Skip to main content
Glama
BackPow MCP Server

BackPow MCP Server

BackPow MCP Server

The official Model Context Protocol server for BackPow — The Proof of Work Oracle.

It gives an AI assistant live mining data for 126+ Proof of Work networks and 770+ hardware models: network difficulty and hashrate, Poisson solo-mining probabilities, Cost of Production, and hardware profitability.

Endpoint: https://mcp.backpow.com/mcp — Streamable HTTP, no API key, no account, no rate-limit gate.


Install

Claude Code

claude mcp add --transport http backpow https://mcp.backpow.com/mcp

Claude Desktop / claude.ai

Settings → Connectors → Add custom connector → https://mcp.backpow.com/mcp

VS Code

{
  "servers": {
    "backpow": { "type": "http", "url": "https://mcp.backpow.com/mcp" }
  }
}

Cursor

Settings → MCP → Add, or in ~/.cursor/mcp.json:

{
  "mcpServers": {
    "backpow": { "url": "https://mcp.backpow.com/mcp" }
  }
}

Local stdio

Not published to npm yet, so there is deliberately no npx command here to copy — it would fail. The remote endpoint above is the supported path and works in every client listed.

To run it locally from a clone in the meantime:

npm install && npm run build
{
  "mcpServers": {
    "backpow": { "command": "node", "args": ["/absolute/path/to/backpow-mcp-server/dist/cli.js"] }
  }
}

Related MCP server: CryptoQuant MCP Server

Tools

Tool

Answers

calculate_solo_mining_odds

"How long to solo mine a Bitcoin block at 100 TH/s?" — mean time, Poisson probability over 1/7/30/90/365 days, the luck spread, and what the electricity costs while you wait

get_cost_of_production

"Is mining Monero profitable?" — CoP vs spot, gross margin, the reference machine and tariff, 30-day trend

get_coin_oracle

"What is Kaspa's current difficulty?" — live network state with a confidence block

list_pow_coins

Browse or filter the tracked networks by algorithm or profitability

get_hardware_benchmarks

"What should I mine with an RTX 4090 at $0.10/kWh?" — coins ranked by net USD/day

get_pow_news

Recent mining and network events, quoted as third-party content

All six are read-only and annotated readOnlyHint, so hosts that support auto-approval will not prompt on every call.

How results are shaped

Every successful result is an envelope:

{
  "warnings": [ /* plain prose caveats, e.g. a stale-collector or reward-status note */ ],
  "source": {
    "as_of_utc": "2026-09-18T08:12:00Z",
    "data_age_seconds": 30,
    "served_from": "live",
    "url": "https://backpow.com/Bitcoin",
    "cite_as": "BackPow — The Proof of Work Oracle, \"BTC solo mining odds\", retrieved 2026-09-18 — https://backpow.com/Bitcoin",
    "methodology": "…"
  },
  "data": { /* the figures */ }
}

Mining numbers move continuously, so a figure quoted without its date can be wrong within hours. Every result therefore carries its measurement timestamp and a citation line.

Two deliberate behaviours worth knowing:

  • Ambiguity is refused, not guessed. Several tickers are shared by multiple tracked chains (DGB by 5, XVG by 5). get_coin_oracle {"coin_id": "DGB"} returns an error listing the candidates rather than picking one.

  • Dead telemetry is refused, not zeroed. A network whose collectors are stalled or unreachable returns an error. It never returns 0 H/s as if that were a measurement.

Data and licence

Figures derive from BackPow's stratum collector nodes and market data, and are published under CC BY 4.0 — see backpow.com/llms.txt. Citation is requested, permission is not required.

This is a calculator and data source, not financial advice. No tool executes a transaction.


Development

npm install
npm run typecheck     # tsc --noEmit
npm test              # unit + integration, no network
npm run dev           # wrangler dev on :8787
npm run conformance -- http://127.0.0.1:8787   # protocol probe against a running server
npm run deploy        # Cloudflare Workers

scripts/conformance.mjs drives a live endpoint through the transport and security behaviours the unit tests structurally cannot reach. CI runs it against a wrangler dev instance on every push.

Transport

Streamable HTTP on a single endpoint, POST /mcp. The server is stateless: it mints no session ids, GET and DELETE answer 405, and notifications get 202 with no body. Protocol revisions 2025-11-25 through 2024-11-05 are negotiated at initialize; server/discover reports the supported set.

The deprecated HTTP+SSE transport has been removed. /sse and /message answer 410 pointing at /mcp.

Licence

MIT — see LICENSE.

Available Tools

6 tools
calculate_solo_mining_oddsSolo mining oddsA
Read-onlyIdempotent

Probability of a solo miner finding a block, computed as a Poisson process over live network difficulty and hashrate, plus the electricity cost of the attempt. Returns mean time to a block, the chance of at least one block over 1/7/30/90/365 days, and lucky-vs-unlucky waiting times (5th, 50th and 95th percentile) — variance dominates at small hashrates, so the average alone is misleading. Use for questions like "how long would it take to solo mine a Bitcoin block with 100 TH/s", "what are my odds solo mining Kaspa", or "is solo mining worth it with this rig". For pooled mining economics or whether a coin is profitable at all, use get_cost_of_production. For raw network state without a miner, use get_coin_oracle.

Inputs: coin_id (required), hashrate (required), hashrate_unit (required), power_watts, +1 more.

get_coin_oracleLive network stateA
Read-onlyIdempotent

Current network state for one Proof of Work chain, measured by BackPow's stratum collector nodes: difficulty, derived network hashrate, block height, block reward, protocol block-time target versus the latest observed interval, and the source pool. Every response carries a confidence block — how many independent pool operators agreed, whether the reward figure is live or a static fallback, and how old the observation is. Networks whose collectors are stalled or unreachable return an error rather than zeros. Use for "what is Kaspa's current difficulty", "network hashrate of Monero", "current block reward". For economics use get_cost_of_production; for mining probability use calculate_solo_mining_odds.

Inputs: coin_id (required).

get_cost_of_productionCost of productionA
Read-onlyIdempotent

Cost of Production (CoP) for one Proof of Work coin: the all-in electricity cost of mining one unit on the most efficient hardware BackPow tracks for that algorithm, compared against spot price. Returns CoP in USD, spot, gross margin, whether miners are currently above or below water, the reference machine and tariff behind the figure, and a 30-day trend including whether the reference machine changed (which indicates the efficiency frontier moved). Accepts a custom electricity rate. Use for "is mining X profitable", "what does it cost to produce one Monero", "are miners underwater", or "break-even electricity price". For a specific rig rather than a coin, use get_hardware_benchmarks. For block-finding probability, use calculate_solo_mining_odds.

Inputs: coin_id (required), electricity_cost_usd_kwh.

get_hardware_benchmarksMining hardware economicsA
Read-onlyIdempotent

Mining hardware matched to the coins it can mine, ranked by net USD per day at a given electricity rate. Covers ASICs, GPUs and CPUs, with hashrate and power draw per coin, gross revenue, net profit, and market price including whether that price is an observed listing or a model estimate. Use for "what should I mine with an RTX 4090", "best ASIC for Scrypt", "is an Antminer S21 still profitable", or "how much does a Bitaxe make". Coins are ranked by profitability, not alphabetically, and results are capped — ask for a higher limit rather than assuming the list is complete. For a coin's economics independent of any particular rig, use get_cost_of_production.

Inputs: query (required), type, limit, coin_id, +1 more.

get_pow_newsPoW mining newsA
Read-onlyIdempotent

Recent news items about Proof of Work mining and network events, optionally filtered to one coin. Items are aggregated from third-party feeds and are returned as quoted external content with their publisher and a relevance score, not as BackPow statements of fact. Use when a question turns on recent events — a halving, a difficulty swing, a pool outage, a chain upgrade. For numbers rather than narrative, use get_coin_oracle or get_cost_of_production.

Inputs: limit, coin_id, include_low_signal.

list_pow_coinsBrowse PoW networksA
Read-onlyIdempotent

Paginated index of the Proof of Work networks BackPow tracks, with algorithm, network rate, collector status and canonical page URL. Optionally filtered by algorithm or restricted to coins currently mining above cost. Returns the distinct algorithm list so valid filter values are discoverable. Use to find which networks exist for an algorithm, to browse the catalogue, or to resolve an ambiguous coin reference. Results are paginated: request a larger limit or a later offset rather than expecting the full catalogue in one response.

Inputs: limit, offset, sort_by, algorithm, +1 more.

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    A4.6/5.0

    Scored across 6 tools

    Disambiguation5/5

    Each tool targets a distinct aspect of PoW mining: odds, cost, network state, catalog, hardware benchmarks, and news. There is no overlap; even get_cost_of_production and get_hardware_benchmarks are clearly separated by coin-level vs rig-level economics.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun snake_case pattern (calculate_, get_, list_). The verbs are specific and the nouns clearly indicate the subject. No mixed conventions or vague verbs.

    Tool Count5/5

    Six tools is a well-scoped set for a PoW mining information server. Each tool serves a distinct function without redundancy, and the count is appropriate for the domain.

    Completeness4/5

    The surface covers the core workflows: network state, economics, hardware profitability, odds, catalog, and news. Minor gaps exist (e.g., no historical data or pool-specific details) but they are outside the apparent scope and do not hinder agent workflows.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      Enables AI assistants to access real-time on-chain crypto analytics, whale tracking, and market metrics through natural language queries. It provides access to over 245 endpoints for comprehensive data analysis of assets like Bitcoin, Ethereum, and stablecoins.
      7
      90 npm
      9
      MIT
    • A
      license
      C
      quality
      D
      maintenance
      Enables AI assistants to access comprehensive cryptocurrency market analysis, including real-time prices, 35+ technical indicators, market sentiment, futures data, and economic events.
      50
      2
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Enables AI assistants to fetch real-time cryptocurrency market data including prices, tickers, exchange data, and OHLCV candles from CoinPaprika with zero configuration.
      30
      64 npm
      30
      MIT