Skip to main content
Glama
@inferra-trade/mcp-server

@inferra-trade/mcp-server

Official
by InferraTrade

@inferra-trade/mcp-server

CI

GPU rental prices for AI agents, over the Model Context Protocol.

The Inferra GPU Index publishes what an hour of an A100, H100, H200 or B200 rents for, aggregated from public rental markets, outlier-filtered, and attested on Solana mainnet through a Chainlink DON every five minutes. This server puts that number one tool call away from any MCP host: a desktop assistant, an IDE, an agent framework of your own.

{
  "mcpServers": {
    "inferra": {
      "command": "npx",
      "args": ["-y", "@inferra-trade/mcp-server"],
      "env": { "INFERRA_API_KEY": "ink_your_key" }
    }
  }
}

The key is free: sign in with a wallet at https://api.inferra.trade, no card, no email. Node 20 or newer.

Tools

Tool

What the agent gets

get_gpu_price

one model: USD per GPU-hour, when it is from, whether it is delayed, the state (live / warming / halt), the sources behind it, whether it is attested on chain

compare_gpu_prices

every model, or a subset, cheapest first, each as a multiple of the cheapest

get_gpu_market_summary

prices, 7-day change and weekly range per model, index health (computation, on-chain feeds, Chainlink delivery, API), the biggest mover

get_gpu_price_history

first, last, low, high and change over a range (1d to all), plus a thinned list of points

Every answer comes as readable text and as structured content, and every answer carries the attribution the API's licence asks for: Inferra GPU Index, https://index.inferra.trade.

Related MCP server: Cralo

What an agent needs to know, and is told

A halted model has no price. When fewer than three independent sources agree, the index freezes that model rather than printing a number one source could move on its own. This server answers usdPerGpuHour: null with the reason, never the last value. The state is also never delayed, on any tier.

The Free tier is 15 minutes behind. Deliberately: the board at index.inferra.trade is live, and so is the chain, but a service pricing its own product off the API gets the value 15 minutes late unless it pays. Every answer says delayed: true and gives the instant it is reporting.

It is a benchmark of offers, not a trade print. The number is a weighted quantile of what on-demand rental is being offered at, per canonical SKU (H100 80GB SXM is not H100 PCIe). Method in full: https://index.inferra.trade/methodology. Uptime and every incident: https://index.inferra.trade/status.

Configuration

Variable

Default

INFERRA_API_KEY

required for every tool; ink_… from https://api.inferra.trade

INFERRA_API_URL

https://api.inferra.trade

a self-hosted index, or a test stub

INFERRA_TIMEOUT_MS

10000

per request

Without a key the server still starts, and each tool answers with instructions for getting one. An MCP host shows a server that exits at once as an opaque failure; a readable tool error is something the user can act on.

The server makes one API call per tool call, except get_gpu_market_summary, which makes two plus one per live model, one at a time. A Free key allows 60 calls a minute, which is a lot of questions about GPU prices.

Programmatic use

import { InferraApi, createInferraMcpServer } from '@inferra-trade/mcp-server'

const api = new InferraApi({ apiKey: process.env.INFERRA_API_KEY })
const server = createInferraMcpServer({ api })
// connect it to any transport the MCP SDK provides

The answer builders (priceAnswer, compareAnswer, summaryAnswer, historyAnswer) are exported too, for anyone who wants the same text and structure inside a different tool surface.

Without this server

Nothing here is privileged. The same numbers are on https://index.inferra.trade with no key, on https://api.inferra.trade as plain JSON, and in four Solana accounts anyone can read with @inferra-trade/gpu-index or a bare RPC call. This package exists so that an agent does not have to be taught any of that first.

Licence

MIT. If you publish a number from the index, attribute it to the Inferra GPU Index and link https://index.inferra.trade so a reader can check it.

Available Tools

4 tools
compare_gpu_pricesCompare GPU pricesA
Read-onlyIdempotent

Compare current rental prices per GPU-hour across models, cheapest first, with each model's multiple of the cheapest one. Omit models to compare every model in the index (A100, H100, H200, B200). Models that are not publishing are listed without a price.

Inputs: models.

get_gpu_market_summaryGPU market summaryA
Read-onlyIdempotent

One-call overview of the GPU rental market: every model's current price per GPU-hour, its 7-day change and weekly range, how many sources price it, whether its on-chain feed is fresh, plus the health of the index itself (computation, on-chain feeds, Chainlink delivery, API) and the biggest mover of the week. Use this first when asked "what do GPUs cost right now".

Inputs: no named parameters.

get_gpu_priceGPU rental priceA
Read-onlyIdempotent

Current rental price of one GPU model in USD per GPU-hour from the Inferra GPU Index, with the timestamp, whether the value is delayed, the model state (live / warming / halt), the number of sources behind it and whether it is attested on Solana mainnet. A halted model returns no price. Models: A100, H100, H200, B200.

Inputs: model (required).

get_gpu_price_historyGPU price historyA
Read-onlyIdempotent

Price history of one model in USD per GPU-hour over a range (1d, 3d, 7d, 14d, 30d, 90d, 1y, all), with the first and last value, the change, the low and the high, and a thinned list of points. The Free API tier sees 30 days; longer ranges are clamped and the answer says so.

Inputs: model (required), range, maxPoints.

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    A4.4/5.0

    Scored across 4 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: single-model current price, cross-model price comparison, full market overview, and historical price trends. No two tools overlap in what they return, making misselection unlikely.

    Naming Consistency4/5

    Three of four tools follow the 'get_gpu_*' pattern, while 'compare_gpu_prices' uses a verb-object form without 'get'. This is a minor deviation, but the naming is otherwise predictable and readable.

    Tool Count5/5

    Four tools is well-scoped for a GPU price index server: current price, comparison, summary, and history cover the main use cases without unnecessary redundancy.

    Completeness4/5

    The tool surface covers the core lifecycle of price queries (individual, comparative, overview, history). A minor gap is the lack of a dedicated endpoint to list available models, though the summary and comparison tools implicitly provide this information.

    Maintenance

    ActivitySlowing
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      C
      maintenance
      Provides public price indices for GPU rentals (spot, on-demand, DePIN) with verify URLs, enabling agents and users to query and verify compute economics rates.
      5
      1
      Apache 2.0
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents to query multi-cloud costs, inventory, waste, and commitments across AWS, GCP, Cloudflare, and OVH through read-only MCP tools.
      Apache 2.0