Eclipse Agent Wallet MCP

io.github.CYAN-ECLIPSE-TECHNOLOGIES-LLCPublished by GitHub account CYAN-ECLIPSE-TECHNOLOGIES-LLCv0.1.0Updated Oct 26, 2026

Policy-scoped agent wallet: caps, recipient allowlist, human approvals, kill switch, audit trail.

VerifiedSTDIODesktop onlyFinanceSecurity & Monitoring

Overview

AI-generated overview

Sandbox agent wallet MCP server that lets an assistant create wallets, spend only within owner-set policy caps, and log every action to an audit trail.

What you can do
  • Create and inspect wallets: create a wallet for a named owner, then read balance, frozen state, today's spend and active policy
  • Set spending scope: grant per-transaction and daily caps, approval threshold, recipient allowlist, expiry and purpose, returning a plain-language liability receipt
  • Check and execute payments: dry-run a payment for allow, approve or deny, then pay inside scope, reject outside it, or queue above the threshold
  • Resolve approvals: approve or deny queued payment requests as the owner
  • Audit and revoke: read the append-only audit log and freeze the wallet instantly with a timestamped kill switch
  • Fund sandbox wallets with simulated test USDC for demos and tests
When to use it
Useful when you want an assistant to make payments under explicit, owner-written limits rather than open-ended authority, and want a provable record of what was authorized. It is a reference implementation for testing policy-scoped spending, not a way to move real money.
Requirements
Runs locally over stdio as a Python 3 process using only the standard library, or via the published Docker image. State is kept in a ledger JSON file, defaulting to ledger.json beside the server and overridable with the AGENT_WALLET_LEDGER environment variable. No accounts, API keys or network access are needed.
Before you install
Sandbox only: balances are simulated test USDC in a local JSON ledger, no real funds move and no network calls are made. The optional desk extension involves a secp256k1 key held outside the server and per-spend signatures; treat any key material carefully. Payments, approvals and revocations change ledger state, so point AGENT_WALLET_LEDGER at a file you are willing to have modified.

Installation

In SourceWeft

  1. Open Eclipse Agent Wallet MCP in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

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 SI 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

v0.2.0 reference implementation. Sandbox only — balances are simulated test USDC in a local JSON ledger. No real funds move and no network calls are made. The policy engine is the product; production payment rails (x402, partner processors) plug in behind it without changing the tool surface.

Desk extension (v0.2.0, 2026-10-27): a wallet may be bound at creation to a desk identity — a per-desk secp256k1 key held in envelope custody outside the server (desk_keys.py / desk_envelope.py, envelope custody). A desk-bound wallet takes the key's real EVM address, and every spend must carry that desk key's signature (EIP-191 over the canonical spend message; strictly increasing nonce per wallet), verified server-side in pure Python (desk_verify.py). Unbound wallets behave exactly as v0.1.0. Operator console: desk_cli.py (issue / policy / fund / signed pay / revoke). The v0.1.0 policy engine was CERTIFIED(sandbox) by the Eclipse Bazaar Test Bench on 2026-10-24; the desk extension is benched separately (see the team wallet registry record).

Tools (10)

ToolWhat it does
create_walletCreate a wallet owned by a named human. Cannot spend until a policy is granted.
get_walletBalance, frozen state, today's spend, active policy.
set_policyOwner grants the spending scope; returns a plain-language liability receipt.
fund_walletSandbox faucet (simulated test USDC) for demos/tests.
check_paymentDry-run: returns allow / approve / deny with the reason. Agents call this before pay.
payExecute inside scope; reject outside it; queue for approval above the threshold.
approve_payment / deny_paymentOwner resolves a queued request.
audit_logThe full append-only trail.
revokeKill switch — freeze instantly.

Run it

bash
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.

Source: README.md at commit 0a0082e

Tools

0
SourceWeft started this package once in an isolated sandbox, without credentials, to list its tools. That failed: the package type cannot run in the sandbox.

Version history

1
  1. v0.1.0LatestOct 26, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts