MoltSets MCP connector
Connect MoltSets to Elaichi and Claude, ChatGPT, Cursor, and the Elaichi Agent can look up people, companies, LinkedIn profiles, business emails, and mobile numbers from your MoltSets account, with every lookup signed in as you and 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 MoltSets to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect MoltSets once
-
Open Connections, choose Add connection, and pick MoltSets.
-
Optionally set Share with to give a team access, then press Connect.
-
Paste a MoltSets API key. One person generates a token in MoltSets 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.
Apollo
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.
MoltSets 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.
MoltSets MCP connector for Claude Code
-
1
In a terminal, run
claude mcp addwith the endpoint.https://api.elaichi.ai/mcp -
2
Start Claude Code and run
/mcp. -
3
Pick elaichi, then sign in and approve in the browser.
Terminal
$ claude mcp add --transport http elaichi --scope user https://api.elaichi.ai/mcp
Use --scope project instead to share it with the repository through .mcp.json.
MoltSets 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.
MoltSets 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 MoltSets 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 MoltSets through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
Sales
Find the right person before you call
Search MoltSets for the decision maker at a target company, then pull their LinkedIn profile and business email in one ask.
-
Sales Development
Turn a LinkedIn URL into a contact
Paste a prospect's LinkedIn profile and get their best business email and mobile number from MoltSets, ready for outreach.
-
Marketing
Build an ad audience from a contact list
Look up the mobile advertising IDs and hashed emails MoltSets holds for a list of contacts, so a matched audience is ready for the ad platform.
-
Revenue Operations
Enrich the record after a form fill
Give the AI an email address from an inbound form and MoltSets returns the person's business profile, title and company.
-
Growth
See which company is visiting the site
Hand over an IP address from web analytics and MoltSets names the company behind it, so anonymous traffic becomes an account to pursue.
-
Finance
Check MoltSets usage before the invoice
Ask how many MoltSets lookups the team has used this month and what the billing shows, without logging into the admin console.
Try asking
- “Find the VP of Sales at Acme and her business email”
- “Which company is behind the IP address 203.0.113.42?”
- “Pull LinkedIn profiles for heads of marketing at fintech startups in Austin”
Compare
Elaichi vs Zapier MCP vs Composio for MoltSets
All three can connect MoltSets 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 MoltSets tools | Allow or restrict single MoltSets 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 MoltSets 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
MoltSets tools for your AI agents
20 tools are ready to call through Elaichi's MCP endpoint the moment you connect MoltSets, 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 MoltSets gets you
6 screens from the product, each doing one job for your MoltSets account.
The agent
Ask for a prospect, get a profile back.
Plain questions return live people, companies, business emails and phones from MoltSets.
- people
- companies
- profiles
- emails
Ask Elaichi to work across your apps.
Find the VP of Sales at Acme and her business email
Which company is behind the IP address 203.0.113.42?
Pull LinkedIn profiles for heads of marketing at fintech startups in Austin
Also runs in Claude, ChatGPT or Cursor
MCP clients
One endpoint puts MoltSets in every client.
Claude, ChatGPT and Cursor reach MoltSets through one org endpoint, no SDK, no shared key.
Copy the endpoint
Tool catalog
20 MoltSets tools, ready with no code.
People, companies, LinkedIn profiles, emails, phones and ad audiences, all cataloged without custom code.
- List all MoltSets search people
- List all MoltSets search companies
- MoltSets linkedin profiles search
- MoltSets linkedin profiles lookup by email
Toolboxes
Each team gets its own MoltSets toolbox.
Sales searches people, Marketing builds ad audiences, Finance sees billing, each from a scoped toolbox.
- Sales
- Sales Development
- Marketing
- Revenue Operations
Shared connections
Share MoltSets without sharing the API key.
One person connects MoltSets, teammates run lookups, and nobody else ever sees the key.
- Sales EMEA
- Sales US
- Outbound
- Marketing
Audit log
Every MoltSets lookup names who ran it.
When, who, what happened and which profile, 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 starts MoltSets work, you approve it.
New MoltSets matches are fetched, grouped, drafted into a digest, approved, then posted back.
MoltSets digest
Run 418 · started 2 minutes ago · on behalf of Emily Carter
-
✓
Schedule
Every weekday at 8:00 AM
0.2s -
✓
Fetch people
MoltSets
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
MoltSets
Queued
Collections and dashboards
MoltSets usage numbers, computed, never asked for.
Four metrics, a 14 day lookup chart and a team breakdown, refreshed on schedule, no model.
MoltSets health
Refreshed 4 minutes ago · every 15 minutes · from the people collection
People
1,284 ↓ 12%
Companies
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
People created
Last 14 days
By team
Share of activity
Sales EMEA 34%
Sales US 27%
Outbound 21%
Marketing 18%
FAQ
Frequently asked questions
How do I connect MoltSets to Claude?
Connect MoltSets in Elaichi by pasting the API key from your MoltSets account 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. Claude signs you in through Elaichi and MoltSets people, company and email lookups are available in your chat.
Does MoltSets work with ChatGPT and Cursor as well as Claude?
Yes. Once MoltSets 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 MoltSets once and every client you use picks it up.
What can an AI agent actually do with my MoltSets data?
It can search MoltSets for people and companies, pull a LinkedIn profile from an email address, and find the business email, personal email or mobile number behind a LinkedIn profile. It can also look up the company behind an IP address, fetch advertising IDs and hashed emails for an ad audience, and show your MoltSets account, billing and usage. Short concrete asks work best, such as a name and a company, or a single LinkedIn URL.
Does connecting MoltSets give the AI everything in my account?
The AI can only run the MoltSets lookups that the connected MoltSets account is entitled to, and each person signs in to Elaichi as themselves. Elaichi can narrow that further, for example keeping mobile phone lookups or billing away from a team, but it can never widen what MoltSets allows.
Can I stop an agent from running certain MoltSets lookups, such as mobile phones or billing?
Yes. MoltSets lookups through Elaichi only search and read, nothing is deleted or changed, but you can still restrict individual actions such as mobile phone lookups, personal email lookups or billing. A restricted MoltSets action is left out of the AI client's tool list entirely and cannot be called, whatever the prompt says.
What happens to a MoltSets connection when someone leaves?
Offboarding a person in Elaichi ends their access to MoltSets at once, in every client they used. A MoltSets connection shared with a team keeps working for everyone else. If you want MoltSets gone completely, disconnecting it once in Elaichi removes it from Claude, ChatGPT, Cursor and every other client.
Does the MoltSets MCP connector work with Gemini, Codex, Claude Code or other MCP clients?
Yes. MoltSets 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 MoltSets?
Yes. Both let Claude, ChatGPT or Cursor use MoltSets. 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 MoltSets call.
How is Elaichi different from Composio for MoltSets?
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 MoltSets: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.
Put MoltSets 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.