Compliance
Secureframe MCP connector
Connect Secureframe to Claude, ChatGPT, Cursor, or any MCP client through Elaichi, and your team can ask about controls, frameworks, evidence, devices, and cloud resources, then add comments or update scope, all inside each person's own Secureframe 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 Secureframe to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect Secureframe once
-
Open Connections, choose Add connection, and pick Secureframe.
-
Optionally set Share with to give a team access, then press Connect.
-
Paste a Secureframe API key. One person generates a token in Secureframe 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 Secureframe 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 Secureframe 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 Secureframe 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 Secureframe 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 Secureframe through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
Compliance
Check control status before the audit call
Ask which SOC 2 or ISO 27001 controls in Secureframe still need attention, pull the details on any one of them, and leave a comment for the owner without opening a tab.
-
Security
Find cloud resources missing from a framework
List the cloud resources Secureframe knows about, spot the ones not yet in scope for a framework, and add them so the next test run covers everything it should.
-
IT
Review devices and bring them into scope
See every laptop and workstation Secureframe is tracking, check which ones fall under a given framework, and put a new hire's machine in scope the same afternoon.
-
Engineering
Keep repositories tagged and in scope
Look up how a code repository is recorded in Secureframe, update its details when a service is renamed, and confirm it counts toward the frameworks your customers ask about.
-
Risk
Pull evidence details for a customer questionnaire
Ask for the evidence attached to a specific control in Secureframe and get a plain summary you can paste into a vendor security questionnaire answer.
-
Leadership
Get a readiness summary in plain language
Ask how many controls are passing for each framework in Secureframe and where the gaps are, then record follow-up notes as comments so the team sees them where they already work.
Try asking
- “List all Secureframe repositories missing a framework asset scope.”
- “Show cloud resources added to Secureframe this week.”
- “Summarize open comments on our SOC 2 framework scopes.”
AI tools
Secureframe tools for your AI agents
57 tools are ready to call through Elaichi's MCP endpoint the moment you connect Secureframe, 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 Secureframe gets you
6 screens from the product, each doing one job for your Secureframe account.
The agent
Ask about repositories, read live Secureframe answers.
Type a question in plain language and get answers from live Secureframe records.
- repositories
- cloud resources
- framework asset scopes
- comments
Ask Elaichi to work across your apps.
List all Secureframe repositories missing a framework asset scope.
Show cloud resources added to Secureframe this week.
Summarize open comments on our SOC 2 framework scopes.
Also runs in Claude, ChatGPT or Cursor
MCP clients
Claude, ChatGPT and Cursor reach Secureframe here.
One governed MCP endpoint over OAuth, no SDK and no shared API key.
Copy the endpoint
Tool catalog
57 Secureframe tools arrive ready to call.
Repositories, cloud resources, framework asset scopes and comments, with no custom code written.
- List all Secureframe repository framework asset scopes
- Create a Secureframe repository framework asset scope
- Update a Secureframe repository by ID
- List all Secureframe repositories
Toolboxes
Every team gets its own Secureframe toolbox.
Curate toolboxes per team so compliance, security and engineering each see their own scope.
- Compliance
- Security
- Engineering
- IT Operations
Shared connections
Teammates query Secureframe without holding credentials.
See who connected each Secureframe account and how many teams and members share it.
- Compliance
- Security Engineering
- Platform
- Internal Audit
Audit log
Every Secureframe call is written down.
When, who, what happened, type and resource, appended for each Secureframe request.
- 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 drafts your Secureframe evidence digest.
Fetch cloud resources, group them, draft a digest, get approval, comment back in Secureframe.
Secureframe digest
Run 418 · started 2 minutes ago · on behalf of Emma Laurent
-
✓
Schedule
Every weekday at 08:00
0.2s -
✓
Fetch repositories
Secureframe
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
Secureframe
Queued
Collections and dashboards
Secureframe compliance numbers refresh on schedule.
Four metrics, 14 days of records created and a team breakdown, computed without a model.
Secureframe health
Refreshed 4 minutes ago · every 15 minutes · from the repositories collection
Repositories
1,284 ↓ 12%
Cloud resources
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Repositories created
Last 14 days
By team
Share of activity
Compliance 34%
Security Engineering 27%
Platform 21%
Internal Audit 18%
Related connectors
More from the catalog
FAQ
Frequently asked questions
How do I connect Secureframe to Claude?
In Elaichi, choose Secureframe and paste in an API key from your Secureframe account. Secureframe connects with an API key, so 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 the endpoint https://api.elaichi.ai/mcp. Sign in with your Elaichi account and Secureframe is ready.
Does Secureframe work with ChatGPT and Cursor as well as Claude?
Yes. Once Secureframe 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 Secureframe once and every client picks it up.
What can an AI agent actually do with my Secureframe data?
An agent can look up frameworks, controls, and the evidence behind them in Secureframe, list the devices, cloud resources, and code repositories being monitored, and tell you which ones are in scope for a framework. It can also add or edit comments, update a repository or cloud resource, put an asset into scope, and record custom connection data. Because Secureframe exposes a lot of actions, short concrete asks such as 'list failing controls for SOC 2' work better than long paragraphs.
Does connecting Secureframe give the AI access to everything in my compliance workspace?
No. Every request runs as the person who signed in, so an agent only sees the frameworks, controls, evidence, and assets that person can already see in Secureframe. Elaichi can narrow that further with restrictions per team or per action, and it can never grant more than the person's own Secureframe permissions allow.
Can I stop an agent from deleting or changing things in Secureframe?
Yes. Restrictions in Elaichi work per action, so you can allow reading controls and evidence in Secureframe while blocking comment deletion, scope changes, or updates to cloud resources and repositories. A blocked action is never shown to the AI client at all, so no prompt, however worded, can reach it.
What happens to a Secureframe connection when someone leaves?
Offboarding a person in Elaichi ends their access to Secureframe through every client at once, with nothing to revoke in Claude, ChatGPT, or Cursor separately. A Secureframe connection they shared keeps working for everyone else on the team. If you want to remove Secureframe entirely, disconnecting it once in Elaichi removes it from every client.
Put Secureframe in front of your team
Fourteen days on Gold, no credit card. Connect it once and pick what each team can call.