JetBrains MCP Server

JetBrains's JetBrains MCP server provides AI agents with deep IDE integration across JetBrains IDEs to inspect Abstract Syntax Trees (AST), trigger refactoring, and navigate project structures. It enables coding agents to analyze project dependencies, execute unit tests, and perform contextual code modifications inside the active editor.

Start for free

Benefits with Ory + JetBrains MCP Server

The MCP server built into JetBrains IDEs, such as IntelliJ IDEA and PyCharm, lets your agents work inside an open project: reading files, searching code, checking problems, and making changes through the IDE. That gives an external agent much of the same reach into your project as the user at the keyboard. Ory Agent Security lets analysis agents read and search while edits and commands stay with the coding agents you approve.

View documentation

Use Cases

— 01 use case

Agent IAM

Reviewers read code at Read, coding agents refactor at Write, the agent that builds and runs commands gets Admin, and Block keeps others out of the IDE.

Explore Agent IAM

Core Functionality

— 04 capabilities

Read, write, admin, or no access
Ory Agent Security classifies every tool on the JetBrains MCP server as read, write, or admin, so you can give each user, team, or agent type only the level it needs: read for analysis agents, write for coding agents that edit files, admin for agents you'd trust with a terminal, and no access for agents outside the coding workflow.
Enforced before execution
Ory Agent Security checks each tool call against the user, the agent acting for them, and any sub-agent inside the agent harness, so a denied terminal command stops before it reaches the IDE, with nothing to roll back and no gateway to deploy.
Observe, then enforce
Observe mode shows which agents edit files or run commands through the IDE without blocking anything, so you can apply Ory's pre-built policy for the JetBrains MCP server and enforce it on your own schedule.
Complete audit trail
Every allow and deny decision on the JetBrains MCP server streams to your SIEM through OpenTelemetry with the user, agent, and action attached, so you can show which agent ran a command on a user's machine.