Nodehour: GPU capacity sized from your run and quoted by providers MCP Server

by forevenza-services Your server? Claim it

answering

Nodehour: GPU capacity sized from your run and quoted by providers is answering right now. Last checked 7 min ago. It exposes 7 tools.

GPU cluster sourcing: describe the run, get a sized requirement, quotes compared by email

Uptime history 71 hours of history

71 hours agonow

100.0%

Uptime 24h

91 of 91 checks

Tools

read from the server

436 ms

Response time

average over 24h

open, no key

Access

streamable-http

What changed 12

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 5 November 2026. No other catalogue keeps this.

6 Nov 5 tools appeared accept_offer, decline_offer, inspect_offer and 2 more

6 Nov a tool changed the parameters it asks for submit_request

5 Nov 2 tools disappeared describe_proposition, list_propositions

5 Nov a tool changed version

5 Nov a tool description was rewritten submit_request

5 Nov a tool appeared describe_business

5 Nov a tool changed the parameters it asks for submit_request

Tools have disappeared from this server

A tool that vanishes takes a piece of your agent with it, and the change arrives silently. Watch this server and every such change lands in your inbox.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 7 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add nodehour --transport http https://nodehour.forevenza.com/mcp

Settings → Connectors → Add custom connector, then paste this address

https://nodehour.forevenza.com/mcp

~/.codex/config.toml

[mcp_servers.nodehour]
url = "https://nodehour.forevenza.com/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "nodehour": {
      "url": "https://nodehour.forevenza.com/mcp"
    }
  }
}

.vscode/mcp.json

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

Available tools 7

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

accept_offer

Place an order on terms you have inspected and the buyer has authorized you to accept. Requires the exact terms hash and explicit acceptance. Follow inspect_offer later for payment links and verified payment state.

decline

decline_offer

Decline an issued offer on its inspected terms.

describe

describe_business

What Nodehour does, what happens to a request, and the request fields.

inspect

inspect_offer

Read the exact authorized terms, terms hash, order state and processor payment links. Use the offer link credentials, or credentials of the request explicitly linked to this offer.

release

release_payment

Confirm a payment condition only where the inspected order allows the customer to release it. This records approval; it does not pay the processor.

request

request_status

Resume a requirement using the receipt credentials. Read the recorded requirement and any linked offers. Contact details are kept apart.

submit

submit_request

Send a requirement to Nodehour. It is kept with a reference number. You get a reference number at once, and we keep exactly what you sent: your words, the proposed configuration, the terms to quote and the open questions. If sizing or an open question changes the quote we email you first; then we take the configuration to providers that can run it, ask each to quote the same terms, and send the options side by side to the address you left. Without an address no one can reply, and nothing goes to providers until you add one. Nothing is priced, held or ordered until you accept an option's terms with the provider. Contact details are deleted after 180 days.

Tools removed

Tools this server used to expose. Anything built against them stopped working on the day they went.

describe_proposition

removed 5 Nov 2026

list_propositions

removed 5 Nov 2026

Endpoints

URL	Transport	State	Latency	Checked
https://nodehour.forevenza.com/mcp	streamable-http	answering	365 ms	7 min ago

Alternatives to Nodehour: GPU capacity sized from your run and quoted by providers

same job, measured the same way

Sendable

by sendable

Send transactional email from your editor — describe the event, Sendable writes and sends it.

44 installs/wk local only

OCOLO Project Requests

by ocolo-www

Submit a data center colocation requirement to OCOLO; reaches 270+ providers. Email-verified.

3 tools answering

Proxy Mail QA

by proxymail

Test inboxes for your app's sign-up and login emails: get the code or link, or why none came.

answering

Dilohost

by dilohost

Hosting run by your AI agent: publish websites, apps, databases, domains and email from chat.

answering

Lanetti

by lanetti

Run your Lanetti hosting from your AI agent: domains, DNS, sites, email, apps, backups and billing.

answering

Enhanciar — company brain

by enhanciar

Ask your company's Slack, Gmail, Drive, Notion, Jira and code from any MCP client, with sources.

12 tools answering

Fiber AI

by fiber

Search companies, enrich contacts, and reveal emails and phones from your AI agent.

5 tools answering

NumeroClaw

by numeroclaw

Order a personalized numerology reading, paid by the person and delivered by email.

3 tools answering

Nodehour: GPU capacity sized from your run and quoted by providers — questions

Answers built from our own checks of this server.

What can Nodehour: GPU capacity sized from your run and quoted by providers do?

It exposes 7 tools, read directly from the server on our last check. Among them: accept_offer, decline_offer, describe_business, inspect_offer, release_payment, request_status and 1 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is Nodehour: GPU capacity sized from your run and quoted by providers working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 436 ms. The bar chart above shows every period we have measured.

Did Nodehour: GPU capacity sized from your run and quoted by providers ever remove tools?

Yes. describe_proposition, list_propositions are no longer exposed — we recorded the date each one disappeared. A tool vanishing usually means a breaking change for anything that depended on it.

How do I connect Nodehour: GPU capacity sized from your run and quoted by providers?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does Nodehour: GPU capacity sized from your run and quoted by providers need an API key?

No. Nodehour: GPU capacity sized from your run and quoted by providers completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 7 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is Nodehour: GPU capacity sized from your run and quoted by providers?

It answers our handshake in 436 ms on average, which is faster than 29% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.