AmpleRun GPU rentals
NPM · @AMPLERUN/MCP · 2 COMPONENTS
Find, price, rent and stop GPUs on AmpleRun. Paid in USDC or USDT on Base. Flat 5% fee.
Available components
Last scanned (4 hours ago)
Scores higher than 39% of npm servers
Category Cloud Infrastructure
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security82
- No malware found by supply-chain analysis.Pass
- CVE check failed: a known high-severity CVE affects @modelcontextprotocol/server 2.1.0, a direct dependency. A fixed version is available. View diagnostics → Fail
- No install/post-install scripts declared.Pass
- 1 of 23 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency19
- Repository check failed: no source repository is declared. See how to fix → View diagnostics → Fail
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 36 days ago).Pass
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability69
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 2198 tokens (~183/item across 12 items; 12 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 Coverage98
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 94% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 12 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 13 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
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.
- 5 Nov 26 −3
- Stability: pass → 0.80 functional
- 30 Oct 26 +1
- Stability: 0.97 → pass security
- 28 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 26 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 24 Oct 26 +1
- CVE-2023-54404 affects this package: high ▼ security
- 22 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.
- 21 Oct 26 −5
- CVE-2026-111768 affects this package: high ▼ security
- CVE-2026-111771 affects this package: high ▼ security
- CVE-2026-111770 affects this package: high ▼ security
- Known CVEs: pass → fail ▼ security
- 19 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.
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 5 Nov 2026 · Analysed npm/@amplerun/mcp@0.1.1
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Vulnerabilities 4 findings
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-46jr-4wx8-v453 | CVE-2026-111768 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| GHSA-jm63-cq47-j5jp | CVE-2026-111770 | high | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:L/A:H | yes |
| GHSA-rvq5-wwqv-78pq | CVE-2026-111771 | medium | CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:N | yes |
| GHSA-mrhx-c7xc-m3w5 | CVE-2023-54404 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
Background: What a vulnerability scan can and cannot prove →
Dependencies 23 packages
| Packages resolved | 23 |
|---|---|
| No linked repository | 1 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
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 →
create_rental Rent a GPU (spends balance) ~331
Rent a GPU on AmpleRun: quotes the template on the offer and reserves the machine in one step, holding up to budget_micro from the account balance. budget_micro is required and is a hard cap: the rental is never charged more, and metering starts only once the machine is verified ready. Returns rental_id, state, the quote, fee_split and the idempotency_key used; retrying with the same idempotency_key never creates a second rental. get_rental reports state and access. Spends money. Write tool: refused unless the server was started with AMPLERUN_MCP_ALLOW_SPEND=1 (the default is read-only).
| Name | Type | Req | Description |
|---|---|---|---|
| asset | string | – | Balance to pay from. USDC when omitted. |
| budget_micro | string | yes | Spending cap in micro-units of the asset ("1000000" = 1 USDC). The rental is never charged more than this. |
| duration_limit_s | integer | yes | Maximum runtime in seconds (60 to 31536000), e.g. 7200 for two hours. |
| idempotency_key | string | – | UUID that makes retries safe. Generated when omitted and returned in the result. |
| offer_id | string | yes | offer_id from search_offers. |
| ssh_public_key | string | yes | One-line OpenSSH public key (the .pub file), e.g. "ssh-ed25519 AAAA... you@laptop". Installed for SSH access. |
| template | string | yes | Template slug such as "pytorch-cuda", or its id (UUID), from list_templates. |
No output schema declared.
No examples provided.
get_agent_account_challenge Start registering this agent's own AmpleRun account ~119
Step 1 of 2. Returns an EIP-4361 (Sign-In with Ethereum) message for a wallet address this agent controls, valid five minutes, single use. Signing it accepts the AmpleRun Terms version it names. Sign the message exactly as returned with personal_sign (EIP-191), then call register_agent_account with message and signature. Never send a private key to any tool.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | – | The agent's wallet address (0x...). Defaults to this server's wallet when it has one. |
No output schema declared.
No examples provided.
get_balance Get account balance ~66
Get the AmpleRun account's USDC and USDT balances as micro-unit strings: spendable (available for new rentals), held by live rentals, pending, disputed and withdrawable, plus the last 30 days' spend. Read-only; needs AMPLERUN_API_KEY.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_quote Get a rental quote ~236
Price a rental without committing: creates a free, non-binding AmpleRun quote (valid 60 seconds; nothing is reserved or charged) for a template on an offer, capped by budget_micro. Returns the quote exactly as the API sent it plus fee_split: the most the rental can cost and how that divides into the platform fee (platform_fee_bps) and the host's share. Needs AMPLERUN_API_KEY with the renter scope. create_rental quotes again when it reserves, so this step is optional.
| Name | Type | Req | Description |
|---|---|---|---|
| asset | string | – | Balance to pay from. USDC when omitted. |
| budget_micro | string | yes | Spending cap in micro-units of the asset ("1000000" = 1 USDC). The rental is never charged more than this. |
| duration_limit_s | integer | yes | Maximum runtime in seconds (60 to 31536000), e.g. 7200 for two hours. |
| offer_id | string | yes | offer_id from search_offers. |
| template | string | yes | Template slug such as "pytorch-cuda", or its id (UUID), from list_templates. |
No output schema declared.
No examples provided.
get_rental Get rental status and access ~114
Get one AmpleRun rental by rental_id: state, cumulative charge (micro-units), rate and funded-through time. While it is RUNNING (verified ready), and read-only for a limited window after STOPPED, also returns access: endpoints, SSH host-key fingerprint, a ready-made command and, for model templates, the endpoint's per-rental API key. Read-only. list_rentals finds rental ids.
| Name | Type | Req | Description |
|---|---|---|---|
| rental_id | string | yes | rental_id from create_rental or list_rentals. |
No output schema declared.
No examples provided.
host_this_machine Earn with this machine's GPU ~90
Explains how to add the GPU of the machine this agent runs on to AmpleRun, so its owner earns from rentals. Returns the one-line installer command, the steps and the earnings links. It runs nothing itself. The installer needs root, so ask the machine's owner before running it, and the owner must approve the machine from the approve_url it prints: nothing is listed without that approval.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_rentals List my rentals ~90
List the account's AmpleRun rentals with state, charge so far (micro-units), rate and funded-through time. Ordered by id, not by time; page with next_cursor. Read-only. get_rental gives details and access for one rental.
| Name | Type | Req | Description |
|---|---|---|---|
| cursor | string | – | next_cursor from the previous page. |
| limit | integer | – | Page size, 1 to 100. |
No output schema declared.
No examples provided.
list_templates List GPU templates ~175
List published AmpleRun templates: pinned container images a rental runs, such as an inference server with fixed model weights or a PyTorch or Jupyter runtime. Returns each template's id, slug (template_id), name, kind, engine, minimum VRAM in bytes and minimum GPU count, plus next_cursor. Read-only; no API key needed. search_offers finds machines for a template.
| Name | Type | Req | Description |
|---|---|---|---|
| cursor | string | – | next_cursor from the previous page. |
| gpu_vram_gib | integer | – | Only templates that fit on a GPU with this much VRAM, in GiB (e.g. 24). |
| kind | string | – | model: an inference server with pinned weights; classical: a general runtime; custom: other images. |
| limit | integer | – | Page size, 1 to 100. |
No output schema declared.
No examples provided.
register_agent_account Register this agent's own AmpleRun account ~152
Step 2 of 2. Opens an AmpleRun account for this AI agent, tagged as agent-created, with its wallet as the verified payout wallet, and returns an API key (shown once; keep it secret). The same wallet again returns the same account and a new key. There is no free credit: renting needs a deposit first. Pass message and signature from get_agent_account_challenge. scopes defaults to ["renter"]; add "host" to host machines.
| Name | Type | Req | Description |
|---|---|---|---|
| agent | object | yes | – |
| message | string | – | The challenge message, exactly as returned. |
| scopes | array | – | – |
| signature | string | – | 0x-prefixed EIP-191 signature of message. |
No output schema declared.
No examples provided.
search_offers Search GPU offers ~314
Search GPU machines that can be rented now on AmpleRun. gpu_model, gpu_count and max_rate_micro_per_hour filter on the server. min_vram_gib and region filter each fetched page here because the API has no such filters, so a page can return fewer than limit matches: scanned is how many offers were checked, and next_cursor continues. Prices are micro-units per hour for the whole machine, fee included; cheapest first. With template, each offer carries fit {fits, reason}. Read-only; no API key needed.
| Name | Type | Req | Description |
|---|---|---|---|
| cursor | string | – | next_cursor from the previous page. |
| gpu_count | integer | – | Minimum number of GPUs in the machine. |
| gpu_model | string | – | Case-insensitive part of the GPU model name, e.g. "4090" or "A100". |
| limit | integer | – | Page size, 1 to 100. |
| max_rate_micro_per_hour | string | – | Highest machine price per hour in micro-units, e.g. "500000" for 0.50 USDC/h. |
| min_vram_gib | integer | – | Minimum VRAM per GPU in GiB. Offers with unmeasured VRAM are excluded. |
| region | string | – | Case-insensitive part of the host's cloud region, e.g. "us-east". Offers without a reported region are excluded. |
| template | string | – | Template slug such as "pytorch-cuda", or its id (UUID), from list_templates. |
No output schema declared.
No examples provided.
stop_rental Stop a rental ~137
Stop an AmpleRun rental: ends the workload and its metering. Files inside the machine stay reachable read-only only for a limited retrieval window. Stopping again is harmless. Returns rental_id and the new state (STOPPING or a later state). Write tool: refused unless the server was started with AMPLERUN_MCP_ALLOW_SPEND=1 (the default is read-only).
| Name | Type | Req | Description |
|---|---|---|---|
| idempotency_key | string | – | UUID that makes retries safe. Generated when omitted. |
| reason | string | – | Recorded with the stop. |
| rental_id | string | yes | rental_id from create_rental or list_rentals. |
No output schema declared.
No examples provided.
top_up Get top-up payment instructions ~160
Get what it takes to top up the AmpleRun USDC balance by amount_micro with x402: the payment requirements (network, USDC contract, treasury payTo, amount, EIP-712 domain). A wallet signs them as an EIP-3009 transferWithAuthorization and repeats POST /api/v1/billing/x402/top-up with the PAYMENT-SIGNATURE header (@amplerun/sdk does this with its x402 option). This server holds no wallet, so it pays nothing; an operator who configures AMPLERUN_MCP_WALLET_KEY_FILE and allows spending lets it pay.
| Name | Type | Req | Description |
|---|---|---|---|
| amount_micro | string | yes | Top-up amount in micro-USDC, e.g. "5000000" for 5 USDC. |
No output schema declared.
No examples provided.
How do I install the AmpleRun GPU rentals MCP server?
AmpleRun GPU rentals runs locally as an npm package, launched with npx -y @amplerun/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @amplerun/mcp
claude mcp add com-amplerun-gpu-rentals -- npx -y @amplerun/mcp
What is the AmpleRun GPU rentals MCP server?
AmpleRun GPU rentals is an MCP server listed in the public MCP registry as com.amplerun/gpu-rentals. Find, price, rent and stop GPUs on AmpleRun. Paid in USDC or USDT on Base. Flat 5% fee. This page covers its npm package (@amplerun/mcp).
Is the AmpleRun GPU rentals MCP server safe to use?
AmpleRun GPU rentals scores 70 out of 100 on VerifyMCP. We recorded 4 known advisories against it as of 5 November 2026. It declares no install or post-install scripts. 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 AmpleRun GPU rentals MCP server expose?
AmpleRun GPU rentals exposes 12 tools: get_agent_account_challenge, register_agent_account, list_templates, search_offers, get_quote, and 7 more. Their descriptions and schemas cost roughly 1,984 tokens of context every time the server is loaded.
Is the AmpleRun GPU rentals MCP server still maintained?
AmpleRun GPU rentals is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the AmpleRun GPU rentals MCP server under?
AmpleRun GPU rentals declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.