Skip to content

[bot] Document multi-model agent lists and MCP CIMD OAuth support #2959

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
github-actions wants to merge 1 commit into
base: main
Choose a base branch
from
+12 −2
Draft

[bot] Document multi-model agent lists and MCP CIMD OAuth support #2959

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 9 additions & 1 deletion website/src/content/docs/learning-hub/building-custom-agents.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@ title: 'Building Custom Agents'
description: 'Learn how to create specialized GitHub Copilot agents with custom personas, tool integrations, and domain expertise.'
authors:
- GitHub Copilot Learning Hub Team
lastUpdated: 2026-08-09
lastUpdated: 2026-09-06
estimatedReadingTime: '10 minutes'
tags:
- agents
Expand Down Expand Up @@ -73,6 +73,14 @@ tools: ['codebase', 'terminal', 'github']

**model** (recommended): The AI model that powers the agent. Choose based on the complexity of the task—use more capable models for nuanced reasoning.

> **New (v1.0.83+)**: `model` can list several models, tried in order until one is available to you (for example, if your account or enterprise policy doesn't have access to the first choice):
>
> ```yaml
> model: [Claude Sonnet 4.5, Claude Sonnet 4, GPT-5]
> ```
>
> Pair this with `model-policy: required` to prevent the model from being changed away from this list mid-session — useful when an agent's behavior depends on a specific model family.

**reasoningEffort** *(v1.0.66+)*: Override the reasoning effort level for this agent. Accepted values are `low`, `medium`, and `high`. This lets you pin specific agents to a cost/quality tradeoff regardless of the user's global setting — for example, a quick code-formatting agent can use `low` effort, while a security reviewer uses `high`:

```yaml
Expand Down
4 changes: 3 additions & 1 deletion website/src/content/docs/learning-hub/understanding-mcp-servers.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@ title: 'Understanding MCP Servers'
description: 'Learn how Model Context Protocol servers extend GitHub Copilot with access to external tools, databases, and APIs.'
authors:
- GitHub Copilot Learning Hub Team
lastUpdated: 2026-08-28
lastUpdated: 2026-09-06
estimatedReadingTime: '8 minutes'
tags:
- mcp
Expand Down Expand Up @@ -215,6 +215,8 @@ Some MCP servers require authentication to connect to protected resources. GitHu

> **Tip**: If your MCP server uses OAuth with Dynamic Client Registration but hosts its authorization metadata at a non-standard URL (as some enterprise servers like Atlassian Rovo do), Copilot CLI handles this automatically.

> **New (v1.0.83+)**: Copilot CLI supports **Client ID Metadata Document (CIMD)** for MCP OAuth sign-in. Instead of registering a client dynamically with each server, the CLI can present a metadata document URL as its client identifier, simplifying OAuth setup for MCP servers that support this emerging standard.

## How Agents Use MCP Tools

When an agent declares an MCP server in its `tools` array, Copilot can invoke that server's capabilities during conversation:
Expand Down