Dvinci MCP connector
The Dvinci connector brings applications, attachments, hiring requests and application history into Claude, ChatGPT, Cursor and the Elaichi Agent, so recruiters can ask about candidates and move them forward inside their own Dvinci access.
-
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 Dvinci to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect Dvinci once
-
Open Connections, choose Add connection, and pick Dvinci.
-
Optionally set Share with to give a team access, then press Connect.
-
Paste a Dvinci API key. One person generates a token in Dvinci 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.
Dvinci 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.
Dvinci 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.
Dvinci 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.
Dvinci 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 Dvinci 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 Dvinci through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
Recruiting
Catch an application up after a screening call
Tell the agent what came out of the call and it updates the application in Dvinci and adds a history entry, so the next person to open it sees the full story.
-
Recruiting
Move candidates to the next stage in bulk
Ask for everyone in a job opening still at phone screen, then change their status or move them to another job opening without clicking through each one.
-
Hiring managers
See where every applicant for my role stands
Ask which applications are open for your job opening, how long each has been waiting, and what the last history entry says.
-
HR
Raise a hiring request without the form
Describe the role, team and start date, and the agent creates the hiring request in Dvinci. Later, ask for its history to see where approval sits.
-
Talent acquisition
Pull the CV before the interview
Ask for the attachments on an application and get the PDF, so the interviewer walks in prepared.
-
Operations
Reconcile applications with the HR system
Look up applications and hiring requests by their external ID to match them against records in payroll or the HRIS, and fix mismatches in place.
Try asking
- “Which applications for the backend engineer opening are still waiting on feedback?”
- “Move Anna Keller's application to interview and note the call summary.”
- “Create a hiring request for a support agent in Hamburg starting May.”
Compare
Elaichi vs Zapier MCP vs Composio for Dvinci
All three can connect Dvinci 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 Dvinci tools | Allow or restrict single Dvinci 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 Dvinci 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
Dvinci tools for your AI agents
75 tools are ready to call through Elaichi's MCP endpoint the moment you connect Dvinci, 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 Dvinci gets you
6 screens from the product, each doing one job for your Dvinci account.
The agent
Ask about applicants, get answers from Dvinci.
Plain questions, answered from live applications, attachments and hiring requests in Dvinci.
- applications
- attachments
- hiring requests
- history entries
Ask Elaichi to work across your apps.
Which applications for the backend engineer opening are still waiting on feedback?
Move Anna Keller's application to interview and note the call summary.
Create a hiring request for a support agent in Hamburg starting May.
Also runs in Claude, ChatGPT or Cursor
MCP clients
One endpoint puts Dvinci in every client.
Claude, ChatGPT and Cursor reach Dvinci through one governed endpoint, no SDK, no shared key.
Copy the endpoint
Tool catalog
75 Dvinci tools, no custom code required.
Applications, attachments, history and hiring requests covered end to end, ready the moment Dvinci connects.
- List all Dvinci applications
- Create a Dvinci application
- Get single Dvinci application by ID
- Update a Dvinci application by ID
Toolboxes
Each team gets its own Dvinci toolbox.
Recruiting works applications, HR works hiring requests, nobody sees more of Dvinci than their role.
- Recruiting
- Hiring managers
- HR
- Talent acquisition
Shared connections
Share Dvinci access, never the API key.
One person connects Dvinci and teammates work through it without ever seeing a credential.
- Recruiting DACH
- HR
- Hiring managers
- Talent acquisition
Audit log
Every Dvinci change has a name on it.
When, who, what happened, and which application or hiring request, 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
Monday's Dvinci digest writes itself, you approve.
A schedule fetches new applications, groups them, drafts a digest, and posts once approved.
Dvinci digest
Run 418 · started 2 minutes ago · on behalf of Emily Carter
-
✓
Schedule
Every weekday at 8:00 AM
0.2s -
✓
Fetch applications
Dvinci
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
Dvinci
Queued
Collections and dashboards
Dvinci pipeline numbers, refreshed without asking.
Applications created over 14 days, split by team, computed on a schedule with no model involved.
Dvinci health
Refreshed 4 minutes ago · every 15 minutes · from the applications collection
Applications
1,284 ↓ 12%
Attachments
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Applications created
Last 14 days
By team
Share of activity
Recruiting DACH 34%
HR 27%
Hiring managers 21%
Talent acquisition 18%
Related connectors
More from the catalog
FAQ
Frequently asked questions
How do I connect Dvinci to Claude?
Two steps. In Elaichi, add Dvinci and paste in your Dvinci API key; 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 asks you to sign in to Elaichi and Dvinci is ready to use.
Does Dvinci work with ChatGPT and Cursor as well as Claude?
Yes. Dvinci is connected once in Elaichi, and the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any other MCP client and the Elaichi Agent. You do not set Dvinci up again for each client.
What can an AI agent actually do with my Dvinci data?
It can find, create and update applications in Dvinci, change their status, move them between job openings and add a history entry after a call. It can fetch attachments, including the PDF of a CV, and create and update hiring requests. Short, concrete asks such as 'move Anna to interview' work better than long paragraphs.
Does connecting Dvinci give the AI access to everything in my account?
No. The AI works through the Dvinci account whose API key was connected, so it can only see and change what that account can, and each person still signs in to Elaichi as themselves. Elaichi can narrow that access further, by team and by action, but it never widens it beyond what Dvinci itself allows.
Can I stop an agent from deleting or changing things in Dvinci?
Yes. Restrictions on the Dvinci connection in Elaichi apply per action, so you can switch off deleting applications or attachments while leaving reading and updating on. A restricted action is left out of the tool list the AI client sees, so it cannot be called no matter how the prompt is worded.
What happens to a Dvinci connection when someone leaves?
Offboarding someone in Elaichi ends their access to Dvinci at once, and a shared Dvinci connection keeps working for everyone else on the team. If you later want to remove Dvinci entirely, disconnecting it once in Elaichi removes it from Claude, ChatGPT, Cursor and every other client.
Does the Dvinci MCP connector work with Gemini, Codex, Claude Code or other MCP clients?
Yes. Dvinci 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 Dvinci?
Yes. Both let Claude, ChatGPT or Cursor use Dvinci. 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 Dvinci call.
How is Elaichi different from Composio for Dvinci?
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 Dvinci: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.
Put Dvinci 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.