About peer-cash
peer-cash prepares and tracks Peer Cash Base USDC cash-outs. The repository is archived, and its functionality has moved into peer-cli; its tools create unsigned transaction plans and never take private keys, sign, or broadcast.
Key features
- 01Prepare unsigned transaction plans
- 02Track cash-out activity
- 03Never accept private keys or sign
- 04Never broadcast transactions
Use cases
- 01Review a cash-out plan
- 02Run the Cash profile through peer-cli
MCP support
The project was an MCP server; its tools are now provided by peer-cli with `mcp --profile cash`, retaining the `peer_cash_*` names.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y peer-cash-mcpPEER_CASH_ENVIRONMENTPeer Cash environment: production, preproduction, or stagingPEER_CASH_RPC_URLSecretCustom Base RPC URL for reads and receipt finalizationPEER_CASH_API_KEYSecretCurator API key when the selected environment requires onePEER_CASH_REFERRAL_CODESix-character Peer integration referral codePEER_CASH_REFERRERAnalytics-only ERC-8021 attribution codeLocal servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
9Saved tool list · updated 3w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| includeRelaySources | boolean | No | Include live Relay-supported EVM source chains and tokens |
Details
From the project READMEMoved to peer-cli
Peer Cash MCP is now part of the canonical
zkp2p/peer-cli runtime. This repository is
archived and receives no fixes or releases.
Use the custody-separated Cash profile:
npx -y github:zkp2p/peer-cli#v0.1.0 mcp --profile cash
The tool names and custody boundary are preserved: peer_cash_* tools prepare
unsigned transaction plans and never accept private keys, sign, or broadcast.
The published peer-cash-mcp npm package is historical. Do not start new
integrations on it.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.