Gem MCP connector
Connect Gem to Elaichi and Claude, ChatGPT, Cursor, or any MCP client can look up candidates, jobs, projects, pipelines and outreach in Gem as the signed-in person, with every call 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 Gem to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect Gem once
-
Open Connections, choose Add connection, and pick Gem.
-
Optionally set Share with to give a team access, then press Connect.
-
Approve it in Gem. Gem'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.
Gem 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.
Gem 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.
Gem 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 Gem 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 Gem through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
Recruiting
Catch up on a candidate before the call
Ask where a candidate sits in the pipeline, which project they came from and what the last outreach said. After the conversation, have a note added to their record in Gem.
-
Sourcing
See which sequences are getting replies
Ask which outreach sequences in Gem are getting replies this week and which projects are running dry, so you know where to spend the afternoon.
-
Hiring managers
Check the pipeline for your open role
Ask how many candidates are at each stage for your job and who has been waiting longest, without opening Gem yourself.
-
Talent operations
Spot stalled candidates across every project
Ask for candidates who have not moved stage in two weeks, grouped by recruiter, and send the list to the people who own them.
-
Coordinators
Leave a note after the debrief
Once the interview panel has decided, ask the agent to add a note to the candidate in Gem with the decision and the next step.
-
Leadership
Get a weekly hiring summary in plain words
Ask for open jobs, pipeline counts by stage and offers out across Gem, written up and ready to paste into the Monday update.
Try asking
- “Which candidates in the Backend Engineer project haven't replied to outreach?”
- “Who has been at onsite stage longer than two weeks?”
- “Add a note to Priya Shah: strong debrief, moving to offer.”
Compare
Elaichi vs Zapier MCP vs Composio for Gem
All three can connect Gem 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 Gem tools | Allow or restrict single Gem 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 Gem 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.
See it in Elaichi
What connecting Gem gets you
5 screens from the product, each doing one job for your Gem account.
The agent
Ask Gem questions in plain language.
Get answers from live candidates, projects and pipelines in Gem, no report to build.
- candidates
- jobs
- projects
- pipelines
Ask Elaichi to work across your apps.
Which candidates in the Backend Engineer project haven't replied to outreach?
Who has been at onsite stage longer than two weeks?
Add a note to Priya Shah: strong debrief, moving to offer.
Also runs in Claude, ChatGPT or Cursor
MCP clients
One governed endpoint for Claude, ChatGPT and Cursor.
Every client reaches Gem through one org endpoint, no SDK and no shared API key.
ElaichiMCP clientsClaude
ChatGPT
Cursor
Copy the endpoint
Toolboxes
Each team gets its own Gem toolbox.
Sourcing, recruiting and hiring managers each work from a toolbox scoped to their role.
- Recruiting
- Sourcing
- Hiring managers
- Talent operations
ElaichiToolboxesShared connections
Share one Gem connection, never a credential.
Teammates work through the account you connected and never see a password or token.
- Engineering recruiting
- GTM recruiting
- Sourcing EMEA
- Sourcing US
ElaichiConnectionsAudit log
Every Gem call is logged with a name.
See who looked up which candidate, when, and what changed, in one append-only log.
- When
- Who
- What happened
- Type
ElaichiAudit logLaunching 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 the work, a person approves.
Candidates from Gem are fetched, grouped, drafted into a digest, approved, then posted back.
Gem digest
Run 418 · started 2 minutes ago · on behalf of Emily Carter
-
✓
Schedule
Every weekday at 8:00 AM
0.2s -
✓
Fetch candidates
Gem
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
Gem
Queued
Collections and dashboards
Gem pipeline health, computed without a model.
Four metrics, fourteen days of candidates created and a split by team, refreshed on schedule.
Gem health
Refreshed 4 minutes ago · every 15 minutes · from the candidates collection
Candidates
1,284 ↓ 12%
Jobs
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Candidates created
Last 14 days
By team
Share of activity
Engineering recruiting 34%
GTM recruiting 27%
Sourcing EMEA 21%
Sourcing US 18%
Related connectors
More from the catalog
FAQ
Frequently asked questions
How do I connect Gem to Claude?
Open Gem in the Elaichi catalog, choose Connect and sign in to Gem in the window that opens. Gem asks you to approve the access, and that is the whole step: there is no client ID or secret to generate. Then in Claude go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Sign in to Elaichi when Claude asks and Gem is available in your next conversation.
Does Gem work with ChatGPT and Cursor as well as Claude?
Yes. Gem is connected once in Elaichi and the same endpoint, https://api.elaichi.ai/mcp, is pasted into Claude, ChatGPT, Cursor or any other MCP client. The Elaichi Agent uses it too, so there is nothing separate to set up per client.
What can an AI agent actually do with my Gem data?
Once Gem is connected, you can ask about candidates, jobs, projects, pipeline stages, sourcing and outreach sequences in plain language and get answers from what is in Gem right now. Some changes are supported as well, such as adding a note to a candidate. Short, concrete asks work best: name the candidate, the job or the project rather than describing them in a long sentence.
Does connecting Gem give the AI everything in my Gem account?
No. Every request to Gem runs as the person who signed in, so the agent sees only the candidates, projects and jobs that person can already see in Gem. Elaichi can narrow that further with roles and restrictions, and it can never widen it beyond what Gem itself allows that person.
Can I stop an agent from changing or deleting things in Gem?
Yes. Restrictions in Elaichi apply per action, so you can allow reading candidates and pipelines in Gem while blocking adding notes or any other change. A restricted action is never advertised to Claude, ChatGPT or Cursor at all, so no prompt, however it is worded, can reach it.
What happens to a Gem connection when a recruiter leaves?
Offboarding that person in Elaichi ends their access to Gem through every client at once. A Gem connection shared with the team keeps working for everyone else. If you want it gone entirely, disconnecting Gem once in Elaichi removes it from Claude, ChatGPT, Cursor and every other client at the same time.
Does the Gem MCP connector work with Gemini, Codex, Claude Code or other MCP clients?
Yes. Gem 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 Gem?
Yes. Both let Claude, ChatGPT or Cursor use Gem. 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 Gem call.
How is Elaichi different from Composio for Gem?
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 Gem: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.
Put Gem 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.