Skip to content

compute.pangle.online — GPU rental market MCP server

online.pangle.compute/gpu-rental-marketcompute.pangle.onlinestreamable-httpv1.2.0Scanned

Live GPU rental market: 2,500+ offers across a dozen provider feeds. History, watches, limit orders.

25 tools: 3 can delete or cancel things, 17 change things and 5 only read.

Tools: 3 delete, 0 irreversible, 17 write, 5 read.
  • Reads private data · 1
  • Reads text others write · 0
  • Can send data out · 2
  • 1 finding, 1 high

Tools listed without sign-in. Remote posture

With Anlyon

3 tools here can delete or cancel things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the compute.pangle.online — GPU rental market MCP server can do

The compute.pangle.online — GPU rental market MCP server is published by compute.pangle.online, a domain the MCP Registry verified. It has 25 tools. It can delete or cancel things (3 tools: delete_watch, cancel_limit_order and destroy_rental) and create or change data (17 tools: market_stats, price_history, idle_history, best_value and 13 more). 5 tools only read.

1 tool reads private data (limit_order_status); 2 tools can send data out of your system (create_watch and create_limit_order).

The fixed checks matched 1 finding, 1 of them high severity (sensitive-path). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 18, 2026, version 1.2.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

25 tools

Deletes or cancels 3Claude Code: deny
  • cancel_limit_orderCancel a limit order.No findings

    Why it is in this group

    • The name "cancel_limit_order" says "cancel": a word for removing or ending something.
    Description, as the server wrote it
    Cancel a limit order. Requires the order_secret from create_limit_order.
  • delete_watchDelete a watch by id.No findings

    Why it is in this group

    • The name "delete_watch" says "delete": a word for removing or ending something.
    Description, as the server wrote it
    Delete a watch by id.
  • destroy_rentalDestroy an instance previously placed on your account (vast or runpod).No findings

    Why it is in this group

    • The name "destroy_rental" says "destroy": a word for removing or ending something.
    Description, as the server wrote it
    Destroy an instance previously placed on your account (vast or runpod). Your key passes through and is never stored.
Changes things 17Claude Code: ask
  • account_usageYour metered usage ledger: placements, destroys, estimated hours and USD, and the platform fee (2.5%, $0.01 min, $5.00 cap per lease per UTC day) priced at the rate live at event t…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Your metered usage ledger: placements, destroys, estimated hours and USD, and the platform fee (2.5%, $0.01 min, $5.00 cap per lease per UTC day) priced at the rate live at event time. Distinct from fee_bps, the display markup.
  • best_valuePerf-per-dollar board: for each GPU model, best live price vs its FP16 tensor throughput (dense, vendor spec sheets) -> TFLOPS per dollar-hour.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Perf-per-dollar board: for each GPU model, best live price vs its FP16 tensor throughput (dense, vendor spec sheets) -> TFLOPS per dollar-hour. The answer to 'most compute for my budget' rather than 'cheapest card'. Models without a defensible public spec figure are listed as unrated.
  • create_limit_orderPlace a standing LIMIT ORDER: when the best live fee-adjusted price for gpu (and optional offer_class) trades at or under max_price_per_gpu_hr, the station cuts a signed FILL TICKE…Can send data outNo findings

    Why it is in this group

    • The name "create_limit_order" says "create": a word for a change.

    What it can reach

    • outboundThe input takes a URL (input.webhook_url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Place a standing LIMIT ORDER: when the best live fee-adjusted price for gpu (and optional offer_class) trades at or under max_price_per_gpu_hr, the station cuts a signed FILL TICKET naming the exact offer. The station never holds your provider key — the ticket is executed by whoever does: the open-source keyholder sidecar (/agents/#sidecar), your own agent long-polling POST /api/orders/{id}/ticket, or a human with curl. Returns the order with order_secret SHOWN ONCE — it authenticates ticket reads and the fill call for this order only and can rent nothing by itself. Triggers are checked on the poll cadence (~5-min bars, not tick-by-tick); orders expire in 30 days; a ticket lasts ~4 minutes then the order re-arms. standing=true makes it a STANDING order — compute that survives: after a live fill the sidecar keeps watching the machine, and when it is preempted or dies the order re-arms and refills from the CURRENT best offer, up to max_refills times with cooloff_seconds between death and refill. Honest limits: this re-provisions the MACHINE, not the WORK (GPU memory is not portable — resume from your own checkpoints); refills need your sidecar alive (it is both witness and executor); cancelling stops supervision but cannot destroy a running machine (the station holds no key). Watchdog: spend_alert_usd / age_alert_hours fire a "still yours?" webhook once per machine when the spend ESTIMATE (uptime x price; the provider's bill is authoritative) or age crosses your line — auto_destroy_budget_usd remains the hard stop.
  • create_watchCreate a price watch (tripwire): fires when the best live fee-adjusted price per GPU-hour matching gpu (and optional offer_class) drops to or under max_price_per_gpu_hr.Can send data outNo findings

    Why it is in this group

    • The name "create_watch" says "create": a word for a change.

    What it can reach

    • outboundThe input takes a URL (input.webhook_url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Create a price watch (tripwire): fires when the best live fee-adjusted price per GPU-hour matching gpu (and optional offer_class) drops to or under max_price_per_gpu_hr. Checked every poll (~5 min). Returns the watch with its id — the id is the only key; poll it with watch_status, or give a public webhook_url to be POSTed on each trip. Watches re-arm when the price climbs 2% back over the line.
  • fill_limit_orderExecute a limit order's live fill ticket on YOUR provider key (used for this one call, never stored).No findings

    Why it is in this group

    • The name "fill_limit_order" says "fill": a word for a change.
    Description, as the server wrote it
    Execute a limit order's live fill ticket on YOUR provider key (used for this one call, never stored). Only works while the order is ticketed; the offer is re-quoted live and refused above the order's line. Idempotent per order — a retry returns the first receipt rather than renting a second machine. The order's auto_destroy_budget_usd (if set) arms the budget guard exactly as rent_offer does.
  • idle_historyThe idle-capacity index over time: share of listed GPU capacity that is interruptible (spot/bid) — idle hardware looking for work.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    The idle-capacity index over time: share of listed GPU capacity that is interruptible (spot/bid) — idle hardware looking for work. Points are [ts, idle_share, idle_offers, total_offers].
  • market_statsLive market snapshot: total offers, GPU models, idle-capacity share, per-provider freshness/health, cheapest price per model, current fee_bps.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Live market snapshot: total offers, GPU models, idle-capacity share, per-provider freshness/health, cheapest price per model, current fee_bps.
  • price_historyPrice history for one GPU model (exact name from search_offers/market_stats, e.g.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Price history for one GPU model (exact name from search_offers/market_stats, e.g. 'RTX 4090'). offer_class: on_demand | interruptible. Returns per-provider series of [ts, min_price_per_gpu_hr, median_price_per_gpu_hr, offer_count]; ranges past 3 days are bucketed (hourly, then 6-hourly past a week).
  • price_positionRent-now-or-wait context: where the current best price for one GPU model sits inside its own trailing 7/30-day range (percentile, 24h trend, verdict).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Rent-now-or-wait context: where the current best price for one GPU model sits inside its own trailing 7/30-day range (percentile, 24h trend, verdict). Descriptive, not a forecast.
  • provider_reliabilityHow dependable each provider's data feed has been for this station (poll success over the trailing window), plus the provider's own average machine reliability where reported.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    How dependable each provider's data feed has been for this station (poll success over the trailing window), plus the provider's own average machine reliability where reported. feed_score is about the DATA, not their hardware.
  • register_accountCreate a metering account: returns a bearer token (shown once, we keep only a hash).No findings

    Why it is in this group

    • The description's first verb is "create": a word for a change.
    Description, as the server wrote it
    Create a metering account: returns a bearer token (shown once, we keep only a hash). Pass it as account_token on rent calls to build a usage ledger you can read back with account_usage. Optional — renting works without one.
  • rent_bestOne-shot rent: search the live book with these filters and place on the best (cheapest) matching offer — 'cheapest H100 under $2/hr, go'.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    One-shot rent: search the live book with these filters and place on the best (cheapest) matching offer — 'cheapest H100 under $2/hr, go'. Same guarantees as rent_offer (dry-run default, live re-quote, your max_price_per_gpu_hr is absolute). If the best offer is already gone it walks to the next, at most 3, and reports what it skipped.
  • rent_offerPlace a rental on YOUR provider account (BYO key — it is used for this one call and never stored).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Place a rental on YOUR provider account (BYO key — it is used for this one call and never stored). Default is a DRY RUN returning exactly what would be executed; a live placement needs dry_run=false AND confirm=true. The offer is re-quoted live first and refused if its price exceeds max_price_per_gpu_hr. Executes on vast and runpod offers. Pass an idempotency_key so retries return the first receipt instead of renting twice. auto_destroy_budget_usd arms the budget guard: this station then holds your key in PROCESS MEMORY ONLY and destroys the rental when estimated spend reaches the cap (a station restart drops the guard — the receipt says so; poll rental_status as backstop). account_token (from register_account) attributes the rental to your usage ledger.
  • rent_x402Rent a prepaid block of GPU time with a wallet and NO account, NO API key and no human, over x402 (HTTP 402 micropayments, USDC on Base).1 finding

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    Findings

    • High

      The description refers to "id_ed25519.pub".

      Matched text

      description: "...your ssh key (one line, the contents of id_ed25519.pub). It is written into the rented con..."

      What this check looks for
    Description, as the server wrote it
    Rent a prepaid block of GPU time with a wallet and NO account, NO API key and no human, over x402 (HTTP 402 micropayments, USDC on Base). Call it with no arguments and you get the payment challenge: an x402 PaymentRequirementsResponse whose accepts[0].extra.x402_fee states the block price, the platform fee IN DOLLARS, that there are no refunds, and that you are charged only after the lease is live. Sign the EIP-3009 transferWithAuthorization it describes, then call again with x_payment set to the base64 PaymentPayload (the same value the HTTP rail sends as X-PAYMENT). `ssh_pubkey` is HOW YOU GET IN, and is required on the paying call: pass the public half of your ssh key (one line, the contents of id_ed25519.pub). It is written into the rented container's authorized_keys and nowhere else, and the receipt comes back with the host and port to connect to. A block nobody can enter is not sold. `lease_id` is minted by the challenge — send back the one you were given; it is the accrual key for the daily fee cap and this station refuses ids it did not mint or that belong to another payer. `originator` is an OPTIONAL opaque attribution label (<=64 chars, e.g. a handle or a reverse-DNS name) naming the client implementation that produced the fill. It is carried unmodified onto the receipt and onto the public ledger row, and it never affects the price, the fee, verification or settlement — the same block costs the same either way. Returns the receipt on success. Every fill is published at /api/receipts. Wire contract: docs/X402-FEE-0.1.md, frozen as x402-fee/0.1. Note for x402 MCP-transport clients: this tool takes the payment as an ARGUMENT rather than in _meta["x402/payment"]. The payload is byte-identical; only the channel differs, because a tool argument is the one place every MCP client can portably put it. The HTTP rail is fully transport-conformant.
  • spot_spreadOn-demand vs interruptible spread: the live discount for idle capacity per model; pass gpu_model for its history too.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    On-demand vs interruptible spread: the live discount for idle capacity per model; pass gpu_model for its history too.
  • true_cost_notesThe billing fine print behind the $/hr, verified per provider from their own published pages (source URL + date on every claim): billing granularity (per-second vs per-minute), whe…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    The billing fine print behind the $/hr, verified per provider from their own published pages (source URL + date on every claim): billing granularity (per-second vs per-minute), whether storage bills while stopped, bandwidth/egress fees, and the commonly-missed gotchas (e.g. Vast bandwidth never appears in $/hr; RunPod stopped volume disk costs double). Providers we have not verified are listed with NO claims.
  • will_it_fitWill this model fit, and what does a fitting machine cost right now?No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Will this model fit, and what does a fitting machine cost right now? Deterministic VRAM arithmetic — weights (params x bytes/precision) + KV cache (2 x layers x kv_heads x head_dim x context x batch) + stated overhead — checked against the live book, cheapest fitting offers first. Pass a known model slug (llama-3.1-8b/70b/405b, mistral-7b, mixtral-8x7b, qwen2.5-7b/32b/72b, gemma-2-9b/27b) OR params_b for a stated Llama-like guess. precision: fp16/int8/int4. If you pass tokens_per_s (YOUR measured throughput — we never invent one), each offer gains usd_per_m_tokens. Every approximation is in the assumptions list, not fine print.
Only reads 5Show 5 read-only tools
  • get_offerFetch one offer by its id (from search_offers).No findings

    Why it is in this group

    • The name "get_offer" says "get": a word for reading.
    Description, as the server wrote it
    Fetch one offer by its id (from search_offers).
  • limit_order_statusState of a limit order (armed/ticketed/filled/cancelled/expired), last price seen, recent events.Reads private dataNo findings

    Why it is in this group

    • The name "limit_order_status" says "status": a word for reading.

    What it can reach

    • private-dataThe input names a secret (input.order_secret), and the tool reads: it reads secrets.
    Description, as the server wrote it
    State of a limit order (armed/ticketed/filled/cancelled/expired), last price seen, recent events. Pass order_secret to also read the live fill ticket when one is cut.
  • rental_statusLive state of an instance on your account: running/starting/stopped/ gone, uptime, price, estimated spend so far, and the budget guard's state if one is armed.No findings

    Why it is in this group

    • The name "rental_status" says "status": a word for reading.
    Description, as the server wrote it
    Live state of an instance on your account: running/starting/stopped/ gone, uptime, price, estimated spend so far, and the budget guard's state if one is armed. Read-only; your key passes through and is never stored.
  • search_offersSearch live GPU offers.No findings

    Why it is in this group

    • The name "search_offers" says "search": a word for reading.
    Description, as the server wrote it
    Search live GPU offers. gpu matches the model name (e.g. '4090', 'H100'). offer_class: on_demand | interruptible | reserved. country: ISO-2 (e.g. US), a comma list ('DE,NL'), or 'EU' for the 27 member states. min_gpu_count filters to multi-GPU configs (8 = full 8x nodes). region substring-matches the provider's region/datacenter label. Returns offers ranked cheapest-first by price_per_gpu_hr.
  • watch_statusCurrent state of a watch: armed/tripped, last price seen, recent events, and the best matching offer right now.No findings

    Why it is in this group

    • The name "watch_status" says "status": a word for reading.
    Description, as the server wrote it
    Current state of a watch: armed/tripped, last price seen, recent events, and the best matching offer right now.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged untrusted-input.

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out2
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:17 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
20
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 20 tools that change things (3 destructive, 17 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://compute.pangle.online/mcp/: tools/list returned 25 tools to an anonymous client, including delete_watch (destructive), cancel_limit_order (destructive), destroy_rental (destructive), market_stats (write), price_history (write) and 15 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

1 high
  • The description refers to "id_ed25519.pub".

    Matched text

    description: "...your ssh key (one line, the contents of id_ed25519.pub). It is written into the rented con..."

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 1.2.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http gpu-rental-market https://compute.pangle.online/mcp/
claude mcp add --transport http gpu-rental-market https://compute.pangle.online/mcp/

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__gpu-rental-market__search_offers",
      "mcp__gpu-rental-market__get_offer",
      "mcp__gpu-rental-market__watch_status",
      "mcp__gpu-rental-market__limit_order_status",
      "mcp__gpu-rental-market__rental_status"
    ],
    "ask": [
      "mcp__gpu-rental-market__market_stats",
      "mcp__gpu-rental-market__price_history",
      "mcp__gpu-rental-market__idle_history",
      "mcp__gpu-rental-market__best_value",
      "mcp__gpu-rental-market__provider_reliability",
      "mcp__gpu-rental-market__price_position",
      "mcp__gpu-rental-market__spot_spread",
      "mcp__gpu-rental-market__will_it_fit",
      "mcp__gpu-rental-market__true_cost_notes",
      "mcp__gpu-rental-market__register_account",
      "mcp__gpu-rental-market__account_usage",
      "mcp__gpu-rental-market__create_watch",
      "mcp__gpu-rental-market__create_limit_order",
      "mcp__gpu-rental-market__rent_x402",
      "mcp__gpu-rental-market__rent_offer",
      "mcp__gpu-rental-market__rent_best",
      "mcp__gpu-rental-market__fill_limit_order"
    ],
    "deny": [
      "mcp__gpu-rental-market__delete_watch",
      "mcp__gpu-rental-market__cancel_limit_order",
      "mcp__gpu-rental-market__destroy_rental"
    ]
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as gpu-rental-market. Review it before you use it.

Capability tags behind 3 rules
  • mcp__gpu-rental-market__create_watch outbound
  • mcp__gpu-rental-market__create_limit_order outbound
  • mcp__gpu-rental-market__limit_order_status private-data

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/online.pangle.compute/gpu-rental-market/verify?hash=3f63a3e368b4de62b8b403dc6107cc3402e68084e34761f8cb6e0b0d90feef30" | jq -e '.changed == false'

Pinned hash 3f63a3e368b4, from Nov 18, 2026, 02:17 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/online.pangle.compute/gpu-rental-market/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for online.pangle.compute/gpu-rental-market
[![Anlyon Radar](https://radar.anlyon.com/badge/online.pangle.compute/gpu-rental-market.svg)](https://radar.anlyon.com/servers/online.pangle.compute/gpu-rental-market)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:54 UTC.

compute.pangle.online — GPU rental market MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the compute.pangle.online — GPU rental market MCP server safe?

No scan can promise that. What its definitions show: 25 tools, 20 of which can change, send or delete something, and 1 finding (1 high) from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the compute.pangle.online — GPU rental market MCP server delete data?

Yes. 3 tools can delete, cancel or revoke something: delete_watch, cancel_limit_order and destroy_rental.

Can the compute.pangle.online — GPU rental market MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the compute.pangle.online — GPU rental market MCP server have?

25 tools: 3 destructive, 17 write, 5 read. delete_watch, cancel_limit_order, destroy_rental, market_stats, price_history, idle_history, best_value, provider_reliability and 17 more.

Does the compute.pangle.online — GPU rental market MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the compute.pangle.online — GPU rental market MCP server send data to outside services?

2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): create_watch and create_limit_order.

Has the compute.pangle.online — GPU rental market MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 18, 2026.