{"slug": "experiments-with-mcp-in-wagtail", "title": "Experiments with MCP in Wagtail", "summary": "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.", "body_md": "# Experiments with MCP in Wagtail\n\n## Prototyping with agents interacting directly with the CMS\n\nFollowing 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!\n\nPretty 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.\n\n## 50+ tools and an agent interface\n\nThe 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:\n\nWe 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.\n\n## Beyond prototyping\n\nGiving 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.\n\nIn 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)!", "url": "https://wpnews.pro/news/experiments-with-mcp-in-wagtail", "canonical_source": "https://wagtail.org/blog/experiments-with-mcp-in-wagtail/", "published_at": "2026-09-24 00:00:00+00:00", "updated_at": "2026-09-24 14:59:12.856403+00:00", "lang": "en", "topics": ["agent-protocols", "ai-agents", "developer-tools", "ai-tools"], "entities": ["Wagtail", "wagtail-mcp", "Model Context Protocol", "Kimi K3", "Pi", "AG-UI", "CopilotKit", "Neuralwatt"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/experiments-with-mcp-in-wagtail", "markdown": "https://wpnews.pro/news/experiments-with-mcp-in-wagtail.md", "text": "https://wpnews.pro/news/experiments-with-mcp-in-wagtail.txt", "jsonld": "https://wpnews.pro/news/experiments-with-mcp-in-wagtail.jsonld"}}