Skip to main content
Glama
BPE MCP Server

BPE MCP Server

by bxetech

BPE MCP Server

Model Context Protocol server for the BPE market-data API. Lets Claude Desktop, Cursor, Goose, and other MCP-enabled agents query consolidated Bitcoin pricing, ML signals, funding-rate skew, and natural-language market briefings — without writing any HTTP boilerplate.

Status: v0.2 — five tools, local stdio transport, no LLM calls inside the briefing endpoint (template-rendered). API key required.

Listed in the official MCP Server Registry as io.github.bxetech/bpe-mcp. Install via npm install -g @bxetech/bpe-mcp or npx -y @bxetech/bpe-mcp.

Why use it

If you're building an agent that touches Bitcoin markets, you have two options today:

  1. Talk to 36 different exchange APIs directly. Each has a different schema, different auth, different rate limits, different reliability. Your agent burns tokens reasoning over inconsistent payloads.

  2. Use one consolidated source. BPE aggregates all 36 venues into a single normalised feed with derived signals (ML predictions, sentiment, funding skew, basis). One auth, one schema, one tool call.

This MCP server is option 2 dressed up as native tools your agent can discover and call.

Related MCP server: polymarket-mcp

Tools (v0.2)

Tool

What it does

get_consolidated_price

Current BTC price aggregated across the BPE network

get_market_briefing

~4 lines (brief) or 6–8 (detailed) natural-language summary — price, funding skew, ML signal, sentiment, anomalies

get_funding_skew

Per-venue annualised funding rates + max-spread pair

get_ml_signal

Current ML prediction (direction, probability, confidence) at the requested horizon

get_sentiment_snapshot

Crypto Fear & Greed index, news sentiment, mempool stress

Install

npm install -g @bxetech/bpe-mcp

Or use npx with no install (recommended for Claude Desktop):

// ~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "bpe": {
      "command": "npx",
      "args": ["-y", "@bxetech/bpe-mcp"],
      "env": {
        "BPE_API_KEY": "bpe_..."
      }
    }
  }
}

Restart Claude Desktop. The five tools appear under the MCP server picker.

Configuration

Env var

Default

Notes

BPE_API_KEY

(required)

Get one at https://bxetech.com/contact

BPE_BASE_URL

https://mcp.bxetech.com

Override for self-hosted / local dev

BPE_TIMEOUT_MS

5000

Per-request timeout

Local development

git clone https://github.com/bxetech/bpe-mcp
cd bpe-mcp
npm install
npm run build
BPE_API_KEY=... npm run dev

To dogfood in Claude Desktop while iterating, point at the local build:

{
  "mcpServers": {
    "bpe-dev": {
      "command": "node",
      "args": ["/abs/path/to/mcp-server/dist/index.js"],
      "env": {
        "BPE_API_KEY": "...",
        "BPE_BASE_URL": "http://localhost:8082"
      }
    }
  }
}

Roadmap

  • v0.2 — get_sentiment_snapshot ✅, friendly tier-aware errors ✅, timestamped briefings ✅

  • v0.3 — get_basis, subscribe_alert (webhook subscription), hosted HTTP transport for non-developer install (Cursor extension, ChatGPT Desktop)

  • v0.4 — Optional LLM-rendered briefing via Haiku (richer prose, with per-call cost)

See docs/research/AGENT_INTEGRATION_AND_MONETISATION_2026-04-27.md for the broader product / monetisation plan.

License

MIT — see LICENSE.

Available Tools

5 tools
get_consolidated_priceA

Get the current consolidated Bitcoin price aggregated across the BPE exchange network. Returns price in USD, the number of contributing exchanges, and freshness in milliseconds. Use this when an agent or user asks 'what's the BTC price right now?' — it's faster and more authoritative than calling any individual exchange.

Inputs: symbol.

get_funding_skewA

Get current perpetual-futures funding rates across major venues, plus the max-spread pair. Annualised. Useful for assessing perp-perp arbitrage conditions, basis trades, and overall positioning skew — high spread = stretched positioning on one side. Returns a sorted table.

Inputs: no named parameters.

get_market_briefingA

Get a concise natural-language summary of the current Bitcoin market state. Synthesises consolidated price, funding-rate skew across major perpetual venues, current ML prediction, and sentiment indicators. 'brief' mode returns roughly 4 lines (price, funding skew, ML signal, sentiment); 'detailed' adds per-venue funding breakdown and ML sub-model details — typically 6-8 lines. This is the most token-efficient way for an agent to get the 'what's happening right now' picture — replaces 4-5 raw data calls plus the reasoning to summarise them.

Inputs: verbosity.

get_ml_signalA

Get the current ML prediction for a specified time horizon. Returns direction (up/down/flat), confidence (0-1), and detected market regime (low/medium/high volatility). The model is a calibrated gradient-boosted classifier trained on a broad feature set including order book imbalance, cross-exchange spreads, sentiment, derivatives, and momentum.

Inputs: horizon.

get_sentiment_snapshotA

Get current Bitcoin market sentiment indicators. Returns Crypto Fear & Greed index (0-100, with label), FinBERT news sentiment (-1 most bearish to +1 most bullish, scored from CoinDesk + Cointelegraph headlines), Google Trends search interest (0-100, baseline 50), and a composite score (-1 to +1) blending all three. Useful for contextualising price action, detecting positioning extremes that may precede reversals, and as a coarse macro filter for shorter-horizon ML signals. Individual indicators are omitted when their upstream collector hasn't run yet.

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.3/5.0

    Scored across 5 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: price, sentiment, funding, ML prediction, and a synthesized briefing. There is no overlap, as each addresses a different aspect of market data.

    Naming Consistency5/5

    All tools follow a consistent get_<noun> pattern in snake_case, making it easy to infer their function from the name.

    Tool Count5/5

    With 5 tools, the server is well-scoped for providing key Bitcoin market insights without being overwhelming or too sparse.

    Completeness4/5

    The set covers price, sentiment, funding, ML signals, and a summary, but lacks direct access to order book or historical data, which are minor gaps for some analysis tasks.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables access to Great Britain electricity grid and market data via the Elexon BMRS Insights API.
      80 npm
      MIT
    • A
      license
      A
      quality
      F
      maintenance
      Wraps a hosted prediction market API to expose estimation, sizing, scanning, ensemble, and service-information tools for experimental research, returning payment-required details on HTTP 402 responses without handling payment itself.
      5
      15 npm
      MIT