@inferra-trade/mcp-server
OfficialClick on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@@inferra-trade/mcp-server compare current GPU rental prices for H100 and H200"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
@inferra-trade/mcp-server
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 |
| 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 |
| every model, or a subset, cheapest first, each as a multiple of the cheapest |
| prices, 7-day change and weekly range per model, index health (computation, on-chain feeds, Chainlink delivery, API), the biggest mover |
| 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 | |
| required for every tool; | |
|
| a self-hosted index, or a test stub |
|
| 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 providesThe 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 toolscompare_gpu_pricesCompare GPU pricesARead-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 summaryARead-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 priceARead-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 historyARead-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
Scored across 4 tools
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.
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.
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.
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
Related MCP Connectors
Pay-per-use tool marketplace for AI agents. Search, price-check, and call APIs via MCP.
ComputePortal marketplace: AI agents find, deploy and manage GPU and CPU compute through MCP.
Find and compare 41,000+ AI agents, MCP servers and APIs, with daily prices and the AEPI price index
Live cloud GPU prices, observed stock and 12-month price history across 30+ providers (H100, H200, A100, RTX 5090 and more), refreshed hourly. Read-only. Needs a GPU Finder API key sent as "Authorization: Bearer <key>"; free key with 60 data calls a month at https://gpufinder.dev/developers. Listing tools and get_usage are free.
Related MCP Servers
- AlicenseAqualityCmaintenanceProvides public price indices for GPU rentals (spot, on-demand, DePIN) with verify URLs, enabling agents and users to query and verify compute economics rates.51Apache 2.0
- FlicenseNot gradedqualityCmaintenancePay-per-use tool marketplace for AI agents. Search, price-check, and call APIs via MCP.-
- AlicenseNot gradedqualityBmaintenanceEnables 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
- AlicenseBqualityBmaintenanceEnables AI agents to submit GPU job requests, select eligible workers, track execution, and retrieve results via MCP.1421MIT