Skip to main content
AI NewsAI NewsAuto PublishingGitHub CopilotSEOMCP allowlistGitHub-verified MCPSlackFigmaNotion

GitHub Copilot Connectors Preview: Control Permissions After One-Time Slack, Figma, or Notion Setup

Twenty-six services can work across app, CLI, VS Code, cloud, and mobile, with extra enterprise policy requirements

ENHE AI5 min0 views
GitHub Copilot Connectors Preview: Control Permissions After One-Time Slack, Figma, or Notion Setup

Key takeaways

GitHub announced GitHub-verified MCP servers, called connectors, in public preview on October 28, 2026. A user can connect a service once and reuse it across the Copilot app, Copilot CLI, VS Code, Copilot in the cloud, and GitHub Mobile. The launch includes 26 services such as Slack, Figma, Notion, Sentry, Linear, and Cloudflare. Business and Enterprise organizations may need the Editor preview features policy enabled, an MCP allowlist entry, and service-side administrator approval. This article provides a least-privilege setup, a read-only verification prompt, cross-client checks, revocation steps, and troubleshooting before a connector reaches recurring automations. Revocation must work across clients.

Connectors are in public preview and can be reused across multiple Copilot clients after one connection.
The launch includes 26 services, but availability still depends on plan, organization policy, and service-side administration.
The first verification should be read-only and should test that revocation works across clients.

By ENHE AI · 2026-11-02 · AI-assisted drafting and editorial checks.

Direct answer: One connection reduces setup but does not remove service permissions

GitHub announced GitHub-verified MCP server connectors in public preview on October 28, 2026. Connectors remove the need to find and install a local MCP server, but authorization is still governed by GitHub, organization policy, and the target service.

Supported clients and services

After one connection, the same service can work across the Copilot app, CLI, VS Code, cloud, and GitHub Mobile. The launch includes 26 services. They include Slack, Figma, Notion, Sentry, Linear, Cloudflare, and Vercel. Available tools still depend on the service authorization.

Colleagues review information around a laptop, representing cross-client verification. Contextual stock photo, not a product test screenshot. Image: Unsplash.
Colleagues review information around a laptop, representing cross-client verification. Contextual stock photo, not a product test screenshot. Image: Unsplash.

A least-privilege trial

Choose one service from Customize in the Copilot app, /mcp in the CLI, Customizations in VS Code, or the GitHub customization page. If the service offers a read-only scope, grant only that scope; otherwise choose the lowest available permission and save the authorization page. Example prompt: “Read only the title and last-updated time of the test Notion page named Connector Trial. Do not create, edit, or comment. If access fails, identify the missing permission layer.” Repeat it in two clients. The expected result is the same title and time without broader access.

Enterprise requirements, revocation, and failure handling

Business or Enterprise may require the Editor preview features policy. Enterprises using an MCP allowlist must also add GitHub-verified MCP servers. Services such as Slack may require service-side administrator approval. If a connector is missing, check those three layers instead of repeatedly authorizing. Revoke after testing; this article recommends checking that the test page is no longer readable in either client. That is an acceptance check, not an official guarantee of instant revocation consistency.

Frequently asked questions

Is the preview available on every Copilot plan?

GitHub says it is rolling out to all Copilot plans, but enterprise policy, an allowlist, or service-side settings can still block access.

Does a connector give Copilot all service data?

No. Accessible data depends on the granted scope and available service tools. Start with least privilege and verify revocation.

Why this matters

Connectors turn external context from per-client setup into a reusable cross-client capability. That reduces configuration while widening permission propagation. The useful standard is not simply connected, but traceable source, least privilege, reproducible queries, and effective revocation.

Related tools and reading

These pages support the same task, workflow, or risk boundary.

Conclusion

Start with one non-sensitive service. Use read-only access when available; otherwise choose the lowest available permission. Record the granted scope, run the same query in two clients, revoke the connection, and confirm access stops. Allow recurring automation to use the connector only after permission, audit, and revocation behavior are clear.

What this means for everyday users

Business or Enterprise may require the Editor preview features policy. Enterprises using an MCP allowlist must also add GitHub-verified MCP servers. Services such as Slack may require service-side administrator approval. If a connector is missing, check those three layers instead of repeatedly authorizing. Revoke after testing; this article recommends checking that the test page is no longer readable in either client. That is an acceptance check, not an official guarantee of instant revocation consistency.

Related tutorials

Related reading

GitHub Copilot Usage API Names Custom Skills, Agents, and MCP Servers: How to Read the Report

GitHub updated the Copilot usage metrics API on October 22, 2026, so customer-defined skills, agents, MCP servers, slash commands, and plugins can appear by configured name instead of being grouped entirely under other or custom. Each totals_by_* list now includes as many as 25 entries per record, up from five. This article helps administrators turn the change into a reliable adoption report. It covers required Copilot CLI and SDK versions, a naming review before reports are shared, one-day and 28-day comparisons, and a reconciliation check against known pilots. It also explains why historical days, path-like names, outdated clients, and blocked telemetry can still undercount activity. The metrics are useful for trends and enablement, not exact billing.

GitHub Copilot Cloud Sessions Are GA: How Cross-Device Work Uses Actions Entitlement

GitHub made its connected Copilot cloud experience and cloud sandboxes generally available on paid Copilot plans on October 28, 2026. A user can start a task on github.com, GitHub Mobile, Copilot CLI, the Copilot app, VS Code, Slack, or Microsoft Teams, then continue the same session elsewhere. The included Actions compute entitlement becomes one shared, dollar-based pool for standard hosted runners, cloud sandboxes, and certain larger runners. Billing for cloud-sandbox usage begins in November 2026, so cross-device convenience can affect the same budget used by builds. This article helps users check repository scope, write access, tool permissions, entitlement consumption, and stop conditions before their first cloud session.

GitHub Copilot Repository Plugin Defaults Are GA: Prevent Permission Drift Across Teams

GitHub made repository plugin defaults and enterprise-managed plugin controls generally available in VS Code, Copilot CLI, and the GitHub Copilot app on October 28, 2026. A maintainer can define a marketplace and default plugins for a trusted repository so contributors avoid repeating setup. Enterprise administrators can require or block plugins and restrict installation to approved marketplaces. Managed settings take precedence over repository and personal choices, and a required plugin cannot be disabled by the user. This article gives teams a rollout checklist for validating publisher identity, plugin contents, MCP connections, credentials, uninstall behavior, repository trust, and the difference between a convenient default and a mandatory enterprise control.

What Is Replica? A Validation Guide for AI Prototypes Built From Your Design System

Replica is an open-source AI prototyping tool released by GitHub Design on October 28, 2026. It uses a team’s existing components, patterns, and documentation to guide interactive prototypes instead of starting from a generic visual language. Team members can describe and refine a prototype through the GitHub Copilot app, begin locally, and optionally deploy a self-hosted Replica Hub for review and comments. The project is available under the MIT license. This durable guide explains the required design-system inputs, a small example task, expected outputs, consistency checks, feedback handling, and failure recovery so a prototype can inform product discussion without being presented as production code or a tested interface.

GitHub Copilot Memory Is GA: Check and Delete Context Before Enabling Dreaming

GitHub announced GitHub intelligence on October 28, 2026. Copilot Memory is generally available on paid plans, Dreaming is an opt-in public preview, and code search can reach related repositories and dependencies. Dreaming may add, update, or remove personal and repository memories, while proposed changes to checked-in skills and instructions arrive as pull requests for team review. Dream runs consume AI credits. This article gives developers a practical way to inspect and delete saved preferences, separate personal from repository context, limit repository access, and decide whether Dreaming and cross-repository search belong in a low-risk trial before broader adoption. The trial remains reversible.

GitHub Issue Artifacts Preview: What Agent Outputs Can Store and How Version History Works

GitHub announced Issue Artifacts in public preview on October 28, 2026. Teams can attach agent-generated plans, research, links, visualizations, and interactive HTML directly to an issue. Updates made on github.com retain version history as an artifact changes. GitHub CLI adds gh issue artifact commands to create, edit, list, view, download, and delete artifacts, while Markdown artifacts can include image and video attachments. This explainer uses a root-cause-analysis example to show which outputs belong beside an issue, how to separate observed evidence from unverified conclusions, when history helps reviewers follow a decision, and when an incorrect or sensitive artifact should be corrected or removed rather than being treated as repository truth.

Sources

Table of contents

Latest Insights