# Veeva Vault MCP connector

The Veeva Vault connector lets Claude, ChatGPT, Cursor, or any MCP client look up a Veeva Vault user record by ID, so your team can confirm who a user is without leaving the conversation.

Source: https://elaichi.ai/connectors/veevavault/

## Facts

| | |
| --- | --- |
| Application | Veeva Vault |
| Category | Compliance |
| AI tools | 1 |
| Authentication | Connects with an API key |
| Needs your own OAuth app | No |
| MCP endpoint | https://api.elaichi.ai/mcp |
| Works with | Claude, ChatGPT, Cursor, any MCP client, and the Elaichi Agent |
| Tools advertised by name | Yes |

## What you can ask once Veeva Vault is connected

- Show the Veeva Vault user record for Priya Raman.
- Which Veeva Vault users belong to the Quality team?
- List Veeva Vault users added in the last 30 days.

## Connect Veeva Vault in Elaichi

This happens once for the organization, before any client is involved.

1. Open Connections, choose Add connection, and pick Veeva Vault.
2. Optionally set Share with, then press Connect.
3. Paste a Veeva Vault API key. One person generates a token in Veeva Vault and pastes it once. Everyone else works through Share with, and never sees it.

Credentials are vaulted and nobody, including the AI, reads them back. The connection becomes a toolbox immediately, so you can curate which Veeva Vault tools are exposed, rename them, or freeze arguments before anyone points a client at it.

## Connect Veeva Vault to Claude

Endpoint: https://api.elaichi.ai/mcp

1. Open Customize, then Connectors.
2. Press Add.
3. Name it, paste the MCP server URL, then Continue.
4. Sign in and approve.

On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.

## Connect Veeva Vault to ChatGPT

Endpoint: https://api.elaichi.ai/mcp

1. Open Plugins, then press the + button.
2. Name it and paste the endpoint into Server URL.
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.

## Connect Veeva Vault to Cursor

Endpoint: https://api.elaichi.ai/mcp

1. Open `~/.cursor/mcp.json`.
2. Add the endpoint under `mcpServers`.
3. Reload Cursor, then sign in and approve.

Set up per machine, so repeat it on each computer you work from.

## Connect Veeva Vault to any MCP client

Endpoint: https://api.elaichi.ai/mcp

1. Add the endpoint as a remote MCP server.
2. Sign in and approve.

The Elaichi Agent already has these tools, with nothing to set up.

## What the consent screen decides

Only Read is granted by default, which is not enough to call a Veeva Vault tool. Over MCP there is no trusted place to confirm a write in the moment, so the consent screen is the standing approval rather than a formality. Grant Read and Run tools. Think hard before granting Delete, which reaches into connected apps and cannot be undone.

## What teams do with Veeva Vault through Elaichi

### Confirm who signed a document

Compliance. When an audit trail entry only shows a user ID, ask the agent to pull the Veeva Vault user behind it and get the name and status in seconds.

### Check a reviewer before a QA sign-off

Quality. Before accepting an approval on a batch record or SOP, confirm the Veeva Vault user who acted is still active and is the person you expected.

### Identify a user on a submission record

Regulatory. Resolve the user IDs listed on a submission or correspondence record into real names so the history reads clearly during a review.

### Verify a Veeva Vault account exists

IT. When someone reports they cannot get into Veeva Vault, look up their user record by ID and see whether the account is present and active.

### Check a leaver's Veeva Vault status

HR. During offboarding, pull the departing employee's Veeva Vault user record to confirm the account shows as inactive.

### Put a name to a study record change

Clinical operations. When a trial document shows a change made by an unfamiliar user ID, ask who that Veeva Vault user is before following up.

## Frequently asked questions

### How do I connect Veeva Vault to Claude?

First, connect Veeva Vault in Elaichi by pasting in an API key from your Veeva Vault account. 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 in https://api.elaichi.ai/mcp. Sign in as yourself and Veeva Vault is available in your conversations.

### Does Veeva Vault work with ChatGPT and Cursor as well as Claude?

Yes. Once Veeva Vault 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 Veeva Vault once and every client you use picks it up.

### What can an AI agent actually do with my Veeva Vault data?

Today the Veeva Vault connector does one thing: it looks up a single Veeva Vault user by their ID. That means an agent can tell you who is behind a user ID on an audit trail, a signature, or a document history, and whether that account is active. It cannot read documents, change records, or manage users.

### Does connecting Veeva Vault give the AI everything in my vault?

No. Every call to Veeva Vault runs under the access of the person who signed in, so the agent can only look up users that person could already see in Veeva Vault. Elaichi can narrow that further with restrictions, but it can never widen access beyond what your Veeva Vault permissions already allow.

### Can my team share one Veeva Vault connection?

Yes. One person connects Veeva Vault in Elaichi and shares the connection with a team, and nobody else ever handles the API key. Each teammate still signs in to Elaichi as themselves, so every Veeva Vault lookup in the audit log is tied to the individual who made it.

### Can I stop an agent from deleting or changing things in Veeva Vault?

The Veeva Vault connector is read only: it can look up a user by ID and nothing else, so there is nothing an agent can delete or change. If you want to restrict even that lookup for some teams, Elaichi applies restrictions per action, and a blocked action is never shown to Claude, ChatGPT, or Cursor, so no prompt can reach it.

### What happens to a Veeva Vault connection when someone leaves?

When you offboard someone in Elaichi, their access to Veeva Vault through Elaichi ends at once, in every client they used. If they shared a Veeva Vault connection with a team, it keeps working for everyone else. Disconnecting Veeva Vault once in Elaichi removes it from Claude, ChatGPT, Cursor, and every other client at the same time.

## All 1 Veeva Vault tools

Every tool below is callable through https://api.elaichi.ai/mcp once Veeva Vault is connected, subject to the toolbox it is in and the restrictions on the caller.

- **Get single Veeva Vault user by ID** (Get). Use this endpoint to get a single user in the Zoho Bigin account. It always requires the ID to fetch.
