Experiments with MCP in Wagtail

Wagtail released wagtail-mcp, an experimental Model Context Protocol package that exposes 50+ CMS tools to AI agents, the project announced. The server was vibe-coded with Kimi K3 and the Pi coding agent in August and includes an in-CMS agent interface built with the AG-UI protocol and CopilotKit; queries run through AI provider Neuralwatt at less than 1 Wh each. Wagtail said giving agents CMS access is promising but dangerous, and that deciding how to offer it with stronger safety guarantees remains the hard work.

Experiments with MCP in Wagtail Prototyping with agents interacting directly with the CMS Following our work to prototype a new CLI for Wagtail https://wagtail.org/blog/prototyping-a-cli-for-wagtail/ , it only felt right to experiment with other ways to give agents access to the CMS via our new API https://wagtail.org/blog/cms-with-ai-not-ai-cms-wagtail-80s-new-api/ and open up opportunities for automation. And voilà , a new experimental MCP https://modelcontextprotocol.io/ package Pretty cool, right? This is wagtail-mcp https://github.com/wagtail/wagtail-mcp , vibe-coded with Kimi K3 and the Pi coding agent back in August, now stable enough for a demo. 50+ tools and an agent interface The server comes with 50+ tools, same as the API. To demo this more easily, we also added an agent interface with the same tools directly in the CMS, built with the AG-UI protocol https://www.copilotkit.ai/ag-ui and CopilotKit. Here’s an example, asking the agent in natural language, how many redirects we have on the site in total: We set this up with one of our preferred AI providers https://wagtail.org/blog/comparing-open-weight-ai-models-and-providers/ , Neuralwatt, so we know exactly how much energy this uses per query: less than 1 Wh - very little. Beyond prototyping Giving agents access to the CMS is very promising but also very dangerous, even with Wagtail’s strong permissions model. In a sense, adding MCP with authentication and permissions matching what we have for users was the easy part, and the hard work left to do is to decide how to make this available with stronger guarantees of safety. Whether we make it stricter for agents, or rework content operations in other ways. In the meantime, if you want to experiment, do give a go to the new package https://github.com/wagtail/wagtail-mcp , and let us know what you think https://github.com/wagtail/wagtail/discussions/14531