Survey
SafetyCulture MCP connector
The SafetyCulture connector brings your actions, groups, action types, labels and custom fields into Claude, ChatGPT, Cursor and any MCP client, so your team can raise, find and schedule safety actions in plain language.
-
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 SafetyCulture to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect SafetyCulture once
-
Open Connections, choose Add connection, and pick SafetyCulture.
-
Optionally set Share with to give a team access, then press Connect.
-
Paste a SafetyCulture API key. One person generates a token in SafetyCulture 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.
Connect SafetyCulture 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 SafetyCulture 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 SafetyCulture 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 SafetyCulture 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 SafetyCulture through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
Safety
Raise a corrective action after a site walk
Describe what you saw and the agent creates the SafetyCulture action with the right action type and labels, so the fix is logged before you leave the site.
-
Operations
See every open action across your sites
Ask for the actions still open at a particular location, of a particular type, or carrying a particular label, and get one list instead of clicking through each site in SafetyCulture.
-
Facilities
Put recurring checks on a schedule
Set up a repeating SafetyCulture action for fire door checks, extinguisher inspections or plant room walks, so the reminder comes round without anyone recreating it by hand.
-
Quality
Tag actions consistently for the next audit
Add or tidy up action labels in bulk so every SafetyCulture action from a given audit or product line carries the same tags when the auditor asks for evidence.
-
Site management
Send a contractor a link to one action
Create a shared link for a single SafetyCulture action and hand it to the electrician or cleaning contractor who needs to see it without a SafetyCulture login.
-
Administration
Set up groups and action types once
Create SafetyCulture groups for new sites, add the action types your business uses, and map custom fields to them, all from a short request instead of a run through the settings screens.
Try asking
- “Which SafetyCulture actions are overdue this week?”
- “List action types used by the Warehouse group.”
- “Summarize inspections raised across SafetyCulture groups this month.”
AI tools
SafetyCulture tools for your AI agents
363 tools are ready to call through Elaichi's MCP endpoint the moment you connect SafetyCulture, 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 SafetyCulture gets you
6 screens from the product, each doing one job for your SafetyCulture account.
The agent
Ask about open actions, get real answers.
The agent reads live SafetyCulture inspections and actions and answers in plain language.
- inspections
- actions
- groups
- action types
Ask Elaichi to work across your apps.
Which SafetyCulture actions are overdue this week?
List action types used by the Warehouse group.
Summarize inspections raised across SafetyCulture groups this month.
Also runs in Claude, ChatGPT or Cursor
MCP clients
Claude, ChatGPT and Cursor reach SafetyCulture.
One org MCP endpoint over OAuth, no SDK and no shared API key.
Copy the endpoint
Tool catalog
363 SafetyCulture tools are ready to call.
Browse tool names, resources and methods for actions, groups and custom fields, no custom code.
- List all SafetyCulture groups
- Create a SafetyCulture group
- Create a SafetyCulture action custom field
- Delete a SafetyCulture action custom field by ID
Toolboxes
Every team gets its own SafetyCulture toolbox.
Curate one toolbox per team so Safety, Operations and Quality see different tools.
- Safety
- Operations
- Quality
- Compliance
Shared connections
Teammates use SafetyCulture without seeing credentials.
See who connected each account and how many teams and members share it.
- Safety EMEA
- Operations APAC
- Quality
- Facilities
Audit log
Answer who closed which action, exactly.
Every SafetyCulture call lands append only with time, person, event, type and resource.
- 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 fires, a digest ships.
Fetch SafetyCulture actions, group them, draft a digest, get approval, post it back.
SafetyCulture digest
Run 418 · started 2 minutes ago · on behalf of Emma Laurent
-
✓
Schedule
Every weekday at 08:00
0.2s -
✓
Fetch inspections
SafetyCulture
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
SafetyCulture
Queued
Collections and dashboards
SafetyCulture health arrives before anyone asks.
Four metrics, 14 days of records created and a team breakdown, computed on schedule.
SafetyCulture health
Refreshed 4 minutes ago · every 15 minutes · from the inspections collection
Inspections
1,284 ↓ 12%
Actions
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Inspections created
Last 14 days
By team
Share of activity
Safety EMEA 34%
Operations APAC 27%
Quality 21%
Facilities 18%
Related connectors
More from the catalog
FAQ
Frequently asked questions
How do I connect SafetyCulture to Claude?
First connect SafetyCulture in Elaichi, which asks you to paste in a SafetyCulture API key from your SafetyCulture 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 with your Elaichi account and SafetyCulture is available in Claude.
Does SafetyCulture work with ChatGPT and Cursor as well as Claude?
Yes. Once SafetyCulture is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, the Elaichi Agent and any other MCP client. You connect SafetyCulture once and every client you use picks it up.
What can an AI agent actually do with my SafetyCulture data?
An agent can raise a SafetyCulture action after a site walk, look up an action by its details, list the actions open at a site or of a certain type, put an action on a repeating schedule, and create a shared link so a contractor can see one action. It can also create groups, action types and labels, and set up the custom fields your actions carry. Short, concrete asks work best, such as "list open electrical actions at the Leeds warehouse" rather than a long paragraph.
Does connecting SafetyCulture give the AI access to everything in my organization?
No. Every request runs as the person who signed in, so the agent sees only the SafetyCulture actions, groups and sites that person's own SafetyCulture account can see. Elaichi can narrow that further with restrictions, and it can never widen access beyond what SafetyCulture itself has granted.
Can I stop an agent from deleting or changing things in SafetyCulture?
Yes. Restrictions in Elaichi work per action, so you can allow an agent to read and create SafetyCulture actions while blocking deletion of actions, labels, action types or custom fields. A blocked action is never shown to Claude, ChatGPT, Cursor or any other client, so no prompt can reach it.
What happens to a SafetyCulture connection when someone leaves?
Offboarding that person in Elaichi ends their access to SafetyCulture through every client at once. If they had shared a SafetyCulture connection with a team, it keeps working for everyone else. Disconnecting SafetyCulture once in Elaichi removes it from Claude, ChatGPT, Cursor and every other connected client.
Put SafetyCulture in front of your team
Fourteen days on Gold, no credit card. Connect it once and pick what each team can call.