Eclipse Agent Wallet MCP

Eclipse Agent Wallet MCP

Powered by Cyan Eclipse Technologies — https://cetech.ai Listed on Eclipse Bazaar (eclipsebazaar.com).

Why this exists

On November 24, 2026, Wells Fargo's Online Access Agreement Section 15 takes effect: anything your AI agent does with your bank account is legally you — "at your own risk," including transactions you did not want or intend, with no controls attached and no duty on the bank to watch.

This MCP server is the opposite design: an agent wallet where responsibility follows scope.

• The human owner grants a written policy: per-transaction cap, daily cap, approval threshold, recipient allowlist, expiry, purpose.
• The agent can spend only inside that scope. Outside it, payments are rejected — or routed to a human approval queue when they exceed only the approval threshold.
• Every grant, payment, rejection, approval and revocation is written to an append-only audit log — the evidence of what was actually authorized.
• A kill switch freezes the wallet instantly, with the revocation timestamped in the log. Revoking access to your bank means "notify us and wait"; here it is immediate and provable.

Status

v0.1.0 reference implementation. Sandbox only — balances are simulated test USDC in a local JSON ledger. No real funds, no private keys, no network calls. The policy engine is the product; production payment rails (x402, partner processors) plug in behind it without changing the tool surface.

Tools (10)

Tool	What it does
create_wallet	Create a wallet owned by a named human. Cannot spend until a policy is granted.
get_wallet	Balance, frozen state, today's spend, active policy.
set_policy	Owner grants the spending scope; returns a plain-language liability receipt.
fund_wallet	Sandbox faucet (simulated test USDC) for demos/tests.
check_payment	Dry-run: returns allow / approve / deny with the reason. Agents call this before pay.
pay	Execute inside scope; reject outside it; queue for approval above the threshold.
approve_payment / deny_payment	Owner resolves a queued request.
audit_log	The full append-only trail.
revoke	Kill switch — freeze instantly.

Run it

python3 server.py            # MCP over stdio, stdlib only, no dependencies

State persists in ledger.json beside the server (override with AGENT_WALLET_LEDGER).

Use it with your Muse (custom connector / local MCP)

Point your agent's MCP configuration at the command python3 /path/to/server.py — any MCP client (Muse, Muse, Cursor) can drive it. A worked example session:

1. create_wallet {owner_id: "[email protected]"} → wallet created, cannot spend.
2. set_policy {per_tx_cap_usdc: "50.00", daily_cap_usdc: "120.00", approval_above_usdc: "20.00", allowlist: ["0xMerchantA"], purpose: "API credits"} → liability receipt issued.
3. pay 10.00 to 0xMerchantA → executed. pay 60.00 → rejected (over cap). pay 30.00 → human approval required.
4. revoke → frozen, timestamped. Agent's authority ends the second the owner says so.

Roadmap

• v0.2: hosted HTTP transport + per-user API keys; policy templates (shopping, SaaS, research budgets).
• v0.3: real rails behind the same policy engine — x402/USDC settlement, partner-processor fiat — only under the owner's granted scope.
• v1.0: Eclipse Bazaar listing with live test-bench scorecard (policy-engine conformance suite runs against every release).

License / attribution

A Cyan Eclipse Technologies product. The "Powered by Cyan Eclipse Technologies" attribution travels with it.