Data & Analytics · Control d + Claude
Control D MCP with Claude: Manage DNS Filtering and Access Rules in Plain English
The short answer
Claude works with Control D through the Model Context Protocol, an open standard that lets Claude securely read and act within the tool. Once connected with an API key, Claude can review filtering reports, check network queries, and suggest or make policy changes, all in natural language. Your team controls which actions are allowed and approves consequential changes.
What is Control d?
Control D is a customisable DNS filtering and traffic redirection platform. DNS is the system that turns website names into network addresses. By filtering those requests, organisations can manage internet access, enforce acceptable use policies and monitor usage across devices and networks. It is typically used by IT and security teams in offices, schools, managed service providers and households with complex networks.
How Claude connects to Control d through MCP
The Model Context Protocol, usually shortened to MCP, is an open standard that lets Claude use other software safely. Think of it as a universal adapter between Claude and a tool. It gives Claude a defined set of things it can read and do, and nothing beyond that. Control D can be connected either through an MCP server or through its direct API, using an API key for sign-in.
Once connected, Claude can typically review DNS query activity, summarise which categories of sites are being blocked, look up how a particular policy is set up, and help draft changes to access rules. A network administrator might ask, in plain English, why a certain site is blocked for one group of devices and receive a clear explanation with the relevant policy details.
Permissions and approvals keep people in charge. Access is limited to the scope of the API key you issue, and we set it to least privilege, so Claude sees only what it needs. Consequential actions, such as changing a policy that affects many devices, can require a named person to confirm before anything is applied. Every action is logged so your team can review what happened and when.
What you can automate
Weekly filtering reports
Claude compiles a summary of blocked and allowed queries across policies each week, highlighting unusual spikes. IT managers receive a short, readable report instead of spending hours inside dashboards, and can ask follow-up questions about any figure.
Answering access requests
When a staff member reports that a work site is blocked, Claude can look up which rule caused the block and explain it. The IT team can then approve or reject a temporary exception, with the decision recorded for audit purposes.
Policy review for schools and campuses
Education administrators can ask Claude to check whether filtering rules still match the acceptable use policy for each year group. Claude can flag rules that look outdated or overlap, so staff can tidy them up during term breaks.
Investigating unusual network activity
When monitoring shows a sudden rise in queries to an unfamiliar domain, Claude can pull the related records and summarise the devices and times involved. Security staff then decide on blocking or further investigation, with Claude speeding up the first look.
Onboarding and offboarding access
When a new team joins or a contractor leaves, Claude can draft the access rule changes needed for that group. A manager reviews the draft and approves it, reducing the chance of forgotten permissions remaining in place.
An end-to-end workflow: Staff access request to resolution
TriggerAn employee submits a request in the IT ticketing system saying a research website is blocked on their laptop.
Claude reads the ticket and identifies the device and user group named in it.
Claude looks up the Control D policy applied to that group and finds the rule blocking the site.
Claude summarises the reason and drafts a time-limited exception for the site.
The IT lead receives the summary in Microsoft Teams and approves or declines the exception.
If approved, the change is applied and the ticket is updated with the new rule and approval record.
Claude schedules a reminder to review the exception when it expires.
OutcomeTypical access requests are resolved in minutes rather than hours, with a clear record of who approved what and when, and fewer repeated tickets about the same site.
How we set it up
Free automation audit
We review how your team currently handles DNS filtering requests, reports and policy changes, and identify the workflows worth automating. You receive a short written plan at no cost.
Secure API key connection
We connect Claude to Control D using an API key, either through the official MCP server or the direct API, whichever suits your setup. The key is stored securely and scoped to least privilege.
Workflow design
We design the end-to-end workflow across Control D and your other systems, such as Microsoft 365, your ticketing tool or your CRM. We agree in advance which actions need human approval.
Testing with real cases
We test the workflow against past tickets and real policy scenarios to confirm Claude's answers and proposed changes are accurate before anything goes live.
Launch, monitoring and training
We launch with audit logging and monitoring in place, then train your IT and operations staff on how to use Claude with Control D day to day.
Who benefits
- IT manager
- Gets fast answers about filtering rules and clear reports without navigating multiple dashboards.
- Security analyst
- Gets a quick first review of unusual query activity, so investigation starts sooner.
- School or campus administrator
- Can review and explain acceptable use policies in plain language and keep rules up to date.
- Service desk lead
- Resolves access requests faster with a documented approval trail.
Security and control
- Claude uses an API key scoped to least privilege, so it can access only the functions your team agrees to.
- Consequential policy changes require named human approval before they are applied.
- Every action Claude takes is recorded in audit logs for review.
- Sensitive configuration details can be restricted from being shared outside the approved team.
- We test thoroughly before launch and monitor the workflow afterwards.
For teams in the US, UK, India and the Middle East
Organisations in the United States and the United Kingdom can use this setup within their existing data protection frameworks, with the hosting region chosen to meet their requirements. In India, the Digital Personal Data Protection Act, 2023 governs personal data handling, and we design access controls with that in mind. Organisations in the UAE and Saudi Arabia must observe their local data protection laws, and we select a hosting region that meets those obligations.
Learn more about Claude and MCP
Anthropic's AI model and assistant.
Secure links between Claude and business tools.
How engineers build and change software with Claude.
Hosted agents that run multi-step work.
The open standard Claude uses to connect to tools.
Frequently asked questions
What does the Control D MCP server do?
The Control D MCP server is the connector that lets Claude communicate with your Control D account in a structured way. It defines which actions Claude can perform, such as reading reports or reviewing policies. It sits between Claude and your account, so access is controlled and predictable.
Is connecting Claude to Control D secure?
Security depends on how the connection is set up. We use an API key with least-privilege access, store it securely, restrict which actions Claude can take, require human approval for consequential changes, and keep audit logs. We test these controls before launch so you can review exactly what Claude can and cannot do.
What can Claude do with Control D once connected?
Typically, Claude can review DNS query activity, summarise blocked and allowed traffic, explain how policies are configured, help draft access rule changes, and produce filtering reports. Which actions it can take depends on the scope we agree with you, and changes can be limited to suggestions requiring approval.
How long does setup take?
Timelines vary with the number of policies, devices and connected systems. A focused setup for one workflow often takes a few weeks, including testing and training. We confirm the timeline during the free automation audit, once we understand your environment.
What account access is needed?
You need an API key from your Control D account, issued with permissions suited to the workflows you want. The exact access level depends on your account arrangement, so we review this with your administrator during the audit and recommend the narrowest permissions that do the job.