JetBrains IDEs
Connect JetBrains AI Assistant to One Horizon through MCP. AI Assistant can use assigned issues from tools like Jira or Linear while you code. When you finish work, it can summarize the result and add a completed task.
MCP support requires JetBrains IDE version 2025.1 or later with AI Assistant enabled. It is available in IntelliJ IDEA, PyCharm, WebStorm, PhpStorm, RubyMine, GoLand, and other JetBrains IDEs.
Configuration
Configure the MCP server in your JetBrains IDE to connect AI Assistant with your work context.
Step 1: Open MCP settings
- Open your JetBrains IDE (IntelliJ IDEA, PyCharm, WebStorm, etc.)
- Go to Settings (or Preferences on macOS)
- Navigate to Tools → AI Assistant → Model Context Protocol (MCP)
Step 2: Add One Horizon MCP server
- Choose the Add (+) button
- Select As JSON
- Paste the following configuration:
{ "mcpServers": { "onehorizon": { "command": "npx", "args": [ "mcp-remote@latest", "https://mcp.onehorizon.ai/mcp" ] } }}
Step 3: Set Scope
In the Level column, choose:
- Global - Available in all your projects (recommended)
- Project - Only available in the current project
Step 4: Apply and Connect
- Choose Apply to start the MCP server
- Check the Status column to verify the connection is active
- Choose OK to close the settings
Activate in AI Assistant
Open AI Assistant in your JetBrains IDE and enable Codebase mode (toggle at the top of the chat window). This allows AI Assistant to use MCP tools.
The first call may take a moment to load. JetBrains prompts you to authenticate. Follow the browser window to sign in and authorize the connection.
Try asking: "show my planned work for this week"
What you can ask AI Assistant
"show my assigned issues and todos for today"
AI Assistant pulls your in-flight issues from tools like Linear or Jira and summarizes them.
"use my assigned work details for the gateway API"
AI Assistant pulls those details into context so it writes code with the right scope and names.
"capture this as completed work"
AI Assistant summarizes what it wrote and adds a completed task.
You can also use the / command in chat to see available commands.
Security and permissions
The connector acts on your behalf. Data access follows your roles, workspace membership, and granted scopes.