Re:amaze

@Re:amaze show me all the response templates we have set up for our support team

Here are your Re:amaze response templates: 'Shipping Delay Apology' (used 47 times this month), 'Refund Request Confirmation' (used 23 times), 'Password Reset Instructions' (used 89 times), 'Feature Request Acknowledgment' (used 12 times), and 'Billing Question Standard Response' (used 34 times). Each template includes placeholder variables for customer name and order number. The most-used template averages 2.3 minutes saved per conversation.

This example shows the MCP retrieving your team's canned responses. Useful for auditing template usage or finding the right snippet to copy. Requires API key with read access to templates. The MCP returns template names and metadata but won't auto-insert them into live conversations — that's a manual step in Re:amaze's UI.

@Re:amaze what are our top 5 conversation tags from the last 30 days and how many times was each used?

Top 5 tags in the past 30 days: 'billing-issue' (142 conversations), 'bug-report' (98 conversations), 'feature-request' (67 conversations), 'shipping-delay' (54 conversations), 'account-access' (41 conversations). These tags represent 62% of all tagged conversations. The 'billing-issue' tag spiked 34% compared to the prior month, suggesting increased payment friction or a recent pricing change.

This example demonstrates tag analytics retrieval. The MCP pulls aggregate counts but won't show individual conversation threads. Helpful for spotting support trends or validating tag taxonomy. Note that tag data reflects only what your team has manually applied — untagged conversations won't appear in these metrics.

@Re:amaze pull our response templates and draft a new one for handling GDPR data deletion requests based on the tone of our existing templates

Based on your existing templates (which average 78 words and use a friendly, solution-focused tone), here's a draft GDPR deletion template: 'Hi [Customer Name], we've received your request to delete your personal data under GDPR Article 17. We'll process this within 30 days and send confirmation to this email address. Please note that we're required to retain transaction records for [X] years per [jurisdiction] law. If you have questions about what data we'll remove versus retain, reply to this message and we'll clarify. Thanks for letting us know.' This matches your team's empathetic style while covering compliance basics.

This example pairs the MCP's template-fetching tool with the AI's drafting ability. The MCP provides existing templates as context; the AI synthesizes a new one. You'll still need to manually add the draft to Re:amaze and adjust placeholder variables. The MCP can't write templates directly into your account — it's read-only for template data.

When Re:amaze MCP helps standardize customer replies at scale

A 6-person support team handling 200+ tickets daily needs to audit whether agents are using approved templates consistently. The Re:amaze MCP pulls response templates and tag reports into Switchy, letting the team lead compare actual conversation tags against template usage patterns in a shared workspace. This works when your team already uses Re:amaze tags religiously and templates are the source of truth for tone and compliance. The MCP breaks down if your agents freestyle most replies or if you need deeper analytics than tag counts—Re:amaze's native dashboard will serve you better there. For teams that live in templates and want a quick cross-check without leaving their AI workspace, this MCP delivers the two data points that matter: what templates exist and how tags cluster across conversations.

Re:amaze MCP as a training reference for new hires

A startup hiring its second and third support agents needs to ramp them fast on approved language and common issue categories. The Re:amaze MCP surfaces response templates directly in Switchy, so new hires can ask the AI to explain when to use each template or compare tag distributions from their first week against the team average. This scenario works when your onboarding bottleneck is template discovery, not policy nuance—if your support playbook lives outside Re:amaze or requires judgment calls the templates don't encode, the MCP won't close the gap. The two-tool limit means you're not automating ticket workflows here, just making the reference material conversational. For teams where template fluency is 80% of the onboarding curve, this MCP turns a static help center into an interactive coach.

Using tag reports to prioritize help articles and macros

A 3-person team reviews support trends monthly to decide which help articles to write or which new templates to create. The Re:amaze MCP pulls tag reports into Switchy, where the team can ask the AI to rank tags by frequency, flag emerging topics, or compare this month's distribution to last quarter's. This works when your tags are granular enough to reveal content gaps—if you only tag by channel or sentiment, the report won't guide editorial decisions. The MCP doesn't write the articles or create the templates; it just surfaces the tag data in a format you can interrogate conversationally. For small teams that treat tags as a lightweight taxonomy and want to spot trends without building a BI dashboard, this MCP turns monthly reporting into a 10-minute Switchy session.