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.

FastGPU

REMOTE · FASTGPU.CO · SCANNED SEP 20

Compare live GPU cloud rental prices and match workloads to the cheapest provider.

Available components

+3 this week 82 Trust /100
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 Security80
Transport & Reachability100
Schema Quality & AI Usability62
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 466 tokens (~233/item across 2 items; 2 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 Management80
  • Stability observed for 24 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 2 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 3 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the FastGPU MCP server?

FastGPU is a hosted endpoint at https://fastgpu.co/api/mcp, 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 · fastgpu.co

# add to Claude Code
claude mcp add --transport http co-fastgpu-fastgpu 'https://fastgpu.co/api/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "co-fastgpu-fastgpu": {
      "url": "https://fastgpu.co/api/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "co-fastgpu-fastgpu": {
      "type": "http",
      "url": "https://fastgpu.co/api/mcp"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.co-fastgpu-fastgpu]
url = "https://fastgpu.co/api/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "co-fastgpu-fastgpu": {
      "type": "remote",
      "url": "https://fastgpu.co/api/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add co-fastgpu-fastgpu --url 'https://fastgpu.co/api/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  co-fastgpu-fastgpu:
    url: "https://fastgpu.co/api/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "co-fastgpu-fastgpu": {
      "Transport": "http",
      "Url": "https://fastgpu.co/api/mcp"
    }
  }
}
# add to Vellum
assistant mcp add co-fastgpu-fastgpu -t streamable-http -u 'https://fastgpu.co/api/mcp'
// mcp.json
{
  "mcpServers": {
    "co-fastgpu-fastgpu": {
      "type": "http",
      "url": "https://fastgpu.co/api/mcp"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

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.

  • 19 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

  • 14 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

  • 12 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

  • 11 Sept 26 0
    • “match_workload” reworded the description of “gpu_count” cosmetic

    1 cosmetic change on this day. Switch on “Show cosmetic changes” to see it.

  • 10 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

  • 7 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

  • 5 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

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 20 Sept 2026 · Probed https://fastgpu.co/api/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=fastgpu.co CN=YR2,O=Let's Encrypt,C=US 29 Jul 2026 27 Oct 2026 RSA 2048 SHA256-RSA 57b43bdf39d92351db454c1376f9d83df82
SANs: fastgpu.co
CN=YR2,O=Let's Encrypt,C=US (CA) CN=Root YR,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 RSA 2048 SHA256-RSA 4ebd24947e24d394802d84a52fd5b319
CN=Root YR,O=ISRG,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 RSA 4096 SHA256-RSA f24b6d17f9d9ad7cb1c9fea78782699f

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of fastgpu.co. Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
co. present 7786 8 Verified
fastgpu.co. absent 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
Header Value
strict-transport-security max-age=31536000; includeSubDomains
content-security-policy default-src 'self'; script-src 'self' 'unsafe-inline' 'unsafe-eval' https://js.stripe.com https://platform.twitter.com https://www.googletagmanager.com; style-src 'self' 'unsafe-inline' https://fonts.googleapis.com; img-src 'self' data: blob: https:; media-src 'self' https: blob:; font-src 'self' https://fonts.gstatic.com; connect-src 'self' https://*.supabase.co wss://*.supabase.co https://api.stripe.com https://www.google-analytics.com https://*.google-analytics.com https://*.analytics.google.com https://www.googletagmanager.com; worker-src 'self' blob:; frame-src 'self' https://js.stripe.com https://hooks.stripe.com https://www.youtube-nocookie.com https://www.youtube.com https://player.vimeo.com https://www.loom.com https://www.dailymotion.com https://platform.twitter.com; frame-ancestors 'self' http://localhost:* https://o-mega.ai https://*.o-mega.ai https://founden.ai https://*.founden.ai https://*.founden.co https://*.e2b.app https://*.vercel.app; object-src 'none'; base-uri 'self'
x-content-type-options nosniff
referrer-policy strict-origin-when-cross-origin
permissions-policy camera=(), microphone=(), geolocation=(), browsing-topics=()

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://fastgpu.co/api/mcp Verified 200
http (plaintext) http://fastgpu.co/api/mcp HTTPS enforced 308 https://fastgpu.co/api/mcp
MCP tools · 2 exposed · ~433 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
list_gpu_prices ~72

One entry per GPU model with the current cheapest live rental price across the whole market (RunPod, Vast.ai, Lambda, hyperscalers and more). No key required. Use this to compare GPU prices.

NameTypeReqDescription
tierstringFilter by tier.
vendorstringFilter by GPU vendor.
NameTypeReqDescription
countintegeryes
gpusarrayyes
staleboolean
updated_atstring|null

No examples provided.

match_workload ~361

The routing DECISION: describe a job (a model, size, or GPU need) and get the ranked, reasoned recommendation for the cheapest place to run it across the live market, with the required VRAM, GPU count, effective $/hr, and how much cheaper it is than a hyperscaler. No key required. Results mirror the site and apply a small, disclosed partner tie-break between otherwise-equal offers (each match reports partner true/false).

NameTypeReqDescription
budget_usd_hrnumberOnly recommend configs at or under this hourly budget.
gpu_countintegerExact positive GPU count. Overrides a count in query text. Returns no matches if no supported configuration fits; omit for automatic sizing.
modelstringOpen model name to size against, e.g. "Llama 3 70B", "Qwen 72B", "Mixtral".
params_bnumberModel size in billions of parameters when no exact model is named.
precisionstringNumeric precision to size the model at.
querystringPlain-language job, e.g. "cheapest to serve Llama 3 70B" or "2x H100 for fine-tuning". Provide this OR a structured spec below.
regionstringRestrict to a data-residency region.
reservedstringSet true to include reserved / committed-term capacity for a lower rate.
spotstringSet true to include interruptible spot capacity for a cheaper rate.
taskstringWhat the job does.
vram_gbintegerRough VRAM the job needs, in GB, if you already know it.
NameTypeReqDescription
countintegeryes
heroobject|null
matchesarrayyes
staleboolean
updated_atstring|null
workloadobject

No examples provided.

Common questions

What is the FastGPU MCP server?

FastGPU is an MCP server listed in the public MCP registry as co.fastgpu/fastgpu. Compare live GPU cloud rental prices and match workloads to the cheapest provider. This page covers its hosted endpoint (https://fastgpu.co/api/mcp).

Is the FastGPU MCP server safe to use?

FastGPU scores 82 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 FastGPU MCP server expose?

FastGPU exposes 2 tools: list_gpu_prices, match_workload. Their descriptions and schemas cost roughly 433 tokens of context every time the server is loaded.

Does the FastGPU MCP server require authentication?

No. We connected to FastGPU without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the FastGPU MCP server still maintained?

FastGPU is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.