Imagine you could just ask for the recording you made last Tuesday, or get a summary of the demo your colleague shared, or pull out the transcript of a meeting — all without opening NeetoRecord, scrolling through folders, or copying and pasting links.
NeetoRecord works with AI assistants you may already be using, like Claude, Cursor, and GitHub Copilot. Once you connect them together, your AI assistant can fetch your recordings, read their transcripts, and organize things for you. You simply ask in plain English and the assistant does the work.
What is MCP?
MCP stands for Model Context Protocol. It is an open standard that lets AI assistants and apps like NeetoRecord speak the same language. You do not need to understand how it works to use any of the steps below — think of it as the plumbing that connects your AI assistant to your NeetoRecord workspace.
Why this is useful
Think of it as giving your AI a passcode to your NeetoRecord library. After that, the usual back-and-forth disappears. A few examples of what becomes possible:
- You ask, "What did I record about the onboarding flow last week?" and the assistant finds it for you.
- You paste a recording link and ask, "What were the three main points in this video?" and you get a summary on the spot.
- You say, "Put my last three demo videos in a folder called Product Demos," and it is done.
- You ask, "How many views did my recordings get this month?" and the assistant pulls up the numbers.
You do not need to be technical to benefit from this. If you already talk to an AI assistant for other things, you can talk to it about your NeetoRecord recordings too.
What you need to get started
Two things:
1. An AI assistant that supports this kind of connection (we cover the popular ones below).
2. A NeetoRecord API key, which authenticates the assistant with your workspace. See the API Keys help article for how to generate one.
That is it. Once you have both, you paste a small snippet of settings into your AI tool and you are done.
Connecting your AI assistant to NeetoRecord
Pick the tool you use. You only need to follow the steps for that one; you can skip the rest. Each section shows a small block of settings — copy it, replace YOUR_API_KEY with your own key, and save.
Claude Code
Open the file ~/.claude.json and paste the following (if the file already has settings, add just the neetorecord entry inside mcpServers):
{
"mcpServers": {
"neetorecord": {
"type": "http",
"url": "https://connect.neetorecord.com/mcp/messages",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}Save the file and restart Claude Code.
Cursor
Open ~/.cursor/mcp.json and paste the following:
{
"mcpServers": {
"neetorecord": {
"url": "https://connect.neetorecord.com/mcp/messages",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}Save it and restart Cursor (or reload the window via the command palette).
VS Code with GitHub Copilot
Create or open .vscode/mcp.json in your workspace and paste:
{
"servers": {
"neetorecord": {
"type": "http",
"url": "https://connect.neetorecord.com/mcp/messages",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}VS Code will ask you for your API key the first time. You need VS Code 1.99 or newer, and you must be in the Copilot chat's Agent mode to use it.
Windsurf
Open ~/.codeium/windsurf/mcp_config.json and paste:
{
"mcpServers": {
"neetorecord": {
"serverUrl": "https://connect.neetorecord.com/mcp/messages",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}Save it and make sure the connection is turned on in Settings > Cascade > MCP Servers. Windsurf has a limit of 100 total tools across all connected services, so if it complains, turn a few other connections off.
Try it out
Once you are connected, the easiest way to see what is possible is to just ask. Here are some prompts you can copy and paste to get a feel for it:
- "List all my recordings from this week."
- "Find recordings where I talked about the onboarding flow."
- "Get the transcript for this recording: <paste link>."
- "Summarize the key points from this video."
- "Create a folder called Product Demos and move my last three demos into it."
- "Get the embed code for my latest recording."
- "How many views did my recordings get this month?"
- "Generate a transcript and chapters for this recording."
- "Write a GitHub issue description based on this recording: [paste URL]."
What your AI assistant can actually do
Under the hood, the connection gives your AI assistant a set of abilities. You do not need to remember any of these names — just ask naturally and the assistant picks the right one. But here is the full list if you are curious.
Finding and managing recordings: list all recordings, search by title, search across transcripts for a topic, get details of a specific recording, update a recording's title or tags, and delete a recording.
Transcripts and chapters: fetch the full transcript with timestamps, fetch auto-generated chapters, and trigger transcript or chapter generation if they are not ready yet.
Sharing and embedding: get a share link, get an embed code to put the video on a website, or get a direct download link for the MP4.
Organizing: list folders, create new folders, move recordings between folders, and list tags.
Analytics: get view numbers for a single recording or across your whole workspace.
Calls to action: list or create call-to-action buttons that appear on your recordings.
There is also a smaller public set of abilities that works with any publicly shared NeetoRecord link, even if it is not from your own workspace. These are limited to reading details and transcripts (so no one can change or delete anything that is not theirs).