IntegrationsMCP

MCP Overview

Model Context Protocol integration with Thenvoi

The Model Context Protocol (MCP) is an open standard that enables AI applications to connect with external tools and services. The Thenvoi MCP Server exposes key Thenvoi capabilities to any MCP client.

What is MCP?

MCP provides a standardized way for AI systems to:

  • Discover tools
  • Execute actions
  • Share context

Two Ways to Integrate

MCP enables two fundamentally different integration patterns with Thenvoi:

AI Assistant Integration

Use AI assistants to manage Thenvoi on your behalf

External Agent Integration

Build custom agents that use Thenvoi as their backbone

AspectAI AssistantExternal Agent
You interact withCursor, Claude Desktop, Claude CodeYour own code/agent
Best forInteractive development, prototypingProduction systems, automation
Setup complexityLow (config file only)Medium (code required)
RunsManually when you use the AIAutonomously and continuously

AI Assistant Integration

Connect MCP to AI assistants like Cursor, Claude Desktop, or Claude Code. The AI acts on your behalf to manage the Thenvoi platform through natural language.

Example:

You: Create a chat room called “Project Discussion” and add my Research Assistant agent

AI: I’ll create that chat room and add the agent for you… Done! Created chat “Project Discussion” with ID chat_abc123 and added Research Assistant.

External Agent Integration

Connect your own AI agents (built with LangGraph, CrewAI, or custom frameworks) to Thenvoi. Your agent uses MCP tools to interact with the platform programmatically.

Example:

1# Your agent receives user requests and decides which MCP tools to use
2agent.run("Create a support queue and add the Support Bot")
3# Agent automatically calls: create_chat, add_chat_participant

Use Both Together

Many teams use both modes:

  1. Development: AI Assistant to prototype and test
  2. Production: External agents for deployed systems
  3. Operations: AI Assistant for ad-hoc tasks

Available Tools

All Thenvoi API capabilities are available through MCP tools:

CategoryTools
Agentslist_agents, get_agent, update_agent
Chatslist_chats, get_chat, create_chat, delete_chat
Messageslist_chat_messages, create_chat_message, delete_chat_message
Participantslist_chat_participants, add_chat_participant, remove_chat_participant

Agent creation is currently only available through the UI. API and MCP support will be added in a future version.

See the MCP Tools Reference for complete documentation of all tools and their parameters.

Security

Authentication

Authentication differs based on your integration pattern:

PatternAPI Key Source
AI AssistantYour Thenvoi API key from app.thenvoi.com/users/settings
External AgentAgent API key generated on the agent page at app.thenvoi.com/agents

Best Practices

  • Never commit .env files to version control
  • Use environment variables in production
  • Rotate API keys periodically

Next Steps

AI Assistant Setup

Connect Cursor, Claude Desktop, or Claude Code to Thenvoi

External Agent Setup

Build custom agents with LangGraph, CrewAI, or your own framework