cutie-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@cutie-mcp show me the dashboard analytics for the last 7 days"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
cutie-mcp
MCP server for the Cuti-E admin API. Manage conversations, reply to feedback, and monitor the platform from Claude Code or any MCP-compatible client.
Features
List and filter conversations (by status, priority, app, category, search)
View conversation details with full message history
Send replies and internal notes
Update conversation status, priority, and assignment
List apps and view app configuration
Dashboard analytics (conversation stats, response times, breakdowns, trends)
Team member listing
Customer/team info
Active user stats (DAU/WAU/MAU) per app or across all apps
Related MCP server: Chatlog MCP Server
Installation
cd ~/.claude/mcp-servers/cutie-mcp
npm installConfiguration
Environment Variables
Variable | Required | Description |
| Yes | Admin API key ( |
| No | API base URL (default: |
Generate an API Key
# Using session auth (from admin dashboard login)
curl -X POST https://api.cuti-e.com/v1/admin/api-keys \
-H "Authorization: Bearer <session_token>" \
-H "Content-Type: application/json" \
-d '{"name": "Claude MCP"}'The response includes the full api_key (only shown once). Store it securely.
MCP Configuration
Add to your .mcp.json:
{
"mcpServers": {
"cutie-mcp": {
"type": "stdio",
"command": "node",
"args": ["/Users/post/.claude/mcp-servers/cutie-mcp/index.js"],
"env": {
"CUTIE_API_KEY": "ck_live_..."
}
}
}
}Tools
Conversations
Tool | Parameters | Description |
|
| List conversations with optional filters. Returns status, priority, unread counts, and pagination. |
|
| Get a single conversation with full message history and tags. |
|
| Send a visible reply or internal admin note. |
|
| Update one or more fields on a conversation. |
|
| Close/delete a conversation. |
list_conversations filter values:
status:open·in_progress·waiting_user·waiting_admin·resolved·closedpriority:low·normal·high·urgentcategory:bug·feature·question·feedback·othersort:last_message(default) ·created·updated
Apps
Tool | Parameters | Description |
| — | List all registered apps with usage stats. |
|
| Get app details, configuration, and notification settings. |
Analytics
Tool | Parameters | Description |
|
| Conversation stats, response times, category/status/priority breakdowns, daily trends, and team activity. |
|
| DAU/WAU/MAU for a specific app. |
|
| Active user counts aggregated across all apps. |
|
| AI-classified sentiment breakdown (positive/neutral/negative) by app and category. |
Feature Requests
Tool | Parameters | Description |
|
| AI-extracted feature requests ranked by vote count. |
|
| Update the status or title of a feature request. |
|
| Merge a duplicate into a target — combines votes and linked conversations, deletes source. |
Team & Account
Tool | Parameters | Description |
| — | List all team members with their roles. |
| — | Get team/customer info including tier, mascot settings, and brand color. |
* Required parameter
Security
API keys are bearer tokens with full admin access to the team's data
Keys use SHA-256 hashing (never stored in plain text)
Keys can be revoked instantly via
DELETE /v1/admin/api-keys/:keyIdOptional expiry via
expires_in_daysparameter at creationNever commit API keys to git -- use environment variables
Available Tools
16 toolsdelete_conversationC
Close/delete a conversation.
Inputs: conversation_id (required).
get_active_usersA
Get active user count (DAU/WAU/MAU) for a specific app based on anonymous activity pings.
Inputs: app_id (required), period.
get_active_users_all_appsC
Get active user counts across all apps at once. Queries each app's DAU/WAU/MAU stats.
Inputs: period.
get_appC
Get details for a specific app including configuration and notification settings.
Inputs: app_id (required).
get_conversationB
Get a single conversation with its messages and tags.
Inputs: conversation_id (required).
get_customerB
Get current team/customer info including tier, mascot settings, and brand color.
Inputs: no named parameters.
get_dashboardC
Get analytics dashboard with conversation stats, response times, breakdowns by category/status/priority/app, daily trends, and team activity.
Inputs: period.
get_feature_requestsB
Get AI-extracted feature requests ranked by vote count. Each request is auto-extracted from user feedback and de-duplicated.
Inputs: status, app_id, search, limit.
get_sentiment_insightsC
Get sentiment analysis breakdown (positive/neutral/negative) by app, category, and time period. Powered by AI classification.
Inputs: period, app_id.
list_appsB
List all registered apps for the current team, with usage stats.
Inputs: no named parameters.
list_conversationsC
List conversations with optional filters. Returns conversations with status, priority, unread counts, and pagination.
Inputs: status, priority, app_id, search, +5 more.
list_teamB
List all team members with their roles.
Inputs: no named parameters.
merge_feature_requestsA
Merge a duplicate feature request into a target. Combines vote counts and linked conversations, then deletes the source.
Inputs: target_id (required), source_id (required).
send_replyC
Send a reply message in a conversation. Can be a visible reply or an internal note.
Inputs: conversation_id (required), message (required), is_internal_note.
update_conversationC
Update conversation status, priority, assignment, title, or category.
Inputs: conversation_id (required), status, priority, assigned_admin_id, +2 more.
update_feature_requestC
Update the status or title of a feature request.
Inputs: request_id (required), status, title.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 16 tools
Most tools have distinct purposes targeting specific resources like conversations, apps, users, or feature requests, with clear separation between get/list operations. However, some potential overlap exists between 'get_dashboard' (analytics overview) and other specific analytics tools like 'get_active_users' or 'get_sentiment_insights', which could cause minor confusion about which to use for detailed metrics.
Tool names follow a highly consistent verb_noun pattern throughout, using clear action verbs like get, list, update, delete, send, and merge paired with specific nouns. All names use snake_case uniformly, making them predictable and easy to parse for an agent.
With 16 tools, the count is slightly on the higher side but reasonable for a customer support/analytics domain that covers conversations, apps, users, dashboards, and feature requests. It provides comprehensive functionality without being overwhelming, though it borders on feeling heavy compared to more focused servers.
The toolset offers excellent coverage for a customer support platform, including full CRUD/lifecycle operations for conversations (list, get, update, delete, send_reply), apps (list, get), feature requests (get, update, merge), and analytics (dashboard, active users, sentiment). No obvious gaps are present, enabling agents to handle end-to-end workflows effectively.
Maintenance
Related MCP Connectors
Manage SRG+ hubs, channels, content, assets, users, and workspaces from any MCP-aware AI agent.
Managed MCP gateway with OAuth, per-agent permissions, shared accounts and activity logs.
Secure and manage MCP servers through the Speakeasy AI Control Plane from your agent.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceAn MCP (Multi-Agent Conversation Protocol) Server that enables interaction with the WhatsApp Business API, allowing agents to send messages, manage media, and perform other WhatsApp business operations through natural language.1-
- AlicenseNot gradedqualityDmaintenanceEnables users to analyze, search, and export chat logs from various platforms through tools for managing chatrooms, contacts, and sessions. It supports advanced filtering by time, keyword, and sender to provide detailed message analytics via MCP-compatible clients.MIT
- AlicenseBqualityDmaintenanceEnables the management of AI-powered VibeKit apps, allowing users to control deployments, monitor logs, and perform database operations directly from MCP-compatible clients. It facilitates interaction with hosted AI agents and the execution of headless coding tasks through natural language.49201 npmMIT
- FlicenseNot gradedqualityBmaintenanceEnables AI clients to manage SlimWeb/Webless e-commerce backend operations such as products, orders, categories, promotions, and settings through a secure Remote MCP server.-