Recently active topics

Hey! I was just wondering if you could tell me more about how does the MCP work in terms of GDPR? Is our customer’s data safe/anonymised in the process? 

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. 

We’re happy to announce that we’re now officially listed in Claude’s connector directory! This should make it easy for you to connect to the Front MCP server. Prior to being listed on the directory, you had to connect Claude to Front’s MCP server as a custom connector, which involved setting up a developer app in Front and then configuring the connection details in Claude. You can now connect directly from the directory listing by simply logging into Front when prompted. If you have other directories you’d like to see us listed in, please let us know in the comments!

We’re happy to announce that we’re now officially listed in Claude’s connector directory! This should make it easier for you to connect to the Front MCP server. Prior to being listed on the directory, you had to connect Claude to Front’s MCP server as a custom connector, which involved setting up a developer app in Front and then configuring the connection details in Claude. You can now connect directly from the directory listing by simply logging into Front when prompted. If you have other directories you’d like to see us listed in, please let us know in the comments! Please note, we launched in the directory last week, but there was a bug on Anthropic’s end that prevented some connections from being successful. Anthropic deployed a fix and we have tested to verify it, but please let us know if you still see issues!

You can now subscribe to conversation lifecycle events in Autopilot Resolve, so your app can react in real time as end users move through a conversation, from starting a new one to escalating to a human teammate. Available event types:created: end user starts a new conversation viewed: end user opens or navigates to a conversation escalation_offered: Autopilot Resolve offers to hand off to a human escalated: the conversation is handed off escalation_declined: end user dismisses the offer status_changed: the conversation moves between open, in_progress, and resolvedThree ways to subscribe, depending on your setup:FrontCompanion.on(handler) for a synchronous listener that returns an unsubscribe function onConversationEvent as an option on init() to register in the same call A companion-conversation-event CustomEvent on window, which works even before the boot script has loadedCommon patterns include firing your own analytics when a conversation escalates, updating your UI when a new conv

We've released a new version of Front Desktop with the following changes:Fixed an issue that prevented signing in to Zoom from the desktop app. Popup windows now open at a proper size. Fixed a problem with clearing temporary storage, improving stability.

We’ve been listening to your feedback on being able to take action on Smart CSAT and Manual CSAT Scores. They’re now available as dynamic variables as conditions in rules to trigger actions such as tagging "low-CSAT", routing or assigning for review or triggering a customer reviews flows or follow up notes on high scoring Manual CSATs!💡 Share how you might use this in your process workflows ? 

You can now create application channels programmatically, without manual setup in the Front UI for every new channel your app needs. This unlocks fully automated provisioning flows so your integration can spin up channels as customers onboard or as new use cases emerge. POST /inboxes/:inbox_id/channels To create an application channel, send a request with:type set to custom application_uid set to the developer app that defines the channel credentials matching your application server's authentication type (API key, basic, bearer, or OAuth2 variants)For OAuth2 authorization_code flows, omit credentials and complete the OAuth flow interactively after the channel is created. Full parameter details, credential shapes, and examples are in the reference docs. Happy coding!

We are looking for an individual to work with an ongoing basis to better customize our Front setup alongside our teams to get the full use out of the platform. 

New to Front? Here's what teammate groups are, and why they replaced custom roles. If you're newer to Front you might see people mention "custom roles" and "teammate groups" and wonder what the difference is. Front moved from one to the other, so I wanted to break it down in plain terms: what a teammate group actually is, and why it's a better way to run your team. So what is a teammate group? It's just a named list of people. That's really it. You might have a Support group, a Sales group, a Managers group, and so on. Once you've built that list, Front lets you reuse it for lots of things instead of setting up each person one by one. What can you use them for? A single group can control: What those people are allowed to do (reply to messages, delete them, change settings, and so on) What they can see (which inboxes and workspaces) Where work goes. You can point a routing rule at a group so incoming messages get shared out among them automatically. So one list answers four questions at

Hi Front team,Sharing a feature request for the MCP server. First, thanks for the open beta and for gathering feedback here directly.The MCP server currently has no Knowledge Base tools. I'd love to see the KB surfaced through MCP.We run a public help center on Front's KB and I'm building an AI agent to keep it healthy — specifically a periodic link audit. For each article, the agent needs to look at the outbound links to other KB articles and flag ones that are broken.Concretely, the tools I'd hope to see- read_knowledge_base_article — returns body with links as [label](url) (or a structured list of links with hrefs), plus last-modified date- list_knowledge_base_articles / list_knowledge_base_categories — for enumerationLater we also like to create drafted articles in some other workflow.So, would love to know if KB support is on the roadmap, and happy to be an early tester if useful. Thanks!

We're a sales team of just three people at a small, local growth company, and we're using a shared inbox on the front end. We're struggling to decide how many routing rules are worth creating when we're so small: should we route by customer type, by pipeline stage, or just let anyone take the conversation as it comes in? If you have a small sales team, what rule/routing configuration has worked best for you without becoming an administrative burden?

Setup: I sync messages from the Core API and process them downstream. For that I need just the new content of each message, not the quoted thread history, signatures or disclaimers.What the API gives me:- `body` - full HTML, including everything- `text` - plaintext rendering, also including everything- `blurb` - quote-free, but truncated, so usable as a signal at bestSo I'm parsing the HTML myself, and running into the usual wall: no standard for marking quoted content, every client does it differently, unclosed tags, tables used for layout. Forwards are the worst case, some clients wrap the entire forwarded message in a single blockquote, so naive stripping leaves an empty body.Front clearly handles this internally (collapsed quotes in the UI, the `front-quoted` class, rules that skip quoted text when matching conditions).1. Is that exposed anywhere I've overlooked, an endpoint, field, parameter, or a paid add-on? Happy to pay for it.2. If not, what are you all using? Interested in wh

Hi everyone! I'm Carolina, the product designer working on Smart CSAT and Smart QA. I'm sharing some designs of concepts we're currently exploring and would love your feedback on.Live CSATWe're exploring a new signal called Live CSAT. Unlike Smart CSAT, which scores a conversation after it closes, Live CSAT surfaces a predicted satisfaction signal while the conversation is still open. You would also be able to use it in rules to get notified when a conversation is at risk of receiving a low CSAT score.Smart CSAT and Smart QA in one placeWe're also exploring consolidating Smart CSAT and Smart QA into a single side panel in your inbox, so all your quality signals live together in one place once a conversation closes.   We'd love your thoughts:What are your first impressions of these designs? How do you imagine using Live CSAT in your workflow? Is there any information missing from the side panel that would be useful to you?Thanks so much for taking the time, we're excited to hear what yo

Hi,I am following your steps for connecting our Ai assistant (ChatGPT), but the Registration URL does not auto-populate. What is the Registration URL for Front’s MCP?A walk-through video showing how to connect Ai assistants would be extremely helpful (Section 2 in https://dev.frontapp.com/docs/mcp-server) 

Hi all, Assumption 1: an Admin created a Tagging Rule, which flags inbound messages containing a certain keyword as “urgent”. Assumption 2: a similar Topic leverages AI to identify “urgent” messages.  Assumption 3 : on the same mailbox, there is a Required Tagging rule, which forces the assignee resolving the message to tag it I’d be interested to see if it is possible to compare the Required Tagging final tag with the original tag and topic. This could help flag wrongly built tagging rules for instanceHas anyone ever created a custom report to do that?Or would you just export Tags/Topics Analysitcs report, feed them to Claude/Chat and ask it to compare with ticket ID? Thanks for your time! 

We're a small company with just a few people handling customer communication, and we don't have a huge volume of emails yet. I'm wondering if it's still worth using Front at this size, or if it's more geared toward larger teams with higher email volume. For those of you who started using Front early on, did you find it useful even before scaling up? Curious to hear how it worked out for you.