An enterprise admin console connects approved plugins, MCP servers, telemetry, and IDE agent permissions into one controlled developer workspace
An enterprise admin console connects approved plugins, MCP servers, telemetry, and IDE agent permissions into one controlled developer workspace
+ Microsoft News

GitHub brings managed Copilot settings to JetBrains

GitHub Copilot for JetBrains now supports enterprise-managed controls for plugins, MCP servers, telemetry routing, and agent permission modes.

GitHub is extending enterprise-managed Copilot settings into JetBrains IDEs.

The August 18 release adds centralized controls for plugin governance, MCP server access, OpenTelemetry, and permission modes in GitHub Copilot for JetBrains. Administrators can apply consistent settings across everyone on an enterprise Copilot plan.

The plugin controls let administrators require specific plugins to be enabled or disabled, add approved marketplaces, and restrict installation to known marketplaces. The MCP controls let administrators allow or deny which MCP servers developers can connect to from Copilot for JetBrains.

GitHub also added managed OpenTelemetry settings for collector endpoint, protocol, service name, resource attributes, and content-capture policy. Managed values take precedence over developer settings. A permission-mode setting can prevent the Copilot agent in JetBrains from using Bypass Approvals or Autopilot.

MCP governance is moving into IDE policy

MCP servers and agent plugins are powerful because they connect a coding assistant to tools, data, and workflows. That is also why they need policy.

Without a central allowlist, every developer machine can become a separate integration decision. One person can connect an agent to a local server, internal system, external SaaS tool, or marketplace plugin before security and platform teams understand the boundary.

GitHub’s JetBrains update makes that boundary part of the managed IDE configuration. That is the right layer for many enterprises because agent risk often starts in the developer environment, not only in a deployed production app.

Telemetry and permissions are part of the same control surface

The OpenTelemetry and permission-mode settings are not cosmetic additions.

Telemetry routing decides where agent activity can be observed. Permission modes decide whether the agent can bypass approvals or run in a more autonomous mode. Plugin and MCP settings decide what tools the agent can reach.

Those controls need to be reviewed together. An enterprise can approve a plugin but still restrict the MCP server it talks to. It can allow telemetry but limit content capture. It can permit agent workflows while disabling bypass behavior for repositories with higher risk.

Sources

The AI Feed Desk

The AI Feed Desk

Editorial desk

The AI Feed Desk tracks AI provider updates, model releases, agent tooling, and enterprise adoption, turning fast-moving announcements into source-linked context for builders and operators.

Noticed a typo, incorrect information, or translation error?

Tell us so we can fix it.

Help Improve This Article

Related Articles

A developer workbench shows completed agent requests with model labels, credit meters, cache indicators, and session branches

GitHub Copilot Auto now shows model and AI-credit details

GitHub Copilot's weekly release adds model, AI-credit, and cache visibility for Auto requests plus new CLI session controls.

The AI Feed Desk

By The AI Feed Desk

Four developer-tool modules connecting into a central customization tray

GitHub Copilot app Customize tab becomes generally available

GitHub made the Copilot app Customize tab generally available, bringing MCP servers, plugins, skills, and canvases into one extension surface.

The AI Feed Desk

By The AI Feed Desk

An abstract coding agent session timeline flows into a secure audit collector

GitHub exposes Copilot agent sessions for enterprise audit

GitHub's public preview lets enterprise owners stream or retrieve Copilot agent session data, including prompts, responses, and tool calls, across major Copilot clients.

The AI Feed Desk

By The AI Feed Desk

A routing switchboard sends coding tasks into different model lanes from an admin control plate

Copilot auto model selection turns routing into an admin setting

GitHub Enterprise admins can now default Copilot conversations to auto model selection through managed-settings.json, tying model routing to enterprise AI standards.

The AI Feed Desk

By The AI Feed Desk

Shared AI credit tokens flow through team lanes while one cost center lane is stopped by a cap gauge

GitHub cost centers can cap shared AI credit pools

GitHub added AI credit pools for cost centers, letting enterprise admins cap how much monthly included Copilot credit one group can draw before metered budgets apply.

The AI Feed Desk

By The AI Feed Desk