Charlie MCP connector
The Charlie connector brings team members, teams, offices, leave requests, leave allowances, salaries and bank accounts from Charlie into Claude, ChatGPT, Cursor and any MCP client, with every question answered inside the access of the person asking.
-
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 Charlie to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect Charlie once
-
Open Connections, choose Add connection, and pick Charlie.
-
Optionally set Share with to give a team access, then press Connect.
-
Paste a Charlie API key. One person generates a token in Charlie 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.
Charlie 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.
Charlie 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.
Charlie 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 Charlie 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 Charlie through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
People
See who is off next week
Ask which team members have leave booked over a given week, and get the list pulled straight from the leave requests in Charlie instead of clicking through each person's profile.
-
Managers
Check remaining leave before saying yes
Before approving a holiday request, ask how much allowance a team member has left this year and what they have already booked, all read live from Charlie.
-
Finance
Reconcile payroll against Charlie salaries
Pull the current salary records and bank account details held in Charlie for the people on this month's payroll run, and spot anything that does not match what the payroll provider has.
-
People
Log a note after a one to one
After a catch up, tell the agent what was discussed and it adds a note to that team member's record in Charlie, filed under the right note type.
-
Operations
Know who sits in which office
Ask for a headcount by office, or a list of everyone based at a particular location, using the offices and team member records kept in Charlie.
-
Leadership
Headcount and team shape on demand
Get a breakdown of team members by team, see how each team has grown, and answer board questions from the teams and people data in Charlie without asking someone to export a spreadsheet.
Try asking
- “Which team members have leave requests approved next week?”
- “Show leave allowances remaining for the London office.”
- “List teams with more than five open leave requests.”
Compare
Elaichi vs Zapier MCP vs Composio for Charlie
All three can connect Charlie 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 Charlie tools | Allow or restrict single Charlie 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 Charlie 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
Charlie tools for your AI agents
22 tools are ready to call through Elaichi's MCP endpoint the moment you connect Charlie, 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 Charlie gets you
6 screens from the product, each doing one job for your Charlie account.
The agent
Ask about leave and headcount, get answers.
Questions in plain language, answered from live Charlie team members and leave requests.
- team members
- leave requests
- leave allowances
- salaries
Ask Elaichi to work across your apps.
Which team members have leave requests approved next week?
Show leave allowances remaining for the London office.
List teams with more than five open leave requests.
Also runs in Claude, ChatGPT or Cursor
MCP clients
Claude, ChatGPT and Cursor read Charlie.
One org MCP endpoint over OAuth, no SDK and no shared API key.
Copy the endpoint
Tool catalog
22 Charlie tools work on day one.
Team members, teams, salaries, offices and leave requests, with no custom code.
- List all Charlie company
- List all Charlie leave allowances
- List all Charlie leave requests
- Get single Charlie leave request by ID
Toolboxes
Each team gets its own Charlie toolbox.
People Ops, Finance and managers see the Charlie tools their work needs.
- People Ops
- Finance
- Engineering
- Recruiting
Shared connections
Teammates use Charlie without seeing credentials.
Every connection shows who connected it and which teams and members share it.
- People Ops
- Finance
- Engineering
- Managers
Audit log
Every Charlie call is on the record.
When, who, what happened, type and resource, 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 Charlie leave into a digest.
Six steps fetch leave requests, group them, draft, wait for approval, then post back.
Charlie digest
Run 418 · started 2 minutes ago · on behalf of Emily Carter
-
✓
Schedule
Every weekday at 8:00 AM
0.2s -
✓
Fetch team members
Charlie
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
Charlie
Queued
Collections and dashboards
Charlie headcount and leave, counted on schedule.
Four metrics, 14 days of records created and a team breakdown, no model involved.
Charlie health
Refreshed 4 minutes ago · every 15 minutes · from the team members collection
Team members
1,284 ↓ 12%
Leave requests
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Team members created
Last 14 days
By team
Share of activity
People Ops 34%
Finance 27%
Engineering 21%
Managers 18%
Related connectors
More from the catalog
FAQ
Frequently asked questions
How do I connect Charlie to Claude?
Connect Charlie in Elaichi first: open the Charlie connector, paste in an API key generated from your Charlie account, and save. 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 the endpoint https://api.elaichi.ai/mcp. Sign in as yourself and Charlie is available in Claude.
Does Charlie work with ChatGPT and Cursor as well as Claude?
Yes. Once Charlie 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 Charlie once and every client you use picks it up.
What can an AI agent actually do with my Charlie data?
With Charlie connected, an agent can look up team members, teams and offices, list leave requests and remaining leave allowances, and read the salary and bank account records your role allows you to see. It can also add a note to a team member's record and set up new note types. It cannot approve leave, change salaries or edit people's details, because the Charlie connector does not offer those actions.
Does connecting Charlie give the AI access to everyone's salary and bank details?
No. Every call to Charlie runs under the access of the person who signed in, so an agent only sees the team members, salaries and bank accounts that person could already open in Charlie. Elaichi can narrow that further, for example hiding salary and bank account records from a manager's toolbox, but it can never grant anything the person does not already have in Charlie.
Can I stop an agent from changing things in Charlie?
Yes. The Charlie connector is mostly read only, and the only actions that write anything, adding team member notes and note types, can be switched off per action in Elaichi. A blocked action is never shown to Claude, ChatGPT or any other client, so no prompt can reach it, and the connector has no way to delete anything in Charlie at all.
What happens to a Charlie connection when someone leaves?
When you offboard someone in Elaichi, their access to Charlie through every AI client ends immediately, and a shared Charlie connection keeps working for everyone else on the team. If you want to remove Charlie entirely, disconnecting it once in Elaichi removes it from Claude, ChatGPT, Cursor and every other client at the same time.
Does the Charlie MCP connector work with Gemini, Codex, Claude Code or other MCP clients?
Yes. Charlie 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 Charlie?
Yes. Both let Claude, ChatGPT or Cursor use Charlie. 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 Charlie call.
How is Elaichi different from Composio for Charlie?
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 Charlie: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.
Put Charlie 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.