Recently active topics

I am not an AI n00b, I have configured dozens of MCP servers for our organization, including building our own custom Front MCP deployed on our own server architecture. I am trying to migrate to the official one, and cannot figure out how to make it work.  I have created a new developer app within Front following the instructions:  And I have added that to our organization in claude: (included adding the OAuth client id/secret)But when I go to connect to it, I get an error: Please advise. 

I got the MCP connected via Claude but it is telling me that the message content is truncated to 200 characters so it can’t read the full messages within a conversation. There isn’t a read_message tool or a flag to tell the MCP to return the full message content as far as Claude can tell after doing some probing. What am I missing? How do we read full message content within a conversation with the MCP? Thanks,Jeremy

I work at a logistic company, where we handle a lot of communication with customers and carriers every day.Since front is designed to make team communication easier, I wanted to ask:How do you use front to stay organized and avoid missing important messages during busy days at work?I’d love to hear your experiences or tips!Thanks! 

Usually when I want to paste into Front and keep the formatting, all I have to do is select the ‘Paste’ option or Ctrl + V and it does it with no problem. However, the past day or so, anytime I paste from any application into Front, it switches to strips the formatting. This is a huge problem for me with my job, as I am always pasting Excel tables into my emails. I guess somehow the default format is stuck in the composer? I can paste while keeping the formatting in any other application. Has anyone experienced this or has any idea how to fix it??

Good news :) Hopefully v1.1 will be ready soon. When you query open conversations via the API or MCP, you get the global conversation status not the per-inbox view your sidebar shows. This means archived conversations still show as open if they're active in any other inbox, making it impossible to programmatically replicate what you see in Front. For any team building AI agents or automations on top of Front, this is a fundamental blocker. 

It appears like Model Context Protocol (MCP) is the protocol that everyone is moving towards as it puts the burden of keeping everything “tidy” on the service provider rather than the client.  There are already many official MCP servers available and more on the way. There are also community developed ones. Is anyone else exploring this?Cheers!

I love the new knowledge base integration with AI, but I’d like to add additional context to the AI based on the user submitted message the AI is looking at.Having the AI have access to our MCP server means it can look up specific information about the user requesting help as well as access documentation.Is that a possibility?  I couldn’t find a good approach using Connectors.

UPDATE: There’s a new version of the MCP server. Please join the following group to learn how to get started: https://community.front.com/groups/beta-mcp-server-83The data access note for the original MCP server does not apply to the new one linked above. We're excited to announce the beta release of the Front MCP server — and we'd love for you to try it.Model Context Protocol (MCP) is an open standard that lets AI applications securely connect to external data sources and tools. With the Front MCP server, AI-powered tools like Claude, Cursor, Windsurf, and others can interact directly with your Front account and API documentation using natural language — no manual API calls required.What does that look like in practice?Ask your AI assistant to pull open conversations from a specific inbox, then tag or triage them Query your Front account data in real time to inform what you're building Explore Front's API endpoints and get full details about specific ones — without digging through doc