> For the complete documentation index, see [llms.txt](https://docs.docontrol.io/docontrol-user-guide/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.docontrol.io/docontrol-user-guide/saas-data-monitoring/docontrol-mcp.md).
# DoControl MCP
DoControl MCP connects your DoControl tenant to AI tools you already use, including Cursor, Claude, ChatGPT, Claude Desktop, and other MCP-compatible clients.
Security teams can ask plain-English questions about SaaS risk, events, identities, assets, alerts, and documentation - and get answers grounded in their live tenant data.
Setup takes about 60 seconds. Authenticate with a DoControl API key, connect your AI client to dc-mcp, and start asking.
***
### Core capabilities
**1. Ask in natural language**
Pose open-ended security questions. Dot orchestrates discovery, querying, and narration end to end.
**2. Query live tenant data**
Run precise GraphQL queries against your DoControl API for events, assets, identities, alerts, and more.
**3. Discover connected apps**
Instantly see which SaaS integrations are connected for your tenant.
**4. Search product documentation**
Pull how-to guidance, alert definitions, and policy explanations from the DoControl user guide - inside the same conversation.
**5. Author guided API queries**
Use built-in query-builder guidance when you need full control over the data path.
***
### What you can ask about
* **SaaS security posture** - risk scores, exposure, misconfigurations
* **Events and activity** - sharing, access, and admin actions across integrated apps
* **Identities** - risky users, VIP exposure, employment status, admin roles
* **Assets** - publicly or externally shared files, sensitive content, shadow apps
* **Alerts and reports** - active alerts, alert definitions (for example DC30), investigation context
* **Documentation and Dot** - product how-tos alongside live tenant data
#### Supported integrations
Google Drive; Microsoft 365 (OneDrive, SharePoint, Teams, Entra ID); Slack; GitHub; Okta; Salesforce; Jira; Box; Dropbox; Zoom; CrowdStrike; and HRIS providers (HiBob, Workday, BambooHR, Deel, SAP SuccessFactors).
***
### Example prompts
#### Identity and risk
* Show me users with a critical risk score
* Which identities are admins in more than one SaaS app?
* List terminated employees who still have externally shared assets
#### Data exposure
* Which Google Drive files are shared via public links?
* Show sensitive files shared with personal email accounts
* What Slack assets are exposed to external collaborators?
#### Alerts and investigation
* What active alerts do I have right now?
* Explain alert DC30 and show matching events in my tenant
* Summarize the riskiest departments this month
#### Stack and configuration
* Which SaaS apps are connected in my DoControl tenant?
* How do I configure an Okta integration?
* What does DoControl’s identity risk score measure?
***
### How it works
1. You ask a question in plain English in your AI client.
2. DoControl MCP routes the request - via Dot, a direct API query, or documentation search.
3. You receive an answer grounded in your tenant data and DoControl product knowledge.
All queries run against your tenant with your credentials, scoped to what your API key can access.
***
### Why teams use it
**Before DoControl MCP**
* Context-switch into the console for every investigation
* Manually navigate modules and filters
* Copy and paste between docs and the product
* Hand-build API queries from scratch
**With DoControl MCP**
* Stay in Cursor, Claude, or ChatGPT
* Ask the question and get the answer
* Combine docs and live data in one conversation
* Use schema search and guided query construction
***
### Getting started
1. Install uv (one-time).
2. Create an API key in DoControl → Settings → API Keys.
3. Run uvx dc-mcp login and paste your key.
4. Add DoControl to your MCP client configuration:
```
{
"mcpServers": {
"docontrol": {
"command": "uvx",
"args": ["dc-mcp"]
}
}
}
```
5. Restart your AI client and ask your first question.
***
### Security notes
* Access is tenant-scoped via your DoControl API credentials.
* Queries return only data your account is authorized to see.
* Prefer least-privilege or read-oriented keys for analyst workflows.
* DoControl’s platform AI features process data within DoControl’s environment; customer data is not used to train third-party models.
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.
Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:
```
GET https://docs.docontrol.io/docontrol-user-guide/saas-data-monitoring/docontrol-mcp.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.