Merge pull request #12 from ayim/patch-2

Updated with review from kkeirstead

Author: anandmeg

docs/ide/copilot-agent.md

@@ -31,19 +31,19 @@ In agent mode, Copilot operates autonomously and determines the relevant context
 
 Follow these steps to get started:
 
-1. Make sure that agent mode is enabled by clicking Tools > Options > GitHub > Copilot and  the "Enable Agent mode in the chat pane".
+1. Make sure that agent mode is enabled by clicking Tools > Options > GitHub > Copilot and the "Enable agent mode in the chat pane".
 
 ![Copilot Agent Settings](./media/vs-2022/copilot-agent/copilotagent-settingupdated.png)
 
-2. Enable agent mode by opening the GitHub Copilot window, clicking the mode dropdown that says "Ask", then select "Agent".
+2. Open the GitHub Copilot window, click the mode dropdown that says "Ask", then select "Agent".
 
 ![Copilot Agent Mode Selector](./media/vs-2022/copilot-agent/copilotagent-dropdown.png)
 
 3. Enter your prompt for making edits in the chat input field and select Send (Enter) to submit it. You can specify a high-level requirement, and you don't have to specify which files to work on. In agent mode, Copilot determines the relevant context and files to edit autonomously.
 
 
 
-4. Agent mode might invoke multiple tools to accomplish different tasks. Optionally, select the Tools icon to configure which tools can be used for responding to your request.
+4. Agent mode might invoke multiple tools to accomplish different tasks. Optionally, select the Tools icon to configure which additional tools can be used for responding to your request.
 
 ![Copilot Agent Tool Selector](./media/vs-2022/copilot-agent/copilotagent-tools.png)
 
@@ -53,7 +53,7 @@ Follow these steps to get started:
 
 6. Copilot detects issues and problems in code edits and terminal commands and will iterate and perform additional actions to resolve them. For example, agent mode might run unit tests as a result of a code edit. If the tests fail, it uses the test outcome to resolve the issue. Copilot agent mode iterates multiple times to resolve issues and problems.
 
-7. As Copilot processes your request, notice that Copilot streams the suggested code edits directly in the editor. Review the suggested edits and accept or discard the suggested edits as a whole in the Total Changes section, or individually by clicking on a file and reviewing the code diffs presented in the editor.
+7. As Copilot processes your request, notice that Copilot streams the suggested code edits directly in the editor. Review the suggested edits and either keep or discard the suggested edits as a whole in the Total Changes section, or individually by clicking on a file and reviewing the code diffs presented in the editor.
 
 ![Copilot Agent List of Changes](./media/vs-2022/copilot-agent/copilotagent-keepundo.png)
 
@@ -67,7 +67,7 @@ Follow these steps to get started:
 
 ## Agent mode tools
 
-![Copilot Agent Tool Selector](./media/vs-2022/copilot-agent/copilotagent-partialtools.png)
+![Copilot Agent Tool Selector](./media/vs-2022/copilotagent-mcp/copilotagent-partialtools.png)
 
 Agent mode can use the following tools:
 
@@ -141,14 +141,14 @@ Take the following troubleshooting steps in the order specified:
 
 ### What happened to Copilot Edits in Visual Studio?
 
-- We perceive Agent mode to an evolution of Edits, with greater ability to iterate on errors, use tools, and automatically apply code changes.
+- We perceive Agent mode to be an evolution of Edits, with greater ability to iterate on errors, use tools, and automatically apply code changes.
 - For the initial releases of Visual Studio 2022 version 17.14, Edits mode is still available if you uncheck the `Enable agent mode` setting in `Tools > Options`.
 
 ### As an administrator, how do I control use of Agent mode for Visual Studio users?
 
 Agent mode in Visual Studio is governed by the "Editor preview features" flag in the GitHub Copilot dashboard for administrator.
 
-More information can be found in the GitHub documentation for [managing policies and feature for copilot in your enterprise](https://docs.github.com/en/enterprise-cloud@latest/copilot/managing-copilot/managing-copilot-for-your-enterprise/managing-policies-and-features-for-copilot-in-your-enterprise#editor-preview-features).
+More information can be found in the GitHub documentation for [managing policies and features for copilot in your enterprise](https://docs.github.com/en/enterprise-cloud@latest/copilot/managing-copilot/managing-copilot-for-your-enterprise/managing-policies-and-features-for-copilot-in-your-enterprise#editor-preview-features).
 
 ## Related content
 

docs/ide/mcp.md

@@ -23,11 +23,11 @@ Model Context Protocol (MCP) is an open standard that enables AI models to inter
 
 ## How do MCP and Visual Studio extend GitHub Copilot's agent?
 
-* MCP clients (like Visual Studio) connect to MCP servers and request actions on behalf of the AI model
+* MCP clients, such as Visual Studio connect to MCP servers and request actions on behalf of the AI model
 * MCP servers provide one or more tools that expose specific functionalities through a well-defined interface.
 * The Model Context Protocol (MCP) defines the message format for communication between clients and servers, including tool discovery, invocation, and response handling
 
-For example, a file system MCP server might provide tools for reading, writing, or searching files and directories. GitHub's MCP server offers tools to list repositories, create pull requests, or manage issues. MCP servers can run locally on your machine or be hosted remotely, and Visual Studio supports both configurations.
+For example, a file system MCP server might provide tools for reading, writing, or searching files and directories. [GitHub's official MCP server](https://github.com/github/github-mcp-server) offers tools to list repositories, create pull requests, or manage issues. MCP servers can run locally on your machine or be hosted remotely, and Visual Studio supports both configurations.
 
 By standardizing this interaction, MCP eliminates the need for custom integrations between each AI model and each tool. This allows you to extend your AI assistant's capabilities by simply adding new MCP servers to your workspace. Learn more about the Model Context Protocol specification.
 
@@ -52,7 +52,7 @@ By standardizing this interaction, MCP eliminates the need for custom integratio
       "command": "npx",
       "args": [ "-y", "@modelcontextprotocol/server-github" ],
       "env": {
-        "GITHUB_PERSONAL_ACCESS_TOKEN": "GITHUB_PAT"
+        "GITHUB_PERSONAL_ACCESS_TOKEN": "${input:github_token}"
       }
     }
   }
@@ -86,28 +86,30 @@ MCP's [official server repository](https://github.com/modelcontextprotocol/serve
 
 MCP is still a relatively new standard, and the ecosystem is rapidly evolving. As more developers adopt MCP, you can expect to see an increasing number of servers and tools available for integration with your projects.
 
-## Adding  an MCP server
+## Adding an MCP server
 
 ### Create a file to manage configuration of MCP servers
 
 If you do not already have an `mcp.json` file, you can create it in various locations depending on the repos, users, and IDEs you would like the servers to be available/used for.
 
 ### File locations for automatic discovery of MCP configuration
 
-Visual Studio looks for MCP server configurations in the following directories, in the following order order:
+Visual Studio looks for MCP server configurations in the following directories, in the following order:
 
 1.  `%USERPROFILE%\.mcp.json` serves as a global MCP server configuration for a specific user. Adding an MCP server here would make it load for all Visual Studio solutions. 
-1.  `<SOLUTIONDIR>\.vs\mcp.json` is specific to Visual Studio and only loads the specified MCP servers for a specific user, for the specified solution.
+2.  `<SOLUTIONDIR>\.vs\mcp.json` is specific to Visual Studio and only loads the specified MCP servers for a specific user, for the specified solution.
 
-If you are looking for an MCP configuration that you can track in source control for a repo, this option woudl work well:
+If you are looking for an MCP configuration that you can track in source control for a repo, this option would work well:
 
 3.  `<SOLUTIONDIR>\.mcp.json` 
 
-Visual Studio will also check for MCP configurations other development environments have have set up. These are scoped to the repository/solution and are typically not source controlled.
+Visual Studio will also check for MCP configurations set up by other development environments. These are scoped to the repository/solution and are typically not source controlled.
 
 4.  `<SOLUTIONDIR>\.vscode\mcp.json`
 5.  `<SOLUTIONDIR>\.cursor\mcp.json`
 
+For #1 and #3, the `.` before `mcp.json` is not a typo, `.mcp.json` is the correct filename for these two directories.
+
 ### MCP configuration format
 
 You may define both **remote** (URL + credentials) and **local** (command-line invocation).