---
title: "Connect VS Code to Speak AI"
description: "Set up the Speak AI MCP server in VS Code. One-click install via deeplink."
---

> Documentation Index
> Fetch the complete documentation index at: https://docs.speakai.co/llms.txt
> Use this file to discover all available pages before exploring further.

# Connect VS Code to Speak AI


VS Code reaches your Speak AI workspace through the MCP server, so it can read your recordings, transcripts and insights while you work.

## What you need

A Speak AI account, and VS Code. Some setup paths also need an API key, which you create at [app.speakai.co/developers/apikeys](https://app.speakai.co/developers/apikeys).

Every client connects to the same address:

```text
https://api.speakai.co/v1/mcp
```

## How do you connect VS Code?

> **Tip**
>
> [Install in VS Code](https://vscode.dev/redirect/mcp/install?name=speakai&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fapi.speakai.co%2Fv1%2Fmcp%22%7D) opens the right screen directly.

1. Click the button, VS Code registers and opens the permission popup

1. Sign in to Speak AI and click **Allow**

## What can you ask for once it is connected?

Ask in your own words. The server exposes 112 tools, so most questions about your workspace resolve without naming one:

- "Summarise my last customer interview."
- "Find every mention of pricing across this month's calls."
- "Upload this recording and tell me the main themes."

## Related guides

- [Connect your AI tool](/mcp) covers every supported client.
- [Connect Claude.ai (web) to Speak AI](/mcp/setup/claude-web/)
- [Speak AI MCP server](/mcp) explains what the server exposes.
- [MCP authentication and rate limits](/mcp/authentication)

Source: https://docs.speakai.co/mcp/setup/vscode/index.mdx