How do I use VIDEO AI ME with OpenClaw?

Last updated:

OpenClaw connects to VIDEO AI ME as a streamable HTTP MCP server: run openclaw mcp add videoaime --url https://videoai.me/api/v1/mcp --transport streamable-http, then add an Authorization header of Bearer va_live_YOUR_KEY to that server entry in ~/.openclaw/openclaw.json and run openclaw mcp reload. Create the key at videoai.me/developers on a Pro or Premium plan.

How do I connect OpenClaw to VIDEO AI ME?

  1. 1.Create an API key

    Log in at videoai.me and open /developers (Developers in the sidebar). Create a key, optionally with a budget cap in dollars so an agent can never overspend, and copy the full va_live_... value immediately: it is shown exactly once. API keys require an active Pro ($99/month) or Premium ($199/month) subscription.

  2. 2.Register the server with its header

    Add the server from the CLI with openclaw mcp add videoaime --url <server url> --transport streamable-http, then put your key in the Authorization header of that entry in ~/.openclaw/openclaw.json. Header values accept ${VAR} interpolation, so keep the key in your environment or the OpenClaw secret store rather than in the file itself.

    ~/.openclaw/openclaw.json

    { mcp: { servers: { videoaime: {
      url: "https://videoai.me/api/v1/mcp",
      transport: "streamable-http",
      headers: { Authorization: "Bearer va_live_YOUR_KEY" },
    } } } }
  3. 3.Reload and verify

    Apply the change to running agents and probe the connection. The VIDEO AI ME tools then sit under the same tool-policy controls as every other OpenClaw tool, so you can allow only discovery and publishing for some agents and makers for others. Ask an agent: "Make a 20 second explainer from this URL and schedule it to LinkedIn".

    Terminal

    openclaw mcp reload
    openclaw mcp doctor videoaime --probe

What can OpenClaw do once connected?

Every skill in the VIDEO AI ME registry: maker skills that generate UGC-style ads, product ads, explainers, and talking-head clips, publishing skills that post and schedule finished videos to your connected social accounts, free discovery skills for templates, actors, voices, and brand memory, and check_run for polling long runs. The full catalog with credit costs and typical durations is on the skill center page, and the REST API equivalent of every tool is described at https://videoai.me/api/v1/openapi.json.

What does access cost?

The API and MCP server are included with the Pro ($99/month) and Premium ($199/month) plans; there is no separate API price. Maker skills spend video credits from the plan's monthly allowance at 1 credit = 1 cent, always quoting the estimate first, and each API key can carry its own budget cap in dollars. Plans and allowances are on the pricing page.

OpenClaw setup questions

Direct answers about connecting OpenClaw to VIDEO AI ME.

Should the VIDEO AI ME server go in openclaw.json or in an agent openclaw.yaml?

openclaw.json under mcp.servers makes the server available to every agent on the gateway, which suits a single brand. Per-agent declarations in openclaw.yaml keep separate clients or budgets apart: each agent can carry its own key, created at videoai.me/developers with its own dollar cap.

Can OpenClaw tool policies restrict which VIDEO AI ME skills an agent may call?

Yes. Tools from an MCP server go through the same tool-profile and tool-policy controls as built-in tools, and the server entry accepts a toolFilter. A common split: allow list_templates, get_brand and check_run everywhere, and reserve the make_* and publish skills for an agent a human supervises.

Why does OpenClaw fail to connect to VIDEO AI ME with a 401?

The Authorization header is missing, mistyped, or interpolating an empty variable. Run openclaw mcp doctor videoaime --probe to see the exact response, confirm the key starts with va_live_ and is active at videoai.me/developers, and remember keys require a live Pro or Premium subscription.

Can an OpenClaw automation on Telegram or Discord make videos through VIDEO AI ME?

Yes: once the server is registered, any OpenClaw agent behind a channel can call it. Maker skills still return a credit quote that the agent must confirm, and publishing skills still confirm the platform list, so design the workflow to surface those confirmations to the human in the channel.

How do I stop an OpenClaw agent from overspending video credits?

Give the agent its own key with a budget cap in dollars at videoai.me/developers; once spend reaches the cap, maker runs are refused with key_budget_exceeded while free skills keep working. Combine it with a toolFilter that excludes the make_* skills for agents that only need to publish or report.