Integration · Developer tools

Connect Claude & ChatGPT to DNSFilter

Ask your AI why a site is blocked, which domains were requested most this week, or what is waiting in the unblock queue, and it reads the answer from DNSFilter. It can search query logs, read threat and request totals, and block or allow domains and categories in your policies. Changes that loosen filtering can require your approval first.

Connect DNSFilter free

Free plan, no credit card. Takes about a minute.

Try asking

“Why is dropbox.com blocked for the sales team?”
The AI looks up how DNSFilter categorizes the domain and searches the query logs for blocked requests from that network.
“What were the most requested domains last week, and were any of them threats?”
It gets the top domains for the period, with a separate view of threats only.
“How many threats did we block per day this month?”
It reads the total blocked threats over the period, bucketed by day.

What your AI can do

Query logs and reports

Search DNS query logs, see top domains, and read total requests and blocked threats over time per network or agent.

Policies and block lists

Create and update policies, block or allow domains, block or unblock content categories, and look up how a domain is categorized.

Networks, agents and requests

Manage networks and read roaming clients, users, organizations and block pages, and decide on unblock requests.

“Block gambling sites in the Office policy.”
It finds the gambling category ID and blocks that category in the policy.
“What unblock requests are waiting?”
It lists open requests from users to unblock a site, and can allow or deny each one when you say so.
“Which roaming clients are offline?”
It lists installed DNSFilter agents filtered by status, with device, policy and version.

28 tools for DNSFilter

These tools are switched on when you connect. You can switch any of them off, or require your approval before it runs.

allow_domain_in_policyChanges dataAdd a domain to a policy's allow list so it is never blocked. Requires `policy_id`, `domain` and a `note`.
block_category_in_policyChanges dataBlock a content category (for example gambling) in a policy. Requires `policy_id` and `category_id` from list_categories.
block_domain_in_policyChanges dataAdd a domain to a policy's block list. Requires `policy_id`, `domain` and a `note` explaining why.
create_networkChanges dataCreate a network (site). Pass `network` with a name, policy_ids, block_page_id and optional IP addresses.
create_policyChanges dataCreate a filtering policy. Pass `policy` with a name, blacklist_categories, blacklist_domains, whitelist_domains and safe-search options.
decide_unblock_requestChanges dataAllow or deny an unblock request by `unblock_request_id`. Set `decision` (allow, allow-universal, deny, deny-and-ignore or resolve-already-allowed); allowing adds the domain to the allow list, and `message` is sent to the requester on deny.
disallow_domain_in_policyDeletesRemove a domain from a policy's allow list. Requires `policy_id`, `domain` and a `note`.
get_current_userGet the connected DNSFilter user and their organization. Use to confirm which account you are working in.
get_networkGet one network by `network_id`, with its IP addresses, policies and block page.
get_policyGet one filtering policy by `category_id` (the policy ID), with its blocked categories, allow list and block list.
get_roaming_clientGet one roaming client by `user_id` (the agent ID), with its device, policy, version and status.
get_top_domainsGet the most requested domains between `from` and `to`, optionally only threats (`security_report`) or by network, user or category.
get_total_requestsGet total DNS request counts over time between `from` and `to`, bucketed by `bucket_size`, optionally per network or agent.
get_total_threatsGet total blocked threat counts over time between `from` and `to`, optionally per network or agent.
list_block_pagesList block pages (the page shown when a site is blocked), optionally for one `organization_id`.
list_categoriesList DNSFilter content categories with their IDs, for use in policies and reports.
list_networksList networks (sites), with optional `search` text and protected/unprotected filters. Returns network IDs, names and assigned policies.
list_organizationsList the organizations you can manage, optionally filtered by `name`. Returns organization IDs for other tools.
list_policiesList filtering policies, optionally for one `organization_id`. Returns policy IDs, names and settings.
list_roaming_clientsList roaming clients (installed DNSFilter agents) with filters such as `search`, `status`, `policy_id`, `network_ids` or `tags`.
list_unblock_requestsList requests from users to unblock a site, filterable by status, domain, email or organization.
list_usersList dashboard users in your DNSFilter account.
lookup_domainLook up how DNSFilter categorizes a domain, by `fqdn`. Use to explain why a site is blocked.
search_query_logsSearch DNS query logs between `from` and `to`, filtered by `domain`/`fqdn`, `result` (allowed or blocked), network, user, agent or category.
unblock_category_in_policyDeletesStop blocking a content category in a policy. Requires `policy_id` and `category_id`.
unblock_domain_in_policyDeletesRemove a domain from a policy's block list. Requires `policy_id`, `domain` and a `note`.
update_networkChanges dataUpdate a network by `network_id`: name, policies, block page, local domains or IP addresses in `network`.
update_policyChanges dataUpdate a filtering policy by `category_id` (the policy ID). Only the fields passed in `policy` change.

Set up in three steps

1
Pick the app
Create a free PipMCP account and choose DNSFilter from the app list.
2
Paste your key
Paste a DNSFilter API key. In the DNSFilter dashboard, open Account Settings and create an API key. PipMCP sends it as-is in the Authorization header.
3
Add the link to your AI
You get a personal MCP link. Add it to Claude, ChatGPT or Cursor:
1. Click your name, then Settings › Connectors › Add custom connector.
2. Paste your link as the Remote MCP server URL.
3. Switch it on from the + menu in a chat.

Questions

What can the AI do in DNSFilter?

It can read networks, policies, categories, block pages, roaming clients, users, organizations and unblock requests, search query logs, look up a domain's category, and read top domains, total requests and total threats. It can create and update policies and networks, block or allow domains and categories in a policy, and allow or deny unblock requests.

Does the AI see my DNSFilter credentials?

No. Your DNSFilter credentials are encrypted at rest and never shown to the AI. After you save them, they are not shown again, not even to you. The AI only sees the results of the tools it calls.

Can I control what the AI is allowed to do?

Yes. You choose which tools are switched on, so you can start with reports and lookups only. Tools that loosen filtering, such as unblocking a domain or category or removing a domain from an allow list, are marked higher risk and can require your approval before they run. Every tool call is logged.

Does it work with ChatGPT?

Yes. In ChatGPT, open Settings › Apps & Connectors › Advanced, turn on Developer mode and add your PipMCP link. Developer mode needs a paid ChatGPT plan: Plus, Pro, Business or Enterprise. The same link also works in Claude (Settings › Connectors › Add custom connector), Cursor and other MCP clients.

What does it cost?

PipMCP has a free plan with no credit card required. Paid plans bill per completed task. You also need your own DNSFilter account.

Can the AI explain why a site was blocked?

Yes. It can look up how DNSFilter categorizes a domain, read the policy that applies with its blocked categories and block list, and search the query logs for that domain. That usually shows whether a category or a block list entry caused the block.