Skip to main content
With this integration, SecureAI shows which AI services the people behind your Meraki MX appliances use, and SecureAI blocks on the MX the providers you prohibit. The MX sends its logs over syslog to a collector in your network, and SecureAI writes its block list into the content filtering of the networks you pick, through the Meraki Dashboard API.

How it works

  1. The MX sends two kinds of syslog: urls (each HTTP request, and each HTTPS session with its host name) and flows (each connection that crosses the firewall, with IPs and ports). With the URLs role it also sends the content filtering blocks (content_filtering_block).
  2. The SecureAI collector, a container that runs in your network, takes the host out of each urls line, keeps only the ones that go to an AI service and sends them to your tenant over HTTPS, without the query string. The rest of the browsing never leaves your network.
  3. SecureAI reads the client’s IP and MAC and the destination host from each line, and shows it under Inventory → Network Sources with the cisco-meraki connector.
  4. When you turn on blocking, SecureAI writes its list into the Blocked URL patterns of each network you picked. It syncs again a few seconds after each block or release, and every 5 minutes.
The patterns you entered by hand in that list stay as they are. SecureAI remembers which ones it wrote and only adds or removes those. It doesn’t touch the blocked categories or the allowed URLs.

Requirements

  • An MX with the Advanced Security license. Without it, the network has no content filtering and SecureAI has nowhere to write the block. Discovery works anyway.
  • A Dashboard API key from an administrator with write (full) access to the networks where SecureAI will block. The API has to be enabled for the organization (Organization → Settings → Dashboard API access). You generate the key under My profile → API access.
  • A Linux machine with Docker on the MX’s network for the collector. The MX must reach it over syslog, and it must reach your tenant over HTTPS.
  • A SecureAI administrator with a second factor set up.

1. Connect the MX in SecureAI

  1. Open Admin → Integrations and pick the Network / SWG category.
  2. On the Cisco Meraki MX card, click Connect.
  3. Under Add a Cisco Meraki MX, enter a name that lets you recognize the device and, if you want, the collector IP.
  4. Click Create and show the configuration. SecureAI asks for your second factor, creates the log source and the feed the collector uses to filter, offers Download the collector (.zip) and shows collector.env and the Values for the Dashboard.
The tokens are shown only at that moment. Download the collector before closing the panel. If you lose the tokens, New tokens on the device row generates new ones, and the old ones stop working.

2. Install the collector

  1. Copy the .zip to a Linux machine with Docker on the MX’s network and unzip it.
  2. In the secureai-collector folder, run docker compose up -d.
The collector listens for syslog on port 514 of the machine, UDP and TCP. It’s the same collector the other firewalls use; the Fortinet FortiGate guide shows the contents of the files and how to run it without Docker.

3. Send the MX syslog to the collector

In the Dashboard: Network-wide → General, Reporting section, Add a syslog server:
  • Server IP: the collector IP.
  • Port: 514.
  • Roles: URLs and Flows.
Save. From MX firmware 18.101, lines from the Flows role arrive with the type firewall instead of flows; SecureAI reads both.

4. Turn on blocking

In the Cisco Meraki MX panel, Blocking tab:
  1. Paste the Dashboard API key.
  2. Show my MX networks lists the networks with an MX in the organizations that key sees. Pick the networks. If the key can’t list organizations, type the network ids (L_… or N_…).
  3. Check I understand that SecureAI writes into the blocked URL patterns of these networks.
  4. Click Turn on blocking. SecureAI asks for your second factor and runs the first sync.
SecureAI stores the API key encrypted and never shows it again. The Activity Log records who turned blocking on. Under Inventory → Network Sources → Response & auto-block you see the status (how many domains in how many networks, and the last sync), change the networks with Change networks or turn it off with Turn off. When you change the networks, SecureAI removes its patterns from the ones you dropped and writes them into the new ones. Temporary blocks an analyst creates from Network Sources go to Meraki when the block destination is Meraki, or automatic and your tenant has neither Cisco Umbrella nor Cloudflare Gateway blocking. A block through Meraki reaches the whole network behind each MX you picked, not only the source IP.

5. Check

  1. In the Dashboard, Security & SD-WAN → Content filtering of a network you picked: Blocked URL patterns shows the domains of the SecureAI block list, after your own.
  2. From a machine behind the MX, open an AI service you prohibited. According to Cisco’s documentation, the MX shows its block page over HTTP and drops the connection over HTTPS.
  3. Under Inventory → Network Sources, the IP of that machine shows up with the cisco-meraki connector.

Turn off blocking

Turn off, under Response & auto-block, asks for your second factor. SecureAI removes the patterns it wrote from each network and leaves yours, and the MX stops blocking those domains. The Activity Log records it with critical severity. If a network doesn’t accept the change, blocking stays on and that network keeps the SecureAI patterns until you turn it off again. If you pause network enforcement in SecureAI, SecureAI stops writing to the networks and the MX keeps blocking the last list.

What SecureAI does when something fails

The panel shows the code of the last failure.

Limits

  • Without decryption, only the host. The MX doesn’t decrypt HTTPS: the urls log of an HTTPS session carries the host and the method UNKNOWN, with no path. Content filtering also decides by host, so SecureAI blocks whole domains.
  • flows lines don’t add to the inventory. They carry IPs and ports, no host: SecureAI accepts them and doesn’t count them.
  • Content filtering blocks may not be counted. In Cisco’s documentation example, the content_filtering_block log carries the client’s MAC and not its IP, and SecureAI can’t tie it to a source. If your firmware adds client_ip, SecureAI counts it as blocked.
  • Entry limit. Neither the API reference (Update Network Appliance Content Filtering) nor the MX content filtering guide publishes a maximum number of blocked patterns, so SecureAI doesn’t cut by default. On a test network with no device, the Dashboard accepted and saved 20,000 patterns; we don’t know how many an MX applies. If the Dashboard rejects the list, that network keeps the one it had and the panel shows MERAKI_BAD_REQUEST. If you know your organization’s limit, ask support to set it: above it, SecureAI doesn’t write to any network and warns you with MERAKI_LIMIT.
  • Wildcards. The MX matches by stripping subdomains from left to right, so openai.com covers api.openai.com, and an asterisk inside a URL counts as text (How to Filter Web Content Using MX and Cisco Talos). That’s why SecureAI writes *.openai.com as openai.com. A wildcard in the middle (bedrock.*.amazonaws.com) can’t be written without widening it, and SecureAI leaves it out; the panel says how many patterns it left out.
  • A block reaches the whole network behind the MX, not a user or an IP.
  • Meraki has a “Generative AI” category. SecureAI doesn’t use it: it blocks by domain, provider by provider, so what you approve keeps working. If you turn it on by hand in the Dashboard, it can also block the providers you approved in SecureAI.

Tested versions