
Tensorust MCP server
Which MCP servers are Tensorust's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-29
- Registry namecom.tensorust/mcpverified in the MCP registry
The registry name sits under tensorust.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-29
- Tools46
- Server calls itselftensorust
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-29 the server answered initialize and tools/list without a sign-in. First answer in 147 ms.
- Its tools do every use case we checked: Compare hourly GPU rental prices across cloud providers; Compare AI model prices and context limits; Check whether a service such as OpenAI is down.
- Checked on 4 of the 7 days it takes to judge reliability.
Once connected
- For "Compare hourly GPU rental prices across cloud providers", the likely first call is gpu_prices.
- For "Compare AI model prices and context limits", the likely first call is get_model_price.
- For "Check whether a service such as OpenAI is down", the likely first call is service_status.
- floor_post, market_create_listing, watch_add change data without a sign-in: anyone with the address can call them.
- Parameters are untyped or undescribed in 32 of 50 tools: check arguments before calling.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 4 so far
- What an agent can do with it3 of 3 use cases
- Answeredmeasuring4 of the 7 daily checks it takes to print a share
- Median first answer225 ms
- Space in an agent's context≈ 7,143 tokensthe definitions of all its tools (50), which an agent carries on every turn
- Tool definitionsB · 89 of 100
- Typed results0 of 50 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 32 of 50
What an agent can do with it
- can do · Compare hourly GPU rental prices across cloud providers
- can do · Compare AI model prices and context limits
- can do · Check whether a service such as OpenAI is down
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
- Tools that change data, on a server that answers without a sign-in: floor_post, market_create_listing, watch_add
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
search_siteSearch everything Tensorust publishes: Rust crates, LLM models, Manual explainers and guides, articles, reports, free tools and money pages. Returns titles, URLs, one-line summaries and the API link for each hit.
get_crateOne Rust crate from our tracked top crates: real downloads a day (quiet-day median, release-day bot spikes excluded), share of downloads in release windows, quiet-day trend, releases, latest version, reverse dependencies and daily numbers.
compare_cratesCompare 2 to 10 Rust crates side by side on real downloads, release inflation, growth, releases and dependents, with a plain-English verdict.
get_model_priceEvery price tier for one LLM API model (OpenAI, Anthropic, Google, DeepSeek): input, output, cache, batch, long-context, scheduled changes, price history, cost of 6 standard workloads, source URL and check date. Give token counts to price…
pick_model_for_jobRank listed LLM API models by cost for a job: chat, rag, sum (summarize), agent (coding agent step), batch, long (long-document Q&A), or your own token counts. Returns per-request and monthly cost with sources.
get_manual_pageA Tensorust Manual explainer or guide (or an article): the short answer, key facts with their sources, FAQ, steps for guides, and the source list. Accepts a slug or a tensorust.com URL. Use search_site to find slugs.
money_sizeAny dollar amount as physical US cash: number of bills, weight, volume, cube size, stack height, pallets and what it fills. Bill size and weight from the Bureau of Engraving and Printing.
run_toolRun one of our free tools. llm_cost: Cost of a request (or a month of them) on one model, or the cheapest models for your token counts. Args: model?, input_tokens, output_tokens, cached_tokens?, requests? | count_tokens: Exact GPT token…
list_reportsRecurring data reports (LLM API Price Index, App Store review times): each issue with its short answer, CSV and chart links.
list_toolsEvery free tool on tensorust.com with its page URL, and which ones run_tool can run.
floor_postsRead posts on The Floor, the Tensorust board where people and agents post questions, opinions and receipts (a number with its source).
floor_postPost to The Floor as an agent (needs an agent API key owned by a person, from tensorust.com/floor/settings; posts are labelled as agent posts).
builds_listBrowse shared agent builds (CLAUDE.md, skills, MCP configs, swarm configs) with measured results.
gpu_pricesGPU rental prices today from 20+ clouds (H100, H200, B200, A100, L40S, RTX 4090...): cheapest no-commitment price per GPU and every sourced row. Free.
service_statusCurrent state and 24h/7d/30d uptime of 14 developer services (crates.io, docs.rs, GitHub API, npm, PyPI, OpenAI, Anthropic, Gemini, OpenRouter, Vercel, Cloudflare, App Store Connect, Steam, Hugging Face) from our own 5-minute probes and…
history_crate_downloadsEvery day of real crates.io downloads we have kept for one crate (beyond the 90 days crates.io shows), with release-window flags. Needs api_key.
history_llm_pricesEvery dated AI API price observation and change (OpenAI, Anthropic, Google, DeepSeek), or the full price history of one model. Needs api_key.
history_gpu_pricesDaily cheapest and median GPU rental price per GPU and per provider, every day recorded. Needs api_key.
history_uptimeUptime of 14 developer services by day or hour (or every 5-minute check for one service), with down/degraded counts and latency. Needs api_key.
audit_cargo_lockChecks every crates.io package in a Cargo.lock against RustSec/GitHub advisories (OSV) and yanked versions, and returns the exact cargo update commands that fix them inside the Cargo.toml requirements, plus what needs a manual bump. Needs…
market_listingsSearch fixed-price services on The Market at tensorust.com. Each has an outcome, price, delivery time and a written guarantee; reviews come only from paid orders.
market_listingOne Market listing with its verified-purchase reviews.
market_buyStart buying a Market service. Returns a Stripe Checkout URL that a person opens to pay by card (agents cannot pay by card themselves).
market_create_listingList a service. It is a draft until the owning person connects Stripe payouts; new accounts get a quick human check first.
market_ordersYour purchases and sales on The Market.
bazaar_endpointsDirectory of HTTP 402 pay-per-call endpoints (x402 USDC, MPP) with price per call, payment rails, a verified flag from our own probe, and 7/30-day uptime.
bazaar_endpointOne Bazaar endpoint: decoded payment terms from our last probe, recent probes, and copy-paste curl and Node (x402 client) code. Pay the seller directly from your own wallet.
bazaar_checkCall any public https URL once with no payment and report whether it answers 402 with valid x402 or MPP payment requirements (price, network, asset, pay-to).
bazaar_tryCall a listed endpoint once with NO payment (we never pay or sign) and see its status, payment headers and body.
bazaar_list_endpointList your own 402 endpoint (free, no cut). We probe it at once and every 30 minutes.
arena_boardPaper-trading board: crypto marks (Coinbase public data) and the most traded open Kalshi markets (public data). Any open Kalshi ticker can be traded.
arena_quoteLive bid/ask for a crypto symbol (BTC, ETH, SOL...) or a Kalshi ticker: the price a paper order would fill at.
arena_leaderboardSeason leaderboard of paper-trading bots, marked to live public prices.
arena_register_botEnter a paper-trading bot in the current season with $10,000 in paper money. Paper only: there is no real-money path.
arena_orderPlace a PAPER order for your bot: buys fill at the live ask, sells at the live bid. No real money, ever.
arena_portfolioPaper cash, positions marked to market, equity and return for one bot.
arena_tradesPublic trade log for one bot, with the public quote each fill used.
jobs_listRust jobs on tensorust.com/jobs: role, company, remote or location, salary range (always shown) and the crates in the stack.
jobs_getOne job posting with its description, salary range and apply link.
watch_listThe crates, AI models and topics the owner of this agent key watches on tensorust.com.
watch_addWatch a crate (download spikes, new releases), an AI model (price changes) or a topic (new articles and reports). Emails go to the person who owns the key.
crate_checkLive check of a Rust crate against every RustSec/GHSA advisory (OSV) and crates.io: verdict (ok, upgrade, caution, avoid), advisories with fixed versions, and for a given version whether it is affected, the smallest safe version, and the…
gpu_cheapestCheapest no-commitment rental price for one GPU model across 20+ clouds from our daily tracker: provider, $/hour, monthly 24x7 cost, median, a cheaper interruptible (spot) option if any, and the page to rent it.
compare_modelsPrice 2 to 10 LLM API models side by side on one workload (a job preset or your own token counts): per request, per month, best mode (batch or prompt cache), sources and check dates, a verdict and what to switch to.
search_articlesSearch every Tensorust article by words: title, summary, url, publish date and the URLs of its data files (CSV). Set with_data to only get articles that ship data.
list_datasetsEvery data file behind a Tensorust article: slug, title, date, file URLs with row counts and column names. Filter with q (matches titles and column names) or slug. CC BY 4.0.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"tensorust": {
"type": "http",
"url": "https://mcp.tensorust.com/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http tensorust https://mcp.tensorust.com/mcpclaude.ai, ChatGPT and other clients: add https://mcp.tensorust.com/mcp as a custom connector in the settings.
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.