
Arbitova
io.github.jiayuanliang0716-maxPublished by GitHub account jiayuanliang0716-maxv3.4.0Updated Nov 3, 2026
Escrow + AI arbitration for A2A payments. Lock funds, confirm delivery, dispute if needed.
Overview
Non-custodial USDC escrow and AI arbitration for agent-to-agent payments on Base, letting an assistant create, confirm, dispute and inspect escrows.
- What you can do
- Create escrows that lock USDC for a seller with delivery and review windows
- Mark delivery and confirm or dispute it, or cancel if nothing was delivered
- Read escrow state for read-only introspection
- All six tools sign locally with ethers v6 against the EscrowV1 contract
- When to use it
- Use it when an assistant needs to settle a paid job between two agents that do not trust each other: locking funds, confirming delivery, or opening a dispute that a neutral AI arbiter resolves. Also useful for read-only monitoring of escrow state.
- Requirements
- Runs locally via npx as a Node.js package. Needs an Ethereum address and, for write actions, a private key supplied through ARBITOVA_AGENT_PRIVATE_KEY; omitting it gives read-only mode. The README's example also sets RPC, escrow and USDC address variables. Currently live on Base Sepolia testnet with real USDC; mainnet is pending audit.
Installation
In SourceWeft
- Open Arbitova in the dashboard and add it to a workspace.
- 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
Arbitova
[jiayuanliang0716-max/Arbitova MCP server]
Non-custodial USDC escrow + AI arbitration for agent-to-agent payments on Base.
Two agents lock USDC into a contract, one delivers, the other confirms or disputes, and a neutral AI arbiter resolves. Arbitova never holds the money — the contract does.
No API keys. No registration. No custody. Your Ethereum address is your identity.
- Contract:
EscrowV1at0xA8a031bcaD2f840b451c19db8e43CEAF86a088fCon Base Sepolia — verified on Basescan, mainnet launching after audit - Spec:
A2A-ESCROW-RFC-v0.1 - Machine-readable descriptor:
/.well-known/arbitova.json - Per-case verdict dashboard: arbitova.com/verdicts
- Integration paths: arbitova.com/integrate (raw contract / reference SDKs / agent-native)
- Reference UI (non-canonical, for humans): arbitova.com/pay
- 15-minute tutorial:
docs/tutorials/15-min-paid-agent.md
Why this exists
Every A2A / agent-commerce spec in the wild — MCP, Google's A2A, ERC-7683, Coinbase's Agent Commerce — defines how agents talk. None of them define how money moves when the agents don't trust each other.
Arbitova is the missing settlement primitive:
- Deterministic state machine.
createEscrow → markDelivered → {confirmDelivery | dispute → resolve | cancel}. No hidden branches, no admin override. - No auto-release after timeout. Review windows expire into
DISPUTED, not into seller payout. Silence is safer than a wrong confirmation. - Content-hash pinned on-chain. Sellers can't swap the delivery file after the buyer inspects.
- Per-case verdict transparency. Every arbiter decision is a signed JSON blob; its
keccak256is stored on-chain. The full verdict history is queryable at/verdicts— no aggregation, no delay.
This is not a marketplace. There is no Arbitova account, no listing fee, no Pro tier. The protocol is the whole product.
Quick start — Node.js SDK
Seller-side, arbiter-side, browser wallet integration: see packages/sdk-js/README.md.
Quick start — Python SDK
Quick start — Claude / any MCP client
Six tools: arbitova_create_escrow, arbitova_mark_delivered, arbitova_confirm_delivery, arbitova_dispute, arbitova_cancel_if_not_delivered, arbitova_get_escrow. All sign locally via ethers v6. Your private key never leaves the process.
Omit ARBITOVA_AGENT_PRIVATE_KEY for read-only introspection mode (useful for observability).
Lifecycle
Two terminal states not drawn: CANCELLED (buyer calls cancelIfNotDelivered after delivery window) and auto-escalation into DISPUTED if the review window expires without confirmation.
Framework reference agents
Three end-to-end A2A demos on Base Sepolia with a live AI arbiter:
- Claude Agent SDK — in-process MCP tools
- LangGraph — ReAct agent, buyer + seller + arbiter
- CrewAI — Agent + Task + Crew
Each demo runs the full CREATED → DELIVERED → CONFIRMED (or DISPUTED → RESOLVED) flow with real on-chain transactions.
Packages
Each ships the same six-entrypoint surface so an agent using the Python SDK can settle with an agent using the MCP server — they're hitting the same contract.
Fees
Fees accrue in the contract. The protocol runs on them; there is no subscription.
Networks
Watch the Dev Log for mainnet launch.
Legacy (Path A)
v2.x of the SDKs and v3.4.0 of the MCP server were a custodial HTTP client against api.arbitova.com. That architecture had four structural problems (DB-vs-onchain drift, custody wallet gas, single ADMIN_KEY, single WALLET_ENCRYPTION_KEY point of failure) and was deprecated in favor of Path B — the non-custodial on-chain design described above.
- Migration for SDK users:
sdk/MIGRATION_PATH_A_TO_B.md - Migration for MCP users:
mcp-server/MIGRATION.md
Old packages remain on npm/PyPI but are deprecated.
License
MIT
Source: README.md at commit f8bb861
Tools
0Version history
1- v3.4.0LatestSep 16, 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