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. 

Is there a limit to the amount of conditions an inbox rule can have?  We currently have a rule to auto archive based on the From address.  The list of addresses is about 20 long right now, but will we eventually reach a limit if we keep adding them?

Wondering how end users utilize the tagging function, in a group that manages a small-scale project for new retirement plan implementations to help manage outstanding tasks and timelines. Does it make the most sense to tag by client and use statuses? I was also thinking that tags for status or stage may be useful. What has worked for your team?

Hey, Having MCP and / or API be able to (at least) read the rules details would be a game changer. Other mail services allow to import / export rules as JSON files, which also helps a lot. Concrete example: Having to screenshot your rules 1 by 1 to share it to Claude to find bugs and inconsistencies is a real pain. The bigger the company, the more relevant this would be. Is this something Front could implement? 

I run an agency and we support many clients.  I want to be able to go to one spot and see all the emails from that company.  I had originally thought about doing this as tags. Then we made mailboxes for all the clients. This seems to be challenging though. I am seeing messages not show up in the mailboxes. I don’t think each client should have their own mailbox. How are other agencies doing this?

Dear all,I have just started using Front and I was wondering if anyone had tips on SLAs to improve customers experience? Thank you.

I’ve been running into problems with Claude reporting timeouts when I try to start a new session and use the Front MCP.  In 8 of the last 12 sessions I’ve had exactly 60 seconds after a successful connect, the local log shows HTTP connection dropped after 60s uptime followed by Failed to open SSE stream: Gateway Time-out. `initialize` on https://mcp.frontapp.com/mcp intermittently hangs with no response at all; observed 2026-06-20, 2026-07-01, and 2026-07-03 around 19:44–19:45 UTC today, with successful reconnect a minute later. Additionally the SSE stream (GET on the same endpoint) is consistently terminated with a Gateway Time-out after exactly 60 seconds of uptime, on essentially every session — looks like a gateway idle-timeout misconfiguration rather than a transient outage. These issues can be resolved by reconnecting, but it really is a pain and makes it much less smooth to try to use MCP.

Hi Javier — saw the "Bring Your Own AI Agent" post and this is right in our lane. I'm building an AI triage assistant on top of Front: it reads a conversation, then drafts replies, summarizes, archives, snoozes, and proposes actions. Today we do exactly the workarounds you mentioned — the agent's writes get attributed to a human account acting as a proxy — so a native agent identity with assignment and @mention support would be a real upgrade for us.One design point that's central to how we've built it: our agent is strictly human-in-the-loop — it proposes actions (replies, tags, archive, etc.) and a person approves them with one click; it never sends or executes on its own. Does the beta support that propose-then-human-confirms pattern (draft/suggested replies, gated actions), or is it oriented toward agents that act autonomously? That distinction is the thing I'd most want to get right.Happy to share concrete use cases — we have a working app and real triage flows. Thanks,Jim

Hi Front community, We successfully tested the MCP Server feature using OAuth and it works great. However, for our production use case we need this feature available for API Tokens as well.Our scenario: we are building a centralized MCP server hosted on our own infrastructure that acts as a proxy to Front's MCP, consumed by multiple support agents through AI assistants (Claude Code). The server needs to authenticate against Front without per-user OAuth flows.  The challenge with OAuth:  - The refresh token is tied to a specific user's identity  - If that person leaves the team or the token is invalidated, the integration breaks  - Managing token rotation in a server environment adds significant operational complexity  What we need:API Tokens with MCP Server feature enabled, so we can authenticate our server-side MCP proxy with a stable, long-lived credential that isn't tied to a specific user's session.This would be the ideal solution for teams building centralized MCP integrations on

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. 

Hey beta testers,We have a related beta we’re launching that has to do with bringing your own AI agents into Front. We know that some of you are using the MCP server to provide Front context to AI agents running complex workflows. We’d like to make that process smoother for you by allowing those agents to work directly within Front, bringing them into your workspaces as true teammates with governance and actions built around them.If this is interesting to you, please consider joining the AI agent beta group to get started.Thanks for your feedback on these emerging AI concepts!

Hey all — we have put together an early prototype of how external agents show up inside Front, and we'd love your feedback before we lock scope.I recorded a short walkthrough (6 min) so you can watch async on your own time:🎥 Video Link, Passcode: !e6jPNn? The video covers three things:Setting up an AI teammate — connecting your external agent to Front A live conversation — your agent picks up a conversation, drafts a reply, and asks a human a question The AI Command Center — where your agent's performance is measured and improvements are flaggedWhat we need from you — reply with the question number so we can follow the thread easily:In the setup flow shown, is anything missing or confusing for how you'd connect your agent? Looking at the conversation demo — does the way the agent drafts and hands off to a human match how you'd want it to work? How are you monitoring and governing your agents today, and what key quality/performance metrics do you track? What's the most impactful issue

Want to create word clouds from your Front conversations? This is a great way to quickly visualize the most frequently mentioned topics, pain points, issues, and positive feedback across your inboxes.To get started, you'll need to be a Front admin (or ask your admin to follow this guide). Navigate to Developers and create a new app:  Name your app and add a logo so its easily recognizable later: In the Features tab, click Add feature and select Sidebar Plugin: In the Sidebar URL field, paste the following url:https://dedarritchon.github.io/front-word-cloudand select the Clipboard component:Click create. We are all set. Go to your inbox, you should see your new Wordcloud app in the sidebar: Of course, the example was made with test data, but on real conversations it should show interesting facts about your customers.You can edit your resulting word cloud by tinkering with the settings.Hope this helps someone! If you tried it, Share your Wordclouds in the comments 😃 

 Now open: request access to the Amazon Connect beta (voice and SMS in Front) If your team is handling phone calls and texts in a different tool from the rest of your customer conversations, this one is for you. We just opened requests to join the beta for our Amazon Connect integration, which brings voice and SMS into Front alongside the email, chat, and everything else you already manage here. Once it is connected, you can place and receive calls, send and receive SMS, and pull up call recordings, transcripts, and AI summaries right in the inbox. The full history of a customer lives in one place instead of scattered across systems. This is a private beta and we are screening who joins, but if you are on the latest Professional plan or above and have a real voice or SMS use case, you are very likely a fit. You can preview the full setup steps in our Help Center. Want in? Request to join the beta group here.We will review and get back to you. Members get a dedicated space for updates a

Now open: request access to the Amazon Connect beta (voice and SMS in Front) If your team is handling phone calls and texts in a different tool from the rest of your customer conversations, this one is for you. We just opened requests to join the beta for our Amazon Connect integration, which brings voice and SMS into Front alongside the email, chat, and everything else you already manage here. Once it is connected, you can place and receive calls, send and receive SMS, and pull up call recordings, transcripts, and AI summaries right in the inbox. The full history of a customer lives in one place instead of scattered across systems. This is a private beta and we are screening who joins, but if you are on the latest Professional plan or above and have a real voice or SMS use case, you are very likely a fit. You can preview the full setup steps in our Help Center. Want in? Request to join the beta group here.We will review and get back to you. Members get a dedicated space for updates an

Hey everyone! 👋 I'm Carolina, the product designer working on Smart QA. I'd love to hear how you navigate and use your scorecards today, it'll help us make it faster and easier to spot and act on quality issues.Shouldn't take more than 5 minutes, and every answer helps, even a quick one!When checking quality for a teammate, do you usually start from the overall score or a specific criteria? What's the biggest pain point you run into when navigating scorecards today? We're also exploring how criteria could be sorted within a scorecard, which of these would you prefer, and why?Option 1 — Low to high score Option 2 — Alphabetical Option 3 — By category Anything else you'd improve about how scorecards work today?Thanks so much for taking the time! 🙏

Hello! Many of you have built agent(s) external to Front and we would love to know a bit more about your setup.  Give us the quick rundown of your current solution by filling our survey here.

 I don’t see an option to enable mcp server too. We use Front as our main customer support hub, especially for our Support Emails inbox. Our goal is to connect Front to Codex so our team can turn support conversations into clearer product insights and operational follow-through. Can you please help get us on the beta so we can try this out?