Compliance
OneTrust MCP connector
Connect OneTrust to Claude, ChatGPT, Cursor, or the Elaichi Agent through Elaichi, so your team can log data subject requests, track AI governance entities and tasks, and review consent banners and preferences inside their own OneTrust access.
-
How it connects. App credentials. 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 OneTrust to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect OneTrust once
-
Open Connections, choose Add connection, and pick OneTrust.
-
Optionally set Share with to give a team access, then press Connect.
-
Paste your OneTrust app credentials. OneTrust authenticates the app rather than a person. One person supplies the credentials once, and everyone else works through Share with.
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.
Connect OneTrust to 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.
Connect OneTrust to 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.
Connect OneTrust to 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 OneTrust 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 OneTrust through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
Privacy
Log a data subject request as it arrives
When someone emails asking for a copy of their data, describe the request in plain language and the agent opens the data subject access request in OneTrust for you.
-
AI governance
Register a new AI system in the inventory
After a vendor demo or an internal build, add the model or use case as an AI governance entity in OneTrust with its type and details filled in, then link it to the systems it relates to.
-
Legal
Check what is on record before a review
Search OneTrust for an AI governance entity by name and read back its details and links before the meeting, instead of clicking through the inventory yourself.
-
Compliance
Assign and update AI review tasks
Create a OneTrust AI governance task for the owner of a system, then update its status and notes straight after the review call.
-
Marketing
Review the consent banners in play
List the cookie banners configured in OneTrust and confirm which version each site carries before a campaign or site launch.
-
Security
Prepare for an audit in minutes
Pull the list of audit event types OneTrust tracks and the preference settings in place, so you know what evidence exists before the auditors ask.
Try asking
- “Summarize AI governance entities created this quarter by type”
- “List governance entities still sitting in review stages”
- “Which teams own the most OneTrust governance links”
AI tools
OneTrust tools for your AI agents
622 tools are ready to call through Elaichi's MCP endpoint the moment you connect OneTrust, 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 OneTrust gets you
6 screens from the product, each doing one job for your OneTrust account.
The agent
Ask about OneTrust records in plain language.
The agent reads live OneTrust governance entities, stages and links to answer.
- governance entities
- entity types
- links
- stages
Ask Elaichi to work across your apps.
Summarize AI governance entities created this quarter by type
List governance entities still sitting in review stages
Which teams own the most OneTrust governance links
Also runs in Claude, ChatGPT or Cursor
MCP clients
One OneTrust endpoint for every MCP client.
Claude, ChatGPT and Cursor connect over OAuth, no SDK, no shared key.
Copy the endpoint
Tool catalog
622 OneTrust tools ready without custom code.
Governance entities, entity types, links and stages, each with full read and write methods.
- Create a OneTrust type stage
- Create a OneTrust AI governance entity
- OneTrust AI governance entities search
- Get single OneTrust AI governance entity by ID
Toolboxes
Every team gets its own OneTrust toolbox.
Curate one toolbox per team so each sees only the OneTrust tools it needs.
- Privacy
- Legal
- Security
- AI Governance
Shared connections
Teammates use OneTrust without seeing credentials.
Each connection shows who linked the OneTrust account and which teams and members share it.
- Privacy EMEA
- Legal
- Security
- AI Governance
Audit log
Every OneTrust call is written down.
When, who, what happened, type and resource, appended for each OneTrust action.
- 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 OneTrust records into decisions.
Fetch governance entities, group them, draft a digest, approve, post back to OneTrust.
OneTrust digest
Run 418 · started 2 minutes ago · on behalf of Emma Laurent
-
✓
Schedule
Every weekday at 08:00
0.2s -
✓
Fetch governance entities
OneTrust
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
OneTrust
Queued
Collections and dashboards
OneTrust health arrives before anyone asks.
Four metrics, 14 days of entities created and a team breakdown, refreshed on schedule.
OneTrust health
Refreshed 4 minutes ago · every 15 minutes · from the governance entities collection
Governance entities
1,284 ↓ 12%
Entity types
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Governance entities created
Last 14 days
By team
Share of activity
Privacy EMEA 34%
Legal 27%
Security 21%
AI Governance 18%
Related connectors
More from the catalog
FAQ
Frequently asked questions
How do I connect OneTrust to Claude?
Two steps. First, connect OneTrust in Elaichi: OneTrust uses app credentials, so you enter the credentials your OneTrust administrator gives you once, and 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. From that point Claude can work in OneTrust as you.
Does OneTrust work with ChatGPT and Cursor as well as Claude?
Yes. Once OneTrust 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 OneTrust once and every client you use picks it up.
What can an AI agent actually do with my OneTrust data?
With OneTrust connected, an agent can open a data subject access request, register an AI system as an AI governance entity, search the inventory and read a system's details, link related systems, and create or update AI governance tasks. It can also list the consent banners, preferences, and audit event types configured in OneTrust. Because OneTrust has a large number of actions, short concrete asks such as "create a task for the fraud model review" work better than long paragraphs.
Does connecting OneTrust give the AI access to everything in the workspace?
No. Every call to OneTrust runs as the person who signed in, so the agent sees only the entities, requests, and settings that person's OneTrust role already allows. Elaichi can narrow that access further with restrictions, and it can never widen it beyond what OneTrust itself grants.
Can I stop an agent from deleting or changing things in OneTrust?
Yes. Restrictions in Elaichi work per action, so you can allow searching and reading OneTrust records while blocking deleting an AI governance entity or removing a link. A blocked action is never advertised to Claude, ChatGPT, Cursor, or any other client, so no prompt can reach it.
What happens to a OneTrust connection when someone leaves?
Offboarding a person in Elaichi ends their access to OneTrust through every client at once. A OneTrust connection shared with the team keeps working for everyone else. If you disconnect OneTrust in Elaichi, it is removed from Claude, ChatGPT, Cursor, and every other client in one step.
Put OneTrust in front of your team
Fourteen days on Gold, no credit card. Connect it once and pick what each team can call.