Monotype MCP Server
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., "@Monotype MCP Server Invite john.doe@example.com to our engineering team"
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.
Monotype MCP Server & Chat Application
A complete system consisting of:
MCP Server - Plugin-ready server for Monotype API integration
Backend - Ollama-powered bridge between chat UI and MCP server
Frontend - React-based chat interface
Architecture
┌─────────────┐ ┌──────────────┐ ┌─────────────┐ ┌──────────────┐
│ Frontend │─────▶│ Backend │─────▶│ MCP Server │─────▶│ Monotype API │
│ (React) │ │ (Ollama) │ │ (Plugin) │ │ │
└─────────────┘ └──────────────┘ └─────────────┘ └──────────────┘Related MCP server: OneLogin MCP Server
Project Structure
NextGenAgenticAI/
├── src/ # MCP Server (can be used as plugin)
│ ├── server.js # Main MCP server
│ ├── api-client.js # Monotype API client
│ ├── auth.js # Authentication service
│ ├── token-decryptor.js # Token decryption utilities
│ └── ...
├── backend/ # Backend server
│ ├── server.js # Express server with Ollama integration
│ └── package.json
├── frontend/ # React chat UI
│ ├── src/
│ │ ├── App.jsx # Main chat component
│ │ └── ...
│ └── package.json
└── README.mdQuick Start
1. MCP Server (Plugin)
The MCP server can be used independently as a plugin with any chat agent.
Setup:
cd src
npm installConfiguration: Add to your MCP client config:
{
"mcpServers": {
"monotype-mcp": {
"command": "node",
"args": ["/path/to/src/server.js"],
"env": {
"MONOTYPE_TOKEN": "your-token-here"
}
}
}
}2. Backend Server
Prerequisites:
Install Ollama: https://ollama.ai
Pull llama3 model:
ollama pull llama3
Setup:
cd backend
npm install
npm startServer runs on http://localhost:3001
3. Frontend
Setup:
cd frontend
npm install
npm run devFrontend runs on http://localhost:3000
Features
MCP Server Tools
invite_user_for_customer- Invite users to your companyget_teams_for_customer- Get all teamsget_roles_for_customer- Get all roles
Backend Intelligence
Uses Ollama (llama3) to detect which tool to call
Extracts parameters from natural language
Fallback keyword matching if Ollama unavailable
Frontend
Secure token input
Modern chat interface
Real-time responses
Tool usage indicators
Usage Examples
Via Chat UI
Start backend and frontend
Enter your token
Try these commands:
"What roles are in my company?"
"Invite user@example.com to my company"
"Show me all teams"
Via MCP Plugin
Use the MCP server directly with any MCP-compatible chat agent (like Cursor, Claude Desktop, etc.)
Development
Running All Services
Terminal 1 - Backend:
cd backend
npm run devTerminal 2 - Frontend:
cd frontend
npm run devTerminal 3 - MCP Server (if testing standalone):
cd src
npm startEnvironment Variables
Backend
MCP_SERVER_PATH- Path to MCP server script (default:../src/server.js)OLLAMA_API_URL- Ollama API URL (default:http://localhost:11434)
MCP Server
MONOTYPE_TOKEN- Your Monotype authentication token (optional, can be set in MCP config)
License
MIT
Available Tools
4 toolsget_role_id_by_nameA
Get role ID by role name. Searches through all roles for the customer and returns the role ID if found.
Inputs: roleName (required), customerId.
get_roles_for_customerC
Get all roles for a specific customer ID
Inputs: customerId.
get_teams_for_customerC
Get all teams for a specific customer ID
Inputs: customerId.
invite_user_for_customerC
Invite a user for a customer. This is equivalent to creating a user for the customer. The user receives an email invitation and then gets onboarded.
Inputs: email (required), roleId (required), teamIds, status.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: get_role_id_by_name retrieves a specific role ID, get_roles_for_customer lists all roles, get_teams_for_customer lists all teams, and invite_user_for_customer handles user invitations. There is no overlap or ambiguity between these operations.
All tools follow a consistent verb_noun pattern with underscores, using 'get' for retrieval operations and 'invite' for creation. The naming is predictable and readable across the set.
With only 4 tools, the server feels thin for a customer management domain. While the tools cover basic retrieval and user invitation, the scope suggests more operations (e.g., updating roles/teams, managing users) would be expected, making the count borderline.
The toolset has significant gaps for customer management. It lacks update or delete operations for roles, teams, or users, and missing core functions like creating roles/teams or managing user details. This incomplete coverage will likely cause agent failures in common workflows.
Maintenance
Related MCP Connectors
Create and manage AI agents that collaborate and solve problems through natural language interacti…
Manage projects, tasks, time tracking, and team collaboration through natural language.
Deploy apps from GitHub, read build/runtime logs, and manage your app's users from your AI agent.
Deploy, monitor, and manage your OpenClaw AI assistants via natural language.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables user name resolution and team management with PostgreSQL backend, providing fuzzy user lookup, batch operations, team hierarchy navigation, and calendar insights through natural language queries.MIT

OneLogin MCP Serverofficial
AlicenseNot gradedqualityBmaintenanceEnables managing users, apps, roles, authentication, and security settings through natural language, providing comprehensive access to the OneLogin API.4,028 npm6MIT- AlicenseNot gradedqualityDmaintenanceIntegrates LLMs with Okta's Admin Management APIs, enabling natural language management of users, groups, applications, and more.Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables AI clients to interact with OfficeRnD coworking space management platform via natural language, exposing 130+ tools for CRUD operations and business logic.MIT