Peer Cash MCP

An MCP server for agents that need to cash out Base USDC throughPeer Cash. It exposes live payout capabilities, oracle estimates, unsigned transaction preparation, receipt finalization, order reads, withdrawals, and top-ups.

The repository is also anAgent Plugins 1.0package.plugin.jsonidentifies the package,skills/peer-cash/SKILL.mdprovides the portable workflow, andmcp.jsonstarts the published server without embedding credentials.

{ "mcpServers": { "peer-cash": { "command": "npx", "args": ["-y", "peer-cash-mcp"] } } }

The default environment is production and the public Base RPC is sufficient for normal reads. Optional environment variables:
- Callpeer_cash_capabilitiesbefore naming a payout platform or currency.
- Callpeer_cash_estimate. Treat it as approximate: the binding Chainlink rate resolves when a buyer fills.
- Callpeer_cash_preparewith a Base USDC amount in 6-decimal base units and one or more payout legs.
- Show the returned transaction plan and obtain explicit user approval.
- Submit each transaction in order through the host wallet and confirm it on Base.
- Callpeer_cash_finalizewith the confirmedcreateDeposittransaction hash.
- IfaccessPolicyRequiredwas true, callpeer_cash_prepare_access_policyand submit that transaction with the depositor wallet.
- Persist the returneddepositIdfor order tracking and recovery.

Unknown transaction outcomes must be inspected before any resubmission. Peer Cash errors include a code, retryability, remediation, and recovery evidence for this purpose.

Validate the portable package separately from the server test suite:

npx skills-ref validate skills/peer-cash

Bridge Town is an MCP-native, git-versioned financial modeling platform for FP&A teams and finance leaders. AI agents use Bridge Town tools to create projects, write Python model files, run models in isolated cloud sandboxes, query data, write outputs to Google Sheets, create dashboards, branch scenarios, and collaborate with teammates.

The Capital.com MCP Server lets your AI assistant talk to your trading account directly. Market data, position checks, trade previews – all in plain language, without leaving your AI tool.

Coinrule Agentic Trading MCP enables investors to create, backtest, execute, and manage trading agents through natural language across stocks, crypto and ETFs

Invest with Claude and other AI assistants

Australian Consumer Data Right Product Data

Remote MCP server for historical crypto & prediction-market data: search ~500K instruments, live market stats (OHLC, turnover, spreads, depth, slippage) and tick-data purchase. Keyless for catalog & stats; optional OAuth for account tools. Endpoint: https://cryptostruct.com/mcp

Cross-border debt collection from your AI assistant: check cases, get pricing, submit new cases.

Read-only MCP server for your Evibe investment portfolio + live market data (holdings, performance, dividends, benchmarks, screeners). Works with Claude & ChatGPT.

Financial and quantitative modeling engine for AI agents. Typed, named, deterministic.