Funding-mcp

Funding-mcp

Real-time perp market-data for AI trading agents — funding rates, funding-arb signals, open interest, volume, orderbook depth/slippage and oracle families across 25 venues, plus HIP-3 RWA coverage (tokenized stocks, metals, oil) that mainstream aggregators lack. x402-native pay-per-call (USDC on Base): one free funding screener tool + 11 paid tools with auto-pay.

Category
Visit Server

README

@usenami/funding-mcp

MCP server for multi-venue perpetual + HIP-3 market data — 20+ exchanges including Binance, Bybit, OKX, Hyperliquid, Aster, Lighter, and Hyperliquid HIP-3 sub-DEXes (stocks, metals, oil, forex, indices, pre-IPO synthetics) that CoinGecko / CMC / Coinglass don't aggregate.

Gives any MCP-capable AI agent a named, schema'd surface for funding, liquidity, positioning, flow, basis, and RWA data — backed by Usenami's live API. Pairs with @usenami/signer-mcp for keyless execution.

Tools

Tool What it does Cost
funding_screener Current cross-venue funding rates (preview) Free
funding_arb Ranked cross-exchange funding-arb candidates ~$0.003
funding_signal Decision-ready funding-arb signal: net-of-fees + breakeven + depth-sized max notional + liquidity flag ~$0.025
funding_spread Per-symbol funding spread across venues ~$0.001
funding_history Historical funding rates (backtesting) ~$0.005
orderbook_slippage Multi-venue execution cost / slippage ~$0.005
open_interest Current OI for ticker on venue ~$0.001
oi_delta OI change over a lookback window ~$0.003
volume_24h 24h perp volume for ticker on venue ~$0.001
volume_anomalies Anomalous volume spikes across venues ~$0.003
oracle_families Oracle-family / basis-risk map ~$0.001
rwa_coverage HIP-3 RWA coverage (stocks/metals/oil) ~$0.001

Paid tools settle in USDC on Base via the x402 protocol. Set X402_PRIVATE_KEY (a Base wallet holding USDC) and the paid tools auto-pay and return data; without it they return the x402 payment requirements so any x402-capable client can pay and retry. funding_screener is free and needs no wallet.

Note: funding_arb is a naive scan (excludes fees, latency, and execution timing) — treat it as a candidate list, not trade advice.

Install

{
  "mcpServers": {
    "usenami-funding": {
      "command": "npx",
      "args": ["-y", "@usenami/funding-mcp"]
    }
  }
}

Optional env: USENAMI_API_BASE (default https://api.usenami.io); X402_PRIVATE_KEY (Base wallet 0x… with USDC — enables built-in auto-pay for the paid tools).

Support

Hit a problem or want data we don't cover yet? Report issues / request data: support@usenami.io · Partnerships: business@usenami.io · Telegram: @USnami.

Local dev

npm install
npm run build
npm start

MIT · usenami.io

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured