What is a Front MCP?
A Front MCP is a server that connects AI agents to your Front workspace through a set of callable tools. Your agents can invoke these tools to read and send messages, manage conversations, update contact records, add tags, and more.
Front offers an official MCP server (in beta). You can also connect to a fully-managed Front MCP server through a third-party platform, like Merge Agent Handler.
How can I use the Front MCP server?
The use cases naturally depend on the agent you've built, but here are a few common ones:
- Automated conversation routing. When a new conversation arrives in a shared inbox, an agent can read the message content, identify the appropriate team or tag based on keywords or sender, and update the conversation assignment without a human stepping in
- Contact enrichment on inbound. When a new contact sends a message in Front, an agent can look up their record, pull account or deal context from a connected CRM, add a note to the contact in Front, and tag the conversation accordingly
- Support escalation workflows. An agent can monitor conversations for escalation signals such as specific keywords or SLA thresholds, add a priority tag, notify the relevant teammate, and post an internal comment summarizing the context
- Weekly inbox health reporting. An agent can query open conversations across inboxes, group them by team or tag, calculate response time metrics, and deliver a structured digest to a Slack channel or email recipient on a set schedule
What are popular tools for Front's MCP server?
Here are some of the most commonly used tools:
<code class="blog_inline-code">list_conversations</code>: retrieves conversations from Front with filtering by inbox, assignee, tag, or status, used by agents that monitor queue health or identify conversations requiring action
<code class="blog_inline-code">search_conversations</code>: runs a full-text search across Front conversations, useful when an agent needs to find prior context about a contact or topic before responding
<code class="blog_inline-code">reply_to_conversation</code>: sends a reply in an existing conversation thread, used by agents that handle routine responses or acknowledgments based on predefined conditions
<code class="blog_inline-code">update_conversation</code>: modifies conversation fields like assignee, status, or inbox, called when an agent needs to route or close a conversation based on its content or age
<code class="blog_inline-code">add_conversation_tag</code>: applies a tag to a conversation, used by agents that categorize inbound messages automatically based on content classification
<code class="blog_inline-code">create_contact</code>: adds a new contact record to Front, typically called when an agent detects a first-time sender who doesn't yet have a record in the workspace
What makes Merge Agent Handler's Front MCP server better than alternative Front MCP servers?
If you're deciding between building your own Front connector or using Merge Agent Handler, here is what tips the balance:
- Enterprise-grade security and DLP. Merge Agent Handler includes built-in data loss prevention controls that let you block or redact sensitive fields before they reach an agent. For Front, this means customer message content, contact handles, and internal comments can be masked even when the agent has broad conversation access
- Managed authentication and credentials. Merge stores and refreshes Front credentials on your behalf. You never hand raw API tokens to an agent or write token rotation logic yourself
- Real-time observability and audit trail. Every tool call against Front is logged with timestamp, tool name, input parameters, and response metadata. Support and ops teams get a complete record of what the agent read, sent, or modified
- Tool Packs and controlled access. Tool Packs let you define exactly which Front tools an agent can access, and pair them with tools from other connectors in a single scoped MCP endpoint. A triage agent can have conversation and tag tools. A reporting agent can have inbox and teammate tools. Each gets only what its use case requires
How can I start using Merge Agent Handler's Front MCP server?
You can take the following steps:
1. Create or log into your Merge Agent Handler account and navigate to Tool Packs.
2. Create a new Tool Pack and enable the Front connector. Select which tools to include. Read and search tools cover most monitoring and reporting use cases, while write tools are available if your agent needs to reply to conversations, update assignments, or manage contacts.
3. Add a Registered User to the Tool Pack. This defines the identity context your agent operates under, and Merge generates a unique MCP URL tied to that user.
4. From the Registered User detail page, complete the Front OAuth flow. Merge handles credential storage and refresh automatically from that point forward.
5. Copy the MCP URL from the Tool Pack detail page and generate an API key under Settings. Both are required to connect your agent.
6. Add the MCP server configuration to your agent or IDE using the MCP URL and API key. Your Front tools will be available through that endpoint immediately.
Can employees use Merge Agent Handler to connect their AI tools to Front?
Yes, Agent Handler for Employees lets your employees connect Claude, ChatGPT, Microsoft Copilot, Cursor, and other MCP-compatible AI tools to Front without bypassing IT governance.
Instead of setting up direct connections with personal credentials that IT can't monitor or revoke, each employee authenticates through Agent Handler and gets individual credentials tied to their identity.
IT also provisions access by role or group via SCIM. A support agent, for example, gets Front access to manage and respond to conversations, Zendesk to cross-reference open tickets, and Slack to coordinate with the escalation team; while a customer success manager gets Front access to review account communication history, Salesforce to pull CRM context, and Google Calendar to schedule follow-up meetings.
Every tool call an employee's AI makes to Front is also inspected against your DLP rules and logged to a searchable audit trail, giving security teams full visibility into what data was accessed and by whom.