Unanswered questions

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 ? 

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. 

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?

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) 

I run an AI agent on claude that sweeps my Front every morning and surfaces what actually needs my attention, especially activity on our biggest deals. Front is the source of truth for that, so the agent reads conversations through the API (and I looked at the new MCP server too).The core problem: there's no way to programmatically get my "Open" view, the thing I look at in the UI every day. My Open is the union of my personal inbox + conversations assigned to me + conversations I'm subscribed/following. The first two are reachable. The subscribed bucket is not.Specifically:follower: search is unreliable. Searching follower:<me> returns only a handful of conversations (4 in my case) when my actual Subscribed bucket in the UI is 23. The conversation object itself correctly lists me under /conversations/{id}/followers, but I can't search or list by it. So there's no way to enumerate "everything I follow." No "Open view" union endpoint. Your own MCP docs confirm this: "There's also

Hi everyone, I’m interested to see how accounts could be leveraged in a rather specific way. I’m thinking about a use case where a Parent Company (Acme) has Subsidiaries (Acme France, Acme USA, Wayne Corp...), with sometimes different domain names.Traditional rules to tag these companies’ conversations, as VIP through the domain name for instance, could fail. In analytics, it would also be interesting to be able to select the parent company with its children companies nested, similar to the Tag > Sub-tag functionality.  On the picture below it makes sense that all “Acme” companies would be related, but Acme Inc could also own companies using a totally different name. Would be nice to have for reporting Is there a way to tie a Parent Company with its child? I saw an Account Custom Field “Parent Account ID”, does it integrate with the existing Salesforce functionality as shown below -- Hilton > DoubleTree > DoubleTree country subsidiaries Thank you for your time ! 

In regulated industries (lending, insurance, healthcare), who's allowed to handle a conversation often depends on something Front doesn't natively know - an active license, a coverage territory, a compliance certification - that lives in an external system of record. The pattern that's worked well for us: sync that external state into a Front custom field (e.g. an "Eligible" flag or region code) via API/webhook, then drive routing/assignment rules off the custom field instead of hardcoding teammate names or emails into rules. When the external system changes (someone's license lapses, territory shifts, roster changes), you update the sync/one field instead of touching a dozen rules. Curious how others are handling this: is anyone else routing based on data that lives outside Front, and if so, custom fields plus sync, or a different approach entirely (webhooks triggering direct API assignment, something else)?

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.

I was hoping to run some high-level reports through Claude using Front’s Analytics API, but hadn’t realized the Analytics API isn’t exposed in the MCP. Is there a timeline for this?Here is exactly what I was after:Total inbound message volume by inbox (in a specific calendar month) from the Workload report Topic breakdowns by inbox (in a specific calendar month) from the Topics report Average Response Time from Team Performance (for a specific calendar month) Smart QA / Smart CSAT scores (for a specific month)Here is what Claude said: The MCP doesn't expose Front's Analytics module (Workload, Topics, Team Performance, Smart QA, Smart CSAT reports) — those live in a separate reporting API that isn't part of the connector we have access to. 

I just followed the documented process for creating a custom connector to leverage the Front MCP within Claude chat.  First, I set up the OAuth app in Front and selected the MCP Server feature.  Then, I created the custom app in Claude Web.  After creating the custom app, I connected it through the browser interface, and it loaded a bunch of tools.  I set the permissions for the tools.When I attempt to use the connector through Claude Chat, Claude returns that “the Front tools aren’t surfacing through tool_search”  It says it is listed in my connected MCP servers, but no tools are loading.  I have attempted disconnecting, reconnecting, new Claude sessions, etc.

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?

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! 

Are you planning to implement OAuth 2.0 so users won't need to create Claude MCP connectors manually? That is how we connected our other apps to Claude, and it's a much more user-friendly experience. 

I’m experimenting with the Front MCP connector to build an email-triage workflow with an agent.The connector already lets the agent review conversations, list existing tags, and apply or remove tags from conversations, which is a great start.The capability I’d love to see added is broader tag management through MCP, including the ability to:create new tags rename or update existing tags remove tags that are no longer useful manage parent and child relationships adjust descriptions, colours, visibility, and inbox scopeThe main value for me is being able to iterate on the workflow collaboratively with the agent. As we test the triage process, I’d like the agent to have enough autonomy to refine the tag structure over time rather than requiring every change to be made manually in Front.I understand the MCP integration is still in beta and does not yet expose every Front capability. Tag management would make it much easier to build and evolve more complete agent-driven workflows.

Has anyone connected Front to Planhat? If so, did you find that this connection was worth your time? 

Need to quickly check the status of a customer's flight without leaving Front? In this tutorial, we'll create a simple Sidebar Plugin that embeds a live flight tracking website directly inside Front, making it easy for support agents and travel teams to monitor flights while responding to customers.This example demonstrates one of the simplest ways to extend Front with custom tools. The same approach can be used to embed internal dashboards, booking systems, CRMs, status pages, and many other web applications.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.Give your app a name, such as Flight Tracker, and upload an icon so it's easy to recognize later.Open the Features tab, click Add feature, and select Sidebar Plugin.In the Sidebar URL field, paste:https://www.flightradar24.comReplace this URL with the URL where you've deployed the plugin.For the component, select Clipboard.Click Create.That's it! 🎉O

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. 

Hi everyone, yesterday I started getting this when trying to reconnect to mcp:❯ /mcp  ⎿  Got new credentials, but front rejected them on reconnect. Try     re-authenticating, or restart Claude Code if it persists.And if I close claude code and reconnect then I get this error after authenticating in the browser: This is the same mcp connection we’ve used since day one, haven’t changed a thing. As far I can see there isn’t a global MCP setting somewhere for the organization?

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?

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?