MCP and CLI guide for Auto Flow Agent Mode

npm install -g @autoflow-mcp/autoflow@beta
autoflow --help
autoflow-mcp --version

autoflow native install-host --extension-id <extension-id> --doctor
autoflow native install-host --extension-id <extension-id>
autoflow pair
autoflow status --json

{
  "mcpServers": {
    "autoflow": {
      "command": "autoflow-mcp",
      "args": []
    }
  }
}

Use Auto Flow MCP. First call autoflow_status, then autoflow_reconcile_project.
Before live submit, ask me for image model, video model, outputs per row,
image/video aspect ratios, video length, Return silent videos on/off, and exact
credit approval. Do not submit, retry, or spend credits unless I approve it.

CLAUDE_SKILL_SRC="$(npm root -g)/@autoflow-mcp/autoflow/claude-skills/autoflow-agent"
mkdir -p ~/.claude/skills
rm -rf ~/.claude/skills/autoflow-agent
cp -R "$CLAUDE_SKILL_SRC" ~/.claude/skills/autoflow-agent

Use the autoflow-agent skill. Start read-only with status and lane inventory.
Build the prompt matrix, dry-run the Agent Mode submit, and ask me for model,
outputs, ratios, silent-video setting, and credit approval before any live submit
or credit confirmation.

tmpdir=$(mktemp -d /tmp/autoflow-npm-mcp-smoke-XXXXXX)
cd "$tmpdir"
npm init -y >/dev/null
npm install @autoflow-mcp/autoflow@beta
node - <<'NODE'
const { spawn } = require("node:child_process");
const child = spawn("./node_modules/.bin/autoflow-mcp", [], { stdio: ["pipe", "pipe", "pipe"] });
let out = "";
child.stdout.on("data", (d) => { out += d; });
function send(message) {
  child.stdin.write(JSON.stringify(message) + "\n");
}
send({ jsonrpc: "2.0", id: 1, method: "initialize", params: { protocolVersion: "2024-11-05", capabilities: {}, clientInfo: { name: "autoflow-npm-smoke", version: "0.0.0" } } });
send({ jsonrpc: "2.0", method: "notifications/initialized", params: {} });
send({ jsonrpc: "2.0", id: 2, method: "tools/list", params: {} });
setTimeout(() => {
  child.kill();
  const messages = out.trim().split(/\n+/).filter(Boolean).map((line) => JSON.parse(line));
  const tools = messages.find((message) => message.id === 2);
  const toolNames = (tools?.result?.tools || []).map((tool) => tool.name);
  console.log(JSON.stringify({
    ok: toolNames.includes("autoflow_status") && toolNames.includes("autoflow_confirm_credits"),
    toolCount: toolNames.length,
    toolNames
  }, null, 2));
}, 1200);
NODE

You are controlling Auto Flow through its local CLI/MCP bridge.

Start read-only:
1. Run autoflow status --json.
2. Confirm the extension is connected, the client is paired, a Flow project is open, and the user is signed in.
3. Run autoflow agent reconcile --project current --json.
4. Build a download plan with autoflow agent artifacts download-plan --reconciled ./reconcile.json --run-name <run-id> --json.

Do not submit, retry, confirm credits, execute downloads, or spend credits until you have explicit project/tab targeting and user approval.
For write commands, use autoflow agent run with --project-id and --tab-id.
Before live submit, ask for image model, video model, outputs per row, image/video ratios, video length, Return silent videos on/off, and exact credit approval.
For video runs, confirm Flow settings Return silent videos is on before submit.
If Flow Agent is visibly waiting on a credit dialog after an image was generated, use autoflow agent confirm-credits with --project-id and --tab-id instead of re-running the row.
For reference-driven rows, attach the real image assets through the Agent plus button and Add to Prompt; typed filenames, handles, or media IDs alone are not enough.
If the bridge is disconnected, pairing is missing, the wrong tab is active, or project ownership is ambiguous, stop and report BLOCKED.
Never guess the Flow project. Never download HTML/tiny files as successful media. Never hide a credit-spending action inside a read-only step.