> For the complete documentation index, see [llms.txt](https://integrations.impact.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://integrations.impact.com/ai-solutions/mcp-quick-start/mcp-for-vs-code.md).

# MCP for VS Code

The impact.com Model Context Protocol (MCP) Server integrates directly with Visual Studio Code, giving you AI-powered access to your partnership data without leaving your editor. Choose between a one-click install or manual configuration.

Follow these steps to configure and connect the impact Model Context Protocol (MCP) to your VS Code environment:

## One-click install

1. Use the [**quick link**](vscode:mcp/install?%7B%22name%22%3A%22impact%20MCP%22%2C%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fmcp.impact.com%2Fmcp%22%2C%22oauth%22%3A%7B%22clientId%22%3A%22mcp-impact-vscode%22%2C%22scopes%22%3A%5B%22offline_access%22%2C%22mcp%3Aread%22%2C%22mcp%3Awrite%22%5D%7D%7D) to easily configure the impact MCP in VS Code.
2. After you select the link, you'll be redirected to VS Code.
3. Agree to install the impact.com MCP.
   * Recommended: installing it for your workspace.
4. From **VS Code Settings**, select **MCP Servers**.
5. Connect your impact.com account.
6. You will be redirected to the [impact.com](http://impact.com/) login page, where you need to authorize the impact MCP in VS Code to access your impact account.
7. Once authorized, it will redirect you back to VS Code.
   * Troubleshooting note: VS Code might prompt you to "try a different way." Select **yes**. It will redirect you back to [impact.com](http://impact.com/) but will not require you to log in again. You can expect to be redirected back to VS Code.
8. VS Code will then retrieve a list of tools.
9. You are now ready to use the MCP tools!

To learn more, see the [VS Code MCP documentation](https://code.visualstudio.com/docs/copilot/customization/mcp-servers).

## Manual configuration

Add this to `.vscode/mcp.json` in your workspace:

{% tabs %}
{% tab title="JSON" %}

```json
{
	"servers": {
		"impact MCP": {
			"type": "http",
			"url": "https://mcp.impact.com/mcp",
			"oauth": {
				"clientId": "mcp-impact-vscode",
				"scopes": [
					"offline_access",
					"mcp:read",
					"mcp:write"
				]
			}
		}
	},
	"inputs": []
}
```

{% endtab %}
{% endtabs %}

### Manage tool permissions

<details>

<summary>How do I manage tool permissions in VS Code?</summary>

Connecting mcp.impact.com authorizes VS Code to call supported tools within your existing impact.com permissions. Separately, VS Code may ask you to approve each tool call, or remember that approval. Those prompts are controlled by VS Code, not by impact.com.

#### Steps

1. When Copilot Chat or the agent needs an MCP tool, review the confirmation dialog (tool name and parameters) and approve or deny.
2. To manage saved approvals: open the Command Palette and run **Chat: Manage Tool Approval**.&#x20;
   1. Tools are grouped by MCP server. Adjust per tool, or trust all tools from a specific server.
3. To change session autonomy: use the permissions dropdown in the chat input (**Default Approvals**, **Bypass Approvals**, or **Autopilot**).&#x20;
   1. Prefer **Default Approvals** for day-to-day use.
4. To clear saved approvals: open the Command Palette and run **Chat: Reset Tool Confirmations**.

Denying a prompt blocks that call in VS Code. It doesn't change your impact.com account permissions or the account-level MCP enablement setting.

</details>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://integrations.impact.com/ai-solutions/mcp-quick-start/mcp-for-vs-code.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.