NeetoRecord MCP and CLI: let AI tools work with your recordings

What is NeetoRecord MCP?

NeetoRecord MCP lets AI tools like Claude and ChatGPT work with your NeetoRecord library. Once it's connected, you can ask your AI assistant to find the recording where something was said, summarize a video you don't have time to watch, look at what's on screen at a given moment, and tidy up titles, tags, and folders, in the same conversation where you're already working.

MCP stands for Model Context Protocol, an open standard for connecting AI tools to the apps you use. You don't need to know anything about it. You connect once, sign in to NeetoRecord, and start asking.

Your AI tool talks to the NeetoRecord MCP server. NeetoRecord hosts it, so there's nothing to install or keep updated, and every workspace uses the same address:

https://connect.neetorecord.com/mcp/messages

When you connect, you sign in with your NeetoRecord account and pick your workspace. The assistant then works as you: it sees only the recordings you can see, and does only what your role allows. It can search recordings by title or by what was said, read transcripts, chapters, and summaries, look at a frame at any timestamp, organize recordings into folders and tags, share and embed them, add calls to action, and read view counts. You never name a tool; you ask in plain language. The full list is in the NeetoRecord MCP tools reference.

NeetoRecord also has a command-line tool, the NeetoRecord CLI. It works with the same library, but runs in your terminal, in scripts, and in scheduled jobs. It's open source, so you can read exactly what it does, change it, and build on it.

Real prompts for real work

These are real prompts for real work with recordings. Copy any of them and try it with Claude, ChatGPT, or another AI tool. For repeatable jobs in automation, we have included CLI examples too.

Ask NeetoRecord questions

NeetoRecord isn't only somewhere videos pile up. It's something you can ask questions about. Try these:

Find the call where we talked about SSO pricing.

What did I record last week?

Which of our recordings have the most views?

How many views has the onboarding walkthrough had, day by day?

Which recordings are tagged "customer"?

Which folders hold the most recordings?

Which of my recent recordings don't have a transcript yet?

What's in the Q3 roadmap recording? Summarize it without me watching it.

The assistant searches titles and transcripts, reads summaries and chapters, and works out the answer. For questions that span thousands of recordings, the CLI is the better fit. See MCP or CLI.

Understand recordings without watching them

Summarize a recording

Summarize the "Acme onboarding call" recording. Give me the key decisions, the chapters with timestamps, and a link I can share.

Pull out action items

Go through yesterday's sprint planning recording and list every action item, who took it, and the timestamp where it was agreed.

Hear what customers said across many calls

Find every recording where a customer talks about exporting data. What did each of them ask for, and how often does the same request come up?

Look at what's on screen

A customer sent a bug recording. Ask:

Look at the "Checkout fails" recording at 0:48. What error is on the screen, and what did the customer click just before it?

The assistant can grab the frame at that moment and read it, so you don't have to scrub through the video.

Turn a walkthrough into written steps

Turn the "Setting up the Slack integration" recording into a step-by-step written guide. Describe what's on screen at each step and note the timestamp.

Organize and share

Give recordings useful titles and tags

Look at my ten most recent recordings. Suggest a clear title and two or three tags for each, based on what's in them. Show me the list before you change anything.

File recordings into a folder

Create a folder called "Customer calls Q4" and move every recording from this month with "call" in the title into it.

Share and embed

Give me the share link and the embed code for the pricing walkthrough, so I can put it on our pricing page.

Add a call to action

Add a "Book a demo" button to the end of the product tour recording that links to https://acme.neetocal.com/demo.

Fill in missing transcripts

Check my recordings from the last two weeks. Generate transcripts for any that don't have one, then add chapters.

Ask a customer to record their screen

Create a recording request titled "Show us the checkout bug", with instructions to record from adding an item to the error. Give me the link to send to the customer.

The assistant creates the request and hands you the link. You send it however you like.

Clear out test recordings

Find recordings titled "test" or "Untitled" that are shorter than 30 seconds. List them with their dates, and delete them only after I confirm.

Deleting a recording is permanent and needs the Delete permission, so this prompt asks for confirmation first.

Automate with the CLI

Why have a CLI when MCP exists? Because some jobs shouldn't need an AI at all. These run on a schedule, with nothing but the neetorecord binary and the tools you already use, such as jq, curl, and your cloud CLI. No model account, no cost per run, and the same result every time.

Save your whole library to a file

The first job pages through every recording and saves it as one JSON line each. The next three jobs reuse that file.

page=1
while :; do
  out=$(neetorecord recordings list --page "$page" --page-size 100 --json) || exit 1
  echo "$out" | jq -c '.data[]'
  [ "$(echo "$out" | jq '.pagination.total_pages')" -le "$page" ] && break
  page=$((page + 1))
done > recordings.jsonl

Export your library to a spreadsheet

jq -r '[.title, .duration, .view_count, .folder_name, .created_at, .public_url] | @csv' recordings.jsonl > recordings.csv

Post the most-watched recordings every week

jq -s '{text: ([sort_by(-.view_count)[:10][] | "\(.view_count) views  \(.title)"] | join("\n"))}' recordings.jsonl \
  | curl -s -X POST -H "Content-Type: application/json" -d @- "$SLACK_WEBHOOK_URL"

Back up transcripts nightly

mkdir -p transcripts
jq -r '.id' recordings.jsonl | while read -r id; do
  neetorecord recordings transcript "$id" --json > "transcripts/$id.json"
done

aws s3 sync transcripts "s3://your-backup-bucket/neetorecord/transcripts/"

Request a recording from your support tool

When a ticket needs a screen recording, create the request from your helpdesk script. The output includes the link to send.

neetorecord recording-requests create \
  --title "Screen recording for ticket #1042" \
  --created-by-email support@example.com \
  --request-instructions "Record from opening the app until the error appears."

Retitle and file a recording

folder=$(neetorecord folders create --name "Customer calls" --quiet)
neetorecord recordings update 3f6a1c58-0b6e-4c71-9d0a-2f4e8b7c1d93 \
  --title "Acme onboarding call" --tag customer --tag onboarding --folder-id "$folder"

Add and remove teammates

neetorecord team-members create --email oliver@example.com --role Standard
neetorecord team-members delete "$(neetorecord team-members list --email sam@example.com --quiet | jq -r '.[0].id')"

Let a coding agent build it for you

You don't have to write these scripts yourself. Claude Code, Codex, or another coding agent can write the automation and use the open-source NeetoRecord CLI to work with your library. Run neetorecord setup claude (or setup codex, setup cursor) once, then ask:

Every Friday at 4 PM, use the NeetoRecord CLI to post this week's new recordings, with their view counts and links, to our Slack channel. Write the script, test it, and set up the cron job.

Using the NeetoRecord CLI, write a script that downloads the transcript of every recording in the Customer calls folder into a Markdown file per call.

You get the convenience of a chat, and the result is a script you can read, run, and commit.

MCP or CLI: which should you use?

Both work with the same recordings, folders, and tags. Pick based on how the work reaches NeetoRecord.

Use MCP when:

• You want to understand a recording. Summaries, action items, and "what's on screen at 0:48" need someone to read the transcript or look at the frame.
• You're searching by meaning. Finding the call where something was said works best when the assistant can read and compare.
• You're asking a question. "Which recordings don't have transcripts?" needs someone to look and explain.
• You don't use a terminal. NeetoRecord hosts the server. There's nothing to install.

Use the CLI when:

• No AI should be in the loop. A cron job or CI step runs the CLI with nothing but the binary. No model account, no cost per run.
• The output feeds another program. The CLI prints raw JSON for jq, a spreadsheet, a Slack webhook, or your own script.
• You're working through thousands of recordings. The CLI pages through everything unattended.
• You're managing team members. Adding and removing teammates is a CLI job.

You can also have both. With neetorecord setup claude, your AI assistant drives the CLI for you, so a plain-language request still ends in a command you can read and reuse.

Connect NeetoRecord to your AI tool

Claude

1. Open NeetoRecord in the Claude directory and click Connect to Claude.
2. Sign in to NeetoRecord and choose your workspace and permissions.

This works in Claude on the web, desktop, and mobile. On a Claude Team or Enterprise plan, an admin may need to turn on NeetoRecord under Organization settings, then Connectors.

ChatGPT

1. In ChatGPT, open Settings, then Security and login, and turn on Developer mode.
2. Go to chatgpt.com/plugins and click +.
3. Name it NeetoRecord, set the connection to Server URL, and paste https://connect.neetorecord.com/mcp/messages.
4. Leave authentication on OAuth, accept the notice, and click Create. Then sign in to NeetoRecord.

Claude Code

claude mcp add --transport http neetorecord https://connect.neetorecord.com/mcp/messages

Then start Claude Code, run /mcp, pick neetorecord, and sign in.

Cursor, Codex, VS Code, Windsurf, and Gemini CLI

Each of these connects to the same server address. The NeetoRecord MCP setup guide has the exact configuration for each one.

To check the connection, ask your assistant: "List my five most recent NeetoRecord recordings."

Install the NeetoRecord CLI

macOS with Homebrew:

brew install neetozone/tap/neetorecord

macOS or Linux:

curl -fsSL https://neetorecord.com/cli/install.sh | sh

Windows (PowerShell):

irm https://neetorecord.com/cli/install.ps1 | iex

Then sign in. This opens your browser, and there's no API key to manage:

neetorecord login --subdomain your-workspace

To teach your AI coding assistant how to use the CLI, run one of these from your project folder:

neetorecord setup claude      # Claude Code
neetorecord setup cursor      # Cursor
neetorecord setup codex       # Codex
neetorecord setup copilot     # GitHub Copilot
neetorecord setup gemini      # Gemini CLI
neetorecord setup windsurf    # Windsurf

Every command supports --json for scripts and --toon, a compact format that uses fewer tokens when an AI tool reads the output. See the NeetoRecord CLI reference for every command.

Permissions and safety

• Your assistant works as you. When you sign in with NeetoRecord, it sees only the recordings you can see and does only what your role allows.
• You choose the access. Read is always on. Create and update lets it retitle, tag, move, and add calls to action, and Delete lets it delete recordings. Leave both off for a read-only connection.
• Deleting is permanent. A deleted recording can't be recovered, along with its transcript, chapters, and analytics, so grant Delete only if you need it.
• Sharing settings stay yours. Your assistant can hand out existing share links and embed codes, but it can't change who can view a recording.
• You can disconnect anytime. Remove the NeetoRecord connector from your AI tool and its access ends.

A good habit is to ask your assistant to show you its plan before it renames, moves, or deletes anything, as several prompts above do.

Open source

The NeetoRecord CLI is open source on GitHub. You can read every command, see exactly what it sends to NeetoRecord, and adapt it to your own workflows. It's written in Go and runs on macOS, Linux, and Windows.

The CLI is built on neeto-cli-commons, the shared foundation behind every Neeto CLI, so what you learn in one works the same way in the others.

Found a bug or want a new command? Open an issue or a pull request.

Frequently asked questions

Do I need to know what MCP is?

No. Connect NeetoRecord to your AI tool once, sign in, and ask in plain language.

Can AI watch my NeetoRecord videos?

It reads them. Your assistant works from the transcript, chapters, and summary, and it can look at the frame at any timestamp you name. That's enough to summarize a recording, find a moment, or describe what's on screen.

Can ChatGPT search my NeetoRecord recordings?

Yes. Connect ChatGPT to the NeetoRecord MCP server and it can search recordings by title or by what was said, summarize them, and organize them, within your permissions. Today you add NeetoRecord to ChatGPT as a custom connector in Developer mode. See Connect NeetoRecord to your AI tool.

Can Claude summarize my NeetoRecord videos?

Yes. Connect NeetoRecord from the Claude directory and you can ask Claude to find a recording, summarize it with chapters and timestamps, and pull out action items in plain language.

Can I use NeetoRecord with Claude Code?

Yes, in two ways. Add the NeetoRecord MCP server with claude mcp add, or run neetorecord setup claude so Claude Code can drive the NeetoRecord CLI. You can use both.

Can I use NeetoRecord MCP with Cursor or Codex?

Yes. Cursor, Codex, VS Code with GitHub Copilot, Windsurf, and Gemini CLI all connect to the same NeetoRecord MCP server. The setup guide has the configuration for each.

Does NeetoRecord MCP require an API key?

No. You sign in with your NeetoRecord account and approve access, so there's no key to copy or rotate. Developer tools such as Claude Code, Cursor, and Codex can use a NeetoRecord API key instead if you prefer, but a key reaches the whole workspace rather than acting as you.

Can I give AI read-only access to NeetoRecord?

Yes. Read access is always on, while Create and update, and Delete, are separate permissions. Leave them unchecked if you want your AI assistant to search and summarize recordings without changing anything.

Can I automate NeetoRecord without using AI?

Yes. The NeetoRecord CLI works directly from your terminal, shell scripts, cron jobs, and CI workflows. You don't need Claude, ChatGPT, or another AI service to use it.

Is the NeetoRecord CLI open source?

Yes. It's on GitHub, and you can use it, read it, and change it.

Where is the NeetoRecord MCP server hosted?

NeetoRecord hosts the MCP server at https://connect.neetorecord.com/mcp/messages. You don't need to download or run a server yourself.

Does NeetoRecord MCP work on the free plan?

Yes. NeetoRecord's free plan includes all features, including the MCP server and the CLI.