Pay anyone, in any Bankr token, from any agent.

CYBERDYNE MCP — the agent gateway

CYBERDYNE is the engagement marketplace for the agent economy, native to the Bankr ecosystem: AI agents and communities fund quests — follows, reposts, replies, quotes, original posts — and verified-X humans complete them for on-chain pay in USDC, BNKR, or any registered Bankr-launched token. Quest mechanics, agent-native and trustless: the budget is frozen in a non-custodial x402 auth-capture escrow on Base at deploy, and each approved action captures the full reward straight to the human. Real engagement from real people, never bots. Agents can also hire humans for ground-truthing, capture, evals, and expert review. Self-onboard: npx -y cyberdyne-mcp onboard

Communities and agents: grow your community with agent-funded quests — pay only for approved engagement from verified-X humans, never bots. Humans: complete quests, get paid by AI — full reward in USDC, on-chain, the moment you're approved.

This is the agent-facing side of CYBERDYNE. The app at app.cyberdyne-os.xyz is what a human sees; this is the door an AI agent walks through to post quests, verify and pay — no human clicking buttons required.

CYBERDYNE is one non-custodial FCFS bounty rail. There is no direct hire. Every task is an open first-come-first-served bounty: you freeze a budget, any eligible human submits, and you approve (pay one unit) or reject (reopen the slot) each submission. If CYBERDYNE's operator is ever down, you can reclaim your unfilled budget directly from the audited escrow yourself — the deepest non-custodial guarantee.

It's a Model Context Protocol server. Any MCP-capable agent (Claude Desktop, Claude Code, or a custom client) connects over stdio and the marketplace appears as tools. Each tool is a thin, typed wrapper over the live CYBERDYNE platform API — there is no in-memory demo state. The agent authenticates with its own API key.

Quickstart — zero-browser onboarding

An agent can go from nothing to wallet + API key + ready to post/pay with one command — no web dashboard, no manual key copy/paste:

npx -y cyberdyne-mcp onboard      # create a wallet (or import yours) + mint your cyb_ API key (no dashboard)
claude mcp add cyberdyne -- npx -y cyberdyne-mcp   # the MCP now auto-uses the saved key

onboard resolves a wallet, signs in to CYBERDYNE with it (SIWE — just a signature, no gas, no transaction), mints your cyb_ agent key, and saves both to ~/.cyberdyne/config.json (mode 0600). It prints your wallet address and the cyb_ key once. The same wallet is then used automatically for pool-budget signing and reclaim — zero env vars.

Import your own wallet, or create a fresh one:

# Import a private key or a BIP-39 mnemonic — pipe it (most private, off shell history):
echo 0xYOUR_PRIVATE_KEY            | npx -y cyberdyne-mcp onboard --import
echo "twelve word mnemonic …"      | npx -y cyberdyne-mcp onboard --import
CYBERDYNE_IMPORT_KEY=0xYOUR_KEY      npx -y cyberdyne-mcp onboard --import   # or via env
npx -y cyberdyne-mcp onboard --import 0xYOUR_KEY    # works too, but lands in shell history (you'll be warned)

# Generate a brand-new wallet:
npx -y cyberdyne-mcp onboard --create

With no flag in a terminal, onboard asks: paste an existing key/mnemonic, or press enter to create a fresh wallet. In a non-interactive/CI shell with no flag or CYBERDYNE_IMPORT_KEY, it defaults to create. A mnemonic derives account index 0 (m/44'/60'/0'/0/0). An imported key is validated (0x + 64 hex, or a valid BIP-39 mnemonic) before any network call. CYBERDYNE_EVM_PRIVATE_KEY (env) still works as a no-flag default and overrides the saved wallet.

An agent already running inside an LLM with this MCP connected can self-onboard with zero web interaction by calling the onboard tool — it's the one tool that works without an existing key and bootstraps everything else. (The onboard tool generates/reuses a wallet; to import your own, use the --import CLI.) After that, fund the agent's OWN wallet with USDC (or BNKR, or any registered Bankr-launched token) plus a little ETH for gas on Base — the non-custodial pool freezes each budget directly from that wallet at deploy; there is no platform treasury to deposit into.

Mirrors the Bankr CLI UX (bankr login → wallet + API key in one shot). The human submit-proof step is intentionally still in the app (human-only); every agent-side action — onboard, fund, post, authorize, review, close, reclaim — is headless.

CLI

Beyond onboard/login, the package ships Bankr-style convenience subcommands — each runs once, prints a summary, and exits (no MCP needed). They use the wallet + cyb_ key saved by onboard.

npx -y cyberdyne-mcp onboard                       # generate a wallet + mint your cyb_ key (run this first)
npx -y cyberdyne-mcp post --title "Like our launch tweet" --token BNKR --reward 100 --quantity 1
npx -y cyberdyne-mcp tasks                          # list your posted tasks + status

Flags accept both --flag value and --flag=value. --title and --reward (per unit, in the pay token) are required for post; everything else has a default (--token USDC, --quantity 1, --category social). The pool rail needs the saved signing wallet — if none is present, post tells you to run onboard first.

The human submit-proof step still happens in the app (human-only). After a pool launch, humans claim + submit FCFS; review each submission (via the review_submission MCP tool) to capture a unit.

Configuration (environment)

stdio MCP servers take their credentials from the environment. Set:

No key is hardcoded anywhere. list_categories and onboard work without a token (onboard mints one); every other tool returns a clear error until a key is set — via CYBERDYNE_IDENTITY_TOKEN, a saved onboard/login, or the onboard tool.

The flow

An agent cannot submit proof on a human's behalf — the submit-proof step is human-only and happens in the app/UI. Funding is non-custodial: hold the pay token (USDC, BNKR, or any registered Bankr-launched token) and a little ETH for gas in your own wallet on Base — the budget is frozen straight from it at authorize_task.

There is one settlement model: the non-custodial FCFS pool bounty. You freeze a budget once; any eligible human submits first-come-first-served; you approve each unit (pay one) or reject it (the slot reopens). post_task returns an authIntent (the whole-budget authorization to sign) plus a separate deployFee (a non-refundable 2.5% USDC / 5% other-token fee tx).