Using the Visualping MCP

Edited

Contents of this article


What is the Visualping MCP?

MCP (Model Context Protocol) is a standard that lets AI assistants like Claude and ChatGPT connect directly to external tools and services. The Visualping MCP allows you to manage your monitors and review detected changes using natural language without needing to open the Visualping dashboard.

Once connected, you can ask your AI assistant things like "Show me all my active monitors" or "Create a monitor for this URL" and it will handle the rest.


MCP: Reading full monitor settings

Full monitor configuration readable via MCP: AI assistants can read a monitor's complete settings such as AI alerting, notifications, schedule, page actions, and crawl config.


Connecting in Claude

Step 1:

Open Settings

In Claude, open Settings and navigate to the Connectors tab.

Step 2:

Add a custom connector

Click Add custom connector and enter the following URL in the Remote MCP URL field:

https://visualping.io/mcp/sse

Step 3:

Sign in to Visualping

You will be prompted to sign in with your Visualping email and password. Once authenticated, the connector will be active and ready to use in your Claude conversations.

Claude Code demo on competitive monitoring page

Claude Code now powers an animated demo on the competitive monitoring page that automatically creates 15 competitor monitors from a single prompt, demonstrating how the Visualping MCP integration works.

https://visualping.io/competitive-monitoring


Connecting in ChatGPT

Step 1:

Install the Visualping App

https://chatgpt.com/apps?q=visualping

Step 2:

Connect with the App

Select Create app and enter the following URL in the Remote MCP URL field:

https://visualping.io/mcp/sse

Click Connect, and sign into Visualping if necessary.

Step 3:

Sign in to Visualping

You will be prompted to sign in with your Visualping email and password. Once authenticated, Visualping will appear as an available tool in your ChatGPT conversations.

Note: To be able to use it in ChatGPT, make sure to enable the MCP in your chats. To do so, click on the + icon and select the tool.


What can I do with it?

Here are some examples of things you can ask your AI assistant once connected:

Viewing your monitors

  • "Show me all my active monitors."

  • "List any monitors tagged 'pricing'.

Managing monitors

  • "Pause the monitor for example.com."

  • "Run monitor 12345 now."

  • "Watch the pricing page at example.com for changes and alert me."

Reviewing changes

  • "Show me recent changes detected across my monitors."

  • "Flag the change with ID X as important."

Note: By default, your AI assistant will look at your first workspace. If you have multiple workspaces, you can ask it to check a specific one — for example: "Show me monitors in my Marketing workspace."


Frequently Asked Questions

Which Visualping plan do I need?

The Visualping MCP is available to all Visualping users.

Which AI clients are supported?

Currently, Claude and ChatGPT are supported. If you are having issues using the MCP with another AI client, please reach out to our Support team.

I'm having trouble connecting

Make sure the MCP URL is entered exactly as: https://visualping.io/mcp/sse (no www). If you continue to have issues, try disconnecting and reconnecting the connector, then sign in again with your Visualping credentials.

My AI assistant is only looking at one workspace

This is expected behaviour. Your AI assistant defaults to your first workspace. Simply tell it which other workspace to check, or ask it to look across all workspaces at once.

Error when requesting a short interval (e.g. every 5 minutes)

Your plan might not support that interval. Use 30, 60, or 1440 for free or lower-tier accounts. Upgrade your Visualping plan to access faster check frequencies.

Triggering an immediate check returns an error

Only active monitors can be run on demand. Ask Claude to list your monitors and confirm the monitor's status is active before retrying.


Related articles

Was this article helpful?

Sorry about that! Care to tell us more?

Thanks for the feedback!

There was an issue submitting your feedback
Please check your connection and try again.