Unipile once in Elaichi removes it from every client.
Does the Unipile MCP connector work with Gemini, Codex, Claude Code or other MCP clients?
Yes. Unipile 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 Unipile?
Yes. Both let Claude, ChatGPT or Cursor use Unipile. 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 Unipile call.
How is Elaichi different from Composio for Unipile?
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 Unipile: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.
Put Unipile 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.