Connect HuggingChat to your fenbs kanban board
HuggingChat’s Chat UI documents custom MCP servers and needs a model that supports tools. Custom-server OAuth is not documented, and fenbs browser sign-in has not been live-tested; hosted availability is not established for every account.
Last checked
Hugging Face documents custom servers in the Chat UI software that powers HuggingChat. You need a model that supports tool calling and a deployment that enables MCP. Its MCP Tools guide (opens in a new tab) does not describe custom-server OAuth, and fenbs browser sign-in has not been live-tested. The documented software support does not establish the same settings for every hosted HuggingChat account.
Connect HuggingChat to fenbs
- Open HuggingChat. Where MCP is enabled, press + beside the chat box, or open Settings, then MCP Servers.
- Choose Add Server. Name it fenbs and paste the URL below.
- Run Health Check and enable fenbs in the MCP Servers panel. If sign-in is offered, finish it in fenbs.
- Start a chat with a model that supports tools and ask: “What is on my fenbs kanban board?”
https://fenbs.ai/api/mcp
Set it up in fenbs for these steps and the server address. Treat this as a documented custom-server route with an unverified fenbs sign-in, rather than a confirmed connection for every account. The Chat UI README (opens in a new tab) also warns that tool use depends on the model; turning on a tool-calling override does not give a model that ability.
What to save from a HuggingChat session, and how the next AI picks it up
After a useful session, keep the result you want to build on: what you tried, which model you used, what worked, what failed and the next step. If the fenbs connection works in your deployment, ask HuggingChat to save those details in fenbs. If it does not, save the useful text yourself instead of relying on an unverified tool call.
When you return, ask the connected AI to read the saved work in fenbs before it starts. It gets the result and next step you chose to keep, rather than an assumed transfer of the chat or model settings. This is especially useful when you change models or continue with another assistant: the handoff can describe the experiment without depending on the same chat screen.
Hugging Face’s Hub MCP server (opens in a new tab) is a separate connection that gives other assistants Hugging Face tools. Adding that server elsewhere does not establish that HuggingChat can sign in to fenbs. Keep the two directions separate when checking a setup.
Never lose the work you did in an AI session
After a useful AI session, save it in fenbs: the key observations, findings, research and context. Then carry on from exactly where you left off, on any device and in any other AI. The next AI you connect reads it at the start of the session, so you never have to explain the same problem again.
Create a free accountFree for up to 5 people and 50 open tasks · No credit card · Works with Claude, ChatGPT, Cursor and more