MCP Server Documentation

Overview

The Model Context Protocol (MCP) server provides standardized access to your data for AI applications. It allows AI assistants like LeChat, ChatGPT, Claude, and others to query your data directly using natural language.

Protocol: JSON-RPC 2.0 | MCP Protocol 2025-06-18 | HTTP Transport | Real-time Queries

Quick Setup

Server Endpoint

Server URL: {HOSTNAME}/api/mcp/{companyId}/mcp

Bearer Token: Your API Key

[navigate:/apiKeys|Get API Key|key]

Server Info: {HOSTNAME}/api/mcp/{companyId}/info

AI Platform Setup

Connect your favorite AI assistant to your MCP server

LeChat Setup [badge:Recommended|success|right]

1. Open LeChat

Go to lechat.mistral.ai and start a new conversation

2. Create API Key

Generate an API key for MCP server access

[navigate:/apiKeys|Manage API Keys|key]

3. Access MCP Settings

In the chat interface, look for the MCP or External Tools settings

4. Add MCP Server

Add your MCP server with the following configuration:

Server Name: {productName}
Server URL: {HOSTNAME}/api/mcp/{companyId}/mcp
Authorization Header: Bearer YOUR_API_KEY

5. Test Connection

LeChat will test the connection and show available tools. Try asking: “What data do you have access to?” or “Show me my products”

**LeChat Advantage:**
LeChat by Mistral AI has excellent MCP support and can effectively use your data tools for analysis, reporting, and data exploration tasks.

ChatGPT Desktop Setup

1. Install ChatGPT Desktop

Download and install ChatGPT Desktop application from OpenAI

2. Create API Key

Generate an API key for MCP server access

[navigate:/apiKeys|Manage API Keys|key]

3. Configure ChatGPT

Add the following configuration to ChatGPT Desktop settings

Configuration File:

{
  "mcpServers": {
    "{productName}": {
      "command": "npx",
      "args": [
        "@modelcontextprotocol/server-fetch",
        "{HOSTNAME}/api/mcp/{companyId}/mcp"
      ],
      "env": {
        "MCP_SERVER_URL": "{HOSTNAME}/api/mcp/{companyId}/mcp",
        "AUTHORIZATION": "Bearer YOUR_API_KEY"
      }
    }
  }
}

4. Start Using

ChatGPT can now access your data directly! Try asking: “Show me my products” or “What categories do I have?”

ChatGPT Web Setup [badge:Limited|warning|right]

The web version of ChatGPT has limited MCP support through remote server connections for research purposes. It does not support the full range of MCP features available in the desktop app.

Setup Steps:

1. Create API Key

Generate an API key for MCP server access

2. Go to ChatGPT Settings

In chat.openai.com, click your profile → Settings → Connections

3. Add MCP Server

Add your MCP server URL with authorization header:

URL: {HOSTNAME}/api/mcp/{companyId}/mcp
Authorization: Bearer YOUR_API_KEY

4. Test Connection

ChatGPT will test the connection and show available tools for research

**Note:**
Web version only supports remote MCP servers for research tasks. For full MCP functionality including tools, resources, and prompts, we recommend using the ChatGPT Desktop application.

**Security Note**
Keep your API keys secure and don't share them publicly. Treat them like passwords.

Available Tools

AI tools exposed by the MCP server

query_data [badge:Tool|info|right]

Execute queries using the query language

Example: products(limit: 10, where: "price > 100") { id, name, price }

list_entities [badge:Tool|info|right]

List all available entities/tables

Example: No parameters required

list_{entity} [badge:Tool|info|right]

List records from specific entities

Example: limit: 10, where: "active = true", fields: "id, name"

API Examples

Direct API calls for testing and integration

Initialize Connection

curl -X POST "{HOSTNAME}/api/mcp/{companyId}/mcp" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "jsonrpc": "2.0",
    "id": 1,
    "method": "initialize",
    "params": {
      "protocolVersion": "2025-06-18",
      "capabilities": {
        "roots": { "listChanged": true },
        "sampling": {}
      },
      "clientInfo": {
        "name": "TestClient",
        "version": "1.0.0"
      }
    }
  }'

Query Data

curl -X POST "{HOSTNAME}/api/mcp/{companyId}/mcp" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "jsonrpc": "2.0",
    "id": 2,
    "method": "tools/call",
    "params": {
      "name": "query_data",
      "arguments": {
        "query": "products(limit: 10) { id, name, price }"
      }
    }
  }'

Testing & Debugging

[navigate:/devdoc/test-query|Test Queries|play]

Use these tools to test your MCP server setup and validate query syntax before using with AI applications.

Learn More