Crypto perps data for AI agents: funding rates, open interest, liquidations, order book, CVD.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
We haven't yet run this listing's install command through our automated sandbox check. This isn't a red flag β we're steadily working through the catalog.
π‘ Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)
Read-only crypto perps microstructure for AI agents β normalized cross-exchange market state with self-declared coverage and freshness on every metric. Facts and normalization, no verdicts: the agent interprets.
https://api.markettrace.ai/mcp (Streamable HTTP, OAuth β no API keys)ai.markettrace/agent-feedThis repo is the front door β connection configs, the interface contract, and a thin stdio bridge. The data pipeline itself (4-venue ingest, archives, normalization) is not open source.
6 assets (BTC, ETH, SOL, BNB, XRP, DOGE) across Binance, Bybit, OKX, Hyperliquid:
| Tool | What it answers |
|---|---|
get_market_state | One normalized snapshot: funding + multi-year percentile, OI, volume, CVD, order-book imbalance, liquidations, basis, drivers. "Is ETH positioning stretched?" |
get_funding_percentile | Current funding ranked against its own multi-year history (0β100) + same-sign streak. |
get_liquidations_recent | Cross-exchange liquidation totals for a window: USD, long/short split. |
get_ohlcv | Consolidated cross-exchange candles (5mβ¦1d) for ATR/range/RV math. |
get_conditional_outcomes | Measured forward-return history after a stated condition β base rates instead of folklore. "What happened historically after funding above the 90th percentile?" |
get_state_history | Time series of any numeric state field from the 15-minute archive β the trend view behind the snapshot. |
Data: funding rates, open interest, cumulative volume delta (CVD), order-book depth, liquidations, OHLCV candles.
Honesty model: every metric carries a coverage entry (venues, window
depth, freshness); thin history answers with disclosed depth instead of
made-up numbers; conditional outcomes go history_silent below the evidence
floor; every response self-declares its age. Reports history, not predictions.
Claude (web/desktop): Settings β Connectors β Add custom connector β
https://api.markettrace.ai/mcp β authorize (email magic link).
Claude Code:
Stdio-only clients (via the standard OAuth-capable bridge):
More client configs in examples/mcp-configs.md.
mcp_server.py is a zero-dependency stdio bridge: it starts
and answers introspection (initialize, tools/list) with no credentials β
the bundled tools.json is a snapshot of the hosted server's
own contract. Tool calls are proxied to the hosted endpoint when
MARKETTRACE_BEARER is set; without it they return a pointer to the hosted
OAuth endpoint instead of data. It holds no methodology β just a client.
Refresh the contract: tools.json is a {version, generated_at, tools} snapshot of the live server's tools/list β regenerate it by capturing that response and stamping the current contract version (mirrors feed.version in get_market_state).
Or with Docker:
Informational market data only β not financial advice. Privacy Policy Β· Terms of Service Β· Contact: support@markettrace.ai
The bridge in this repo is MIT-licensed (LICENSE); the hosted service is governed by the Terms above.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/markettrace-agent-feed-2)<a href="https://allmcps.com/mcp/markettrace-agent-feed-2"><img src="https://allmcps.com/api/badge/markettrace-agent-feed-2?style=directory" alt="MarketTrace agent Feed on AllMCPs" /></a>