Integration

Bumpups integration

Bumpups turns public YouTube videos into timestamped chapters and answers questions about them. With this API an agent can process a YouTube link into chapters (the tool waits for the result and spends the account's minutes: the video's length in whole minutes, at least 1), read a video's status and chapters, ask a question about a ready video and read the Markdown answer, and check the plan and minutes left. API access needs the Pro plan; minutes and the 25 questions per video are shared with the Bumpups web app. Only public YouTube videos up to 3 hours are accepted (unlisted ones must be 30 minutes or longer; live streams and premieres are refused). Authentication is an API key (bu_live_ followed by 40 letters and digits) created on the API page of the Bumpups app, sent as a Bearer token.

Connect Bumpups How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Bumpups.Built from the 5 Bumpups tools below, on the connection you add once.

What you can do with Bumpups

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Question, 2 operations

ask_questionAsk questionPOSTAsks Bump AI a question about a ready video and returns at once with status pending: read the answer with get_question (about 10 s later). Uses no minutes; counts toward the video's 25 questions.
get_questionGet questionGETReturns a question's status (pending, answered or failed) and, once answered, the answer in Markdown citing moments of the video as m:ss. Call it after ask_question until status is answered.

Video, 2 operations

get_videoGet videoGETReturns a video's status (processing, ready or failed) and, once ready, its chapters as a list and as chapters_text, ready to paste into a YouTube description.
process_videoProcess videoPOSTSpends minutes (the video's length, at least 1; refunded if it fails): turns a public YouTube link into chapters, returned as a list and as chapters_text. Waits for the job and returns the finished result; gives up after 10 minutes.

Account, 1 operation

get_accountGet accountGETReturns the account's plan, its minutes for the cycle (limit, used, left) and when they reset. Read minutes_left before process_video: a video costs its length in whole minutes.

Use Bumpups from Claude Code, Cursor or Codex

Connect Bumpups in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Bumpups operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Bumpups

Create your workspace
Sign up free. Nothing to install.
Connect Bumpups once
Add your Bumpups connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.