Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

GridHop GPU Price & Carbon Index

REMOTE · GRIDHOP.DEV

Live GPU rental prices on AWS, Azure, Google Cloud, Vast.ai, RunPod, Lambda and more, with carbon.

Available components

71 Trust /100

Last scanned (15 hours ago)

Scores higher than 56% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Cloud Infrastructure

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security74
  • The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
  • No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation. See how to fix → View diagnostics → Partial
  • HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
  • HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
  • DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
Schema Quality & AI Usability59
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1507 tokens (~376/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management20
  • Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
What we tested

Checks we ran (13)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Nov 26 +1
    • Tool “find_offers” rewrote its description, which is the text the model reads security
    • Schema quality: 332 → 376 ▼ functional
    • Server version: 0.11.0 → 0.11.1 functional
    • Server version: 0.9.0 → 0.11.0 functional
    • “find_offers” added an optional parameter “continents” cosmetic
    • “find_offers” added an optional parameter “us_states” cosmetic
    • “find_offers” reworded the description of “providers” cosmetic
    • “find_offers” reworded the description of “region_filter” cosmetic
  • 19 Nov 26 0
    • Server version: 0.8.0 → 0.9.0 functional
  • 18 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Nov 26 0
    • Tool “find_offers” rewrote its description, which is the text the model reads security
    • Server version: 0.7.0 → 0.8.0 functional
    • “find_offers” reworded the description of “providers” cosmetic
  • 16 Nov 26 +1
    • Tool “find_offers” rewrote its description, which is the text the model reads security
    • Tool coverage: 95% → 100% ▲ functional
    • Stability: unverified → 0.03 ▲ functional
    • Schema quality: good → excellent functional
    • Server version: 0.6.1 → 0.7.0 functional
    • Server version: 0.6.0 → 0.6.1 functional
    • “find_offers” reworded the description of “providers” cosmetic
    • “grid_carbon” reworded the description of “limit” cosmetic
  • 15 Nov 26 68

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://gridhop.dev/v1/mcp?src=mcp-registry

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=gridhop.dev CN=WE1,O=Google Trust Services,C=US 15 Nov 2026 13 Feb 2027 ECDSA 256 ECDSA-SHA256 5e6a76cdde9886f7134550fb33bac743
SANs: gridhop.dev
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of gridhop.dev. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
dev. DS published 60074 8 Verified
gridhop.dev. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://gridhop.dev/v1/mcp?src=mcp-registry Verified 200
http (plaintext) http://gridhop.dev/v1/mcp?src=mcp-registry HTTPS enforced 301 https://gridhop.dev/v1/mcp?src=mcp-registry
MCP tools · 4 exposed · ~1,363 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
find_offers ~875

Cheapest GPU machines for rent right now across Vast.ai, RunPod, Nebius, CoreWeave, Lambda, OVHcloud, AWS, Azure and Google Cloud, ranked by price. Returns price per hour, provider, country, tier (datacenter or community host), reliability score, whether the price is interruptible (spot), and grid carbon intensity where an open data feed covers the host's grid (Europe and GB live; US by state or cloud region, a day old). Can filter and sort by carbon. AWS, Azure and Nebius are covered with on-demand prices (providers aws, azure, nebius) and spot prices (aws_spot, azure_spot, nebius_spot); Google Cloud with spot prices only (gcp_spot); CoreWeave with on-demand list prices of whole 8-GPU nodes (coreweave); Lambda and OVHcloud with on-demand list prices (lambda, ovh). Data is refreshed hourly; `observed_at` is the snapshot time. Read-only, free, no account.

NameTypeReqDescription
continentsarray–Only hosts on these continents, e.g. ['europe']. Mexico, Central America and the Caribbean are north_america; Turkey and the Middle East are asia. Combined with region_filter or us_states, a host in…
countinteger–GPUs on one machine
gpu_classstringyesGPU model, e.g. RTX4090, RTX5090, H100, H200, A100_80, A100_40, L40S, A6000, RTX3090, L4, T4. Loose forms like '4090' or 'RTX 4090' work.
include_interruptibleboolean–Omit (default) to get on-demand prices plus AWS, Azure, Google Cloud and Nebius spot, which are real prices for a running machine. true also adds Vast.ai / RunPod minimum bids, which are a floor rath…
limitinteger–Maximum offers returned, in sort_by order. total_matching gives the full count.
max_carbon_g_kwhnumber–Only hosts on a grid at or below this carbon intensity, gCO2eq/kWh. Offers with no carbon value are dropped when this is set.
max_price_hrnumber–Upper bound on USD per hour for the whole machine
min_reliabilitynumber–Drop hosts whose provider reliability score (0..1, Vast.ai only) is below this. Offers with no score are kept. 0 shows every host.
providersarray–Only these providers. Default: all. aws, azure, nebius, coreweave, lambda and ovh are on-demand prices; aws_spot, azure_spot, nebius_spot and gcp_spot are spot prices, so combined with include_interr…
region_filterarray–Only hosts in these ISO 3166-1 alpha-2 countries, e.g. ['US','DE']. Hosts with unknown country are excluded. For a whole continent use continents; for US states use us_states.
sort_bystring–price: cheapest first. carbon: lowest grid carbon intensity first, cheapest within the same grid; offers with no carbon value go last.
tierstring–datacenter keeps only hosts the provider lists as datacenters and drops community hosts (independent hosts on a marketplace)
us_statesarray–Only hosts in these US states, two-letter codes, e.g. ['TX','CA'] (DC counts as a state). Narrows 'US' if region_filter also lists it. Cloud regions are placed in the state the provider documents (AW…
vram_minnumber–Minimum VRAM per GPU, GB
NameTypeReqDescription
alternativesarray–Only when the class asked for is a consumer card that no cloud rents out (RTX 4090, 5090, 3090: marketplaces only) and the search asked for a cloud provider, or for a datacenter and found none: datac…
notestring––
observed_atstring|nullyesUTC time of the price snapshot (ISO 8601)
offersarrayyes–
sourcesstring–Data sources and attribution
total_matchingintegeryesOffers matching the filters before `limit`
warningsarrayyes–

No examples provided.

grid_carbon ~215

How clean and how expensive the electricity is on the power grids GPU hosts sit on (Europe, Great Britain, the US): carbon intensity now, its low and high over the last 24 hours and when, the hour of day that is usually cleanest, the day-ahead wholesale power price now and the cheapest hour in the next 24. Use it to choose where or when to run a job that can wait. The grid_zone values match the grid_zone on find_offers results.

NameTypeReqDescription
grid_zonestring–One grid by id, e.g. SE-SE3, DE, US-TEX-ERCO
limitinteger–Maximum number of grids to return, after sorting. total_matching says how many there are in all.
region_filterarray–Only grids in these ISO 3166-1 alpha-2 countries, e.g. ['SE','NO']
sort_bystring–carbon: cleanest first. power_price: cheapest day-ahead price first.
NameTypeReqDescription
notestring––
snapshotstring|nullyesHour the readings refer to, UTC
sourcesstring––
total_matchingintegeryes–
warningsarrayyes–
zonesarrayyes–

No examples provided.

list_gpus ~94

Every GPU class in the current snapshot: VRAM, how many offers and which providers have it, the machine sizes (GPU counts) listed, and the cheapest on-demand and spot price per GPU. Use it to see what exists before calling find_offers, or to pick a class by VRAM and price.

NameTypeReqDescription
vram_minnumber–Only classes with at least this much VRAM per GPU, GB
NameTypeReqDescription
gpusarrayyesCheapest on-demand first; classes with spot prices only come last
notestring––
observed_atstring|nullyesUTC time of the price snapshot

No examples provided.

price_history ~179

How the cheapest rental price of one GPU class has moved: one point per day since 1 November 2026 (snapshots are hourly from 10 November; earlier days have only a few), or one per hour for the last three days. For each point: the cheapest on-demand price seen, the typical cheapest (median across the day's hourly snapshots) and the cheapest cloud spot price, per GPU. Use it to judge whether a price is unusually low or high before renting, or how much waiting could save.

NameTypeReqDescription
daysinteger–How far back, in days (hourly: at most 3)
gpu_classstringyesGPU model, as for find_offers: RTX4090, H100, A100_80, L4 ...
granularitystring–hourly covers the last 72 hours
NameTypeReqDescription
granularitystringyes–
notestring––
observed_atstring|nullyes–
seriesarrayyesOne entry per matching class (H100 matches the SXM, PCIe and NVL variants)
unitstring––
warningsarrayyes–

No examples provided.

Install

How do I install the GridHop GPU Price & Carbon Index MCP server?

GridHop GPU Price & Carbon Index is a hosted endpoint at https://gridhop.dev/v1/mcp?src=mcp-registry, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · gridhop.dev

# add to Claude Code
claude mcp add --transport http gridhopai-gpu-price-index 'https://gridhop.dev/v1/mcp?src=mcp-registry'
Common questions

What is the GridHop GPU Price & Carbon Index MCP server?

GridHop GPU Price & Carbon Index is an MCP server listed in the public MCP registry as io.github.gridhopai/gpu-price-index. Live GPU rental prices on AWS, Azure, Google Cloud, Vast.ai, RunPod, Lambda and more, with carbon. This page covers its hosted endpoint (https://gridhop.dev/v1/mcp?src=mcp-registry).

Is the GridHop GPU Price & Carbon Index MCP server safe to use?

GridHop GPU Price & Carbon Index scores 71 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the GridHop GPU Price & Carbon Index MCP server expose?

GridHop GPU Price & Carbon Index exposes 4 tools: find_offers, list_gpus, price_history, grid_carbon. Their descriptions and schemas cost roughly 1,363 tokens of context every time the server is loaded.

Does the GridHop GPU Price & Carbon Index MCP server require authentication?

No. We connected to GridHop GPU Price & Carbon Index without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the GridHop GPU Price & Carbon Index MCP server still maintained?

GridHop GPU Price & Carbon Index is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the GridHop GPU Price & Carbon Index MCP server?

VerifyMCP ran 13 checks on GridHop GPU Price & Carbon Index, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.