Close MCP connector
The Close connector brings leads, contacts, opportunities, calls, emails, and notes from Close into Claude, ChatGPT, Cursor, and the Elaichi Agent, so each person can ask about their pipeline inside their own Close access, with every request logged.
-
How it connects. Connects over OAuth. 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 Close to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect Close once
-
Open Connections, choose Add connection, and pick Close.
-
Optionally set Share with to give a team access, then press Connect.
-
Approve it in Close. Close's own window opens. Whoever approves it decides what this connection can reach.
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.
Close 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.
Close 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.
Close 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 Close 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 Close through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
Sales
Prep for a call in one question
Ask for everything on a lead before you dial: the contacts, the open opportunity, the last email thread, and the notes your colleague left. The answer comes from live Close records, not a stale export.
-
Sales
Review what happened on yesterday's calls
Pull the meeting transcripts and call records from the day and get a summary of what each prospect said, what they objected to, and what you promised to send.
-
Sales development
Work a smart view without clicking through it
Ask which leads in a saved smart view have had no activity this week, which status they sit in, and who owns them, then decide where to spend the morning.
-
Sales leadership
Get a pipeline picture before the Monday meeting
Ask how many opportunities sit in each status, which ones moved since last week, and which have gone quiet, totaled by rep or by month.
-
Customer success
Catch up on an account before renewal
Read the full history of a lead in Close, including emails, notes, calls, and tasks, and get a short account summary before you reach out.
-
Finance
Check invoices against closed deals
Look up the invoices attached to a lead in Close, compare them with the won opportunities, and spot anything billed late or not at all.
Try asking
- “Which opportunities in the Q3 pipeline haven't had a call this week?”
- “Summarize yesterday's meeting transcript with Acme and list the follow-ups”
- “Show me leads in the Trial ending soon smart view”
Compare
Elaichi vs Zapier MCP vs Composio for Close
All three can connect Close 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 Close tools | Allow or restrict single Close 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 Close 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
Close tools for your AI agents
121 tools are ready to call through Elaichi's MCP endpoint the moment you connect Close, governed by the same roles, restrictions, and audit log as everything else in Elaichi. Close builds and runs these tools.
No tools match your search.
See it in Elaichi
What connecting Close gets you
6 screens from the product, each doing one job for your Close account.
The agent
Ask about your pipeline, get answers from Close.
Live leads, opportunities, and call notes, answered in plain language.
- leads
- contacts
- opportunities
- calls
Ask Elaichi to work across your apps.
Which opportunities in the Q3 pipeline haven't had a call this week?
Summarize yesterday's meeting transcript with Acme and list the follow-ups
Show me leads in the Trial ending soon smart view
Also runs in Claude, ChatGPT or Cursor
MCP clients
Close works in every client through one endpoint.
Claude, ChatGPT, and Cursor connect to Close over OAuth, with no SDK or shared API key.
Copy the endpoint
Tool catalog
121 Close tools, ready without writing code.
Leads, contacts, opportunities, calls, emails, notes, and tasks, covered with no custom code.
- Activity search
- Aggregation
- Close product knowledge search
- Customized builtin labels
Toolboxes
Every team gets its own Close toolbox.
Sales, finance, and success each see the Close tools that fit their work.
- Sales
- Sales development
- Customer success
- Finance
Shared connections
Share Close access, never share a credential.
One person connects Close; teammates work through it without seeing a login.
- Sales EMEA
- Sales US
- Outbound
- Customer success
Audit log
Every Close request is logged with a name.
When, who, and which lead or opportunity was touched, kept 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 Close activity into real work.
Calls and emails are fetched, grouped, drafted into a digest, approved, and posted back to Close.
Close digest
Run 418 · started 2 minutes ago · on behalf of Emily Carter
-
✓
Schedule
Every weekday at 8:00 AM
0.2s -
✓
Fetch leads
Close
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
Close
Queued
Collections and dashboards
Close pipeline health, computed without a model.
Leads created over 14 days, broken down by team, refreshed on a schedule.
Close health
Refreshed 4 minutes ago · every 15 minutes · from the leads collection
Leads
1,284 ↓ 12%
Contacts
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Leads created
Last 14 days
By team
Share of activity
Sales EMEA 34%
Sales US 27%
Outbound 21%
Customer success 18%
Related connectors
More from the catalog
FAQ
Frequently asked questions
How do I connect Close to Claude?
Connect Close in Elaichi first. Close connects over OAuth, so you sign in to Close with your normal login and approve the access; there is 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 will ask you to sign in to Elaichi and Close is ready to use.
Does Close work with ChatGPT and Cursor as well as Claude?
Yes. Once Close 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 Close once and every client picks it up.
What can an AI agent actually do with my Close data?
It can find leads, contacts, and opportunities in Close, read the calls, emails, notes, tasks, meeting transcripts, and invoices attached to them, and summarize what it finds. It can also total things up, such as opportunities by status or activity by rep, and look at your saved smart views and lead statuses. Short, specific asks tend to work better than long paragraphs, for example a lead name and the question you have about it.
Does connecting Close give the AI access to every lead in my organization?
No. Each person signs in to Close as themselves, so the agent sees only the leads, contacts, and opportunities that person can already see in Close. Elaichi can narrow that further by role or by action, but it can never widen access beyond what Close itself allows the signed-in person.
Can I stop an agent from deleting or changing things in Close?
Yes. Restrictions in Elaichi work per action, so you can allow reading leads and opportunities while blocking anything that edits or removes records in Close. A restricted action is never shown to Claude, ChatGPT, or any other client at all, so no prompt, however worded, can reach it.
What happens to a Close connection when someone leaves?
Offboarding that person in Elaichi ends their access to Close through every connected client at once, including Claude, ChatGPT, Cursor, and the Elaichi Agent. A Close connection they shared with a team keeps working for everyone else. If you want Close gone entirely, disconnecting it once in Elaichi removes it from every client.
Does the Close MCP connector work with Gemini, Codex, Claude Code or other MCP clients?
Yes. Close 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 Close?
Yes. Both let Claude, ChatGPT or Cursor use Close. 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 Close call.
How is Elaichi different from Composio for Close?
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 Close: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.
Put Close 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.