# Lantern Works GPU Prices: daily GPU rental price comparison (pypi · lantern-works-deals-mcp)

GPU rental prices checked daily, with price history and change feed; stack optimizer; AI-infra deals

- Trust score: 52/100 (low)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `lantern-works-mcp.lantern-works.workers.dev`: 56/100, [markdown](https://verifymcp.io/servers/connormatthewdouglas-lantern-works-deals/lantern-works-mcp.md), [page](https://verifymcp.io/servers/connormatthewdouglas-lantern-works-deals/lantern-works-mcp)
- pypi · `lantern-works-deals-mcp`: 52/100 (this document), [markdown](https://verifymcp.io/servers/connormatthewdouglas-lantern-works-deals/lantern-works-deals-mcp.md), [page](https://verifymcp.io/servers/connormatthewdouglas-lantern-works-deals/lantern-works-deals-mcp)

## Channel facts

- Registry: `pypi`
- Package: `lantern-works-deals-mcp`
- Version: `0.6.0`
- Transport: `stdio`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Supply Chain Security**: 50/100
  - Malware scan not yet available for this package.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it.
  - 0 of 28 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 1 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 47/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2552 tokens (~283/item across 9 items; 9 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 30/100
  - Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Lantern Works GPU Prices: daily GPU rental price comparison MCP server?

Lantern Works GPU Prices: daily GPU rental price comparison runs locally as a PyPI package, launched with uvx lantern-works-deals-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add connormatthewdouglas-lantern-works-deals -- uvx lantern-works-deals-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "connormatthewdouglas-lantern-works-deals": {
      "command": "uvx",
      "args": [
        "lantern-works-deals-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "connormatthewdouglas-lantern-works-deals": {
      "command": "uvx",
      "args": [
        "lantern-works-deals-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add connormatthewdouglas-lantern-works-deals -- uvx lantern-works-deals-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "connormatthewdouglas-lantern-works-deals": {
      "type": "local",
      "command": [
        "uvx",
        "lantern-works-deals-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add connormatthewdouglas-lantern-works-deals --command uvx --arg lantern-works-deals-mcp
```

### Hermes

```yaml
mcp_servers:
  connormatthewdouglas-lantern-works-deals:
    command: "uvx"
    args: ["lantern-works-deals-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "connormatthewdouglas-lantern-works-deals": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "lantern-works-deals-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add connormatthewdouglas-lantern-works-deals -t stdio -c uvx -a lantern-works-deals-mcp
```

### Other

```json
{
  "mcpServers": {
    "connormatthewdouglas-lantern-works-deals": {
      "command": "uvx",
      "args": [
        "lantern-works-deals-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 52, −15)

- [security regression] Malware scan: pass → unverified

### 2026-11-04 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-03 (score 66, +15)

- [security improvement] Malware scan: unverified → pass
- [functional] Package version: 0.5.5 → 0.6.0

### 2026-11-02 (score 51, −15)

- [security regression] Malware scan: pass → unverified
- [functional regression] Schema quality: 2257 → 2496
- [functional] Package version: 0.3.52 → 0.5.5
- [functional] Package version: 0.3.52 → 0.5.4
- [functional] Package version: 0.3.52 → 0.5.2
- [functional] Package version: 0.3.52 → 0.4.2
- [functional] Package version: 0.3.52 → 0.4.1

### 2026-11-01 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 65, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-10-30 (score 50, +1)

- [security regression] Provenance: fail → unverified
- [functional regression] Schema quality: 256 → 282
- [functional] Package version: 0.3.24 → 0.3.52
- [functional] Package version: 0.3.24 → 0.3.50
- [functional] Package version: 0.3.24 → 0.3.45
- [functional] Package version: 0.3.24 → 0.3.43
- [functional] Package version: 0.3.24 → 0.3.42
- [functional] Package version: 0.3.24 → 0.3.40
- [functional] Package version: 0.3.24 → 0.3.37
- [functional] Package version: 0.3.24 → 0.3.35
- [functional] Package version: 0.3.24 → 0.3.34
- [functional] Package version: 0.3.24 → 0.3.33
- [functional] Package version: 0.3.24 → 0.3.32
- [functional] Package version: 0.3.24 → 0.3.28
- [functional] Package version: 0.3.24 → 0.3.26

### 2026-10-29 (score 49, −1)

- [security regression] Tool safety: pass → unverified
- [security regression] Stability: 0.03 → unverified
- [security improvement] Malware scan: unverified → pass
- [functional regression] Schema quality: 185 → 256
- [functional regression] Schema quality: 185 → 241
- [functional regression] Schema quality: 185 → 229
- [functional regression] Schema quality: 185 → 212
- [functional regression] Schema quality: 1111 → 1350
- [functional regression] Schema quality: 1111 → 1276
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Capabilities: pass → unverified
- [functional] First check of Tool coverage: 100
- [functional] First check of Schema quality: unverified
- [functional] Package version: 0.3.6 → 0.3.24
- [functional] Package version: 0.3.6 → 0.3.19
- [functional] Package version: 0.3.6 → 0.3.17
- [functional] Package version: 0.3.6 → 0.3.16
- [functional] Package version: 0.3.6 → 0.3.14
- [functional] Package version: 0.3.6 → 0.3.12
- [functional] Package version: 0.3.6 → 0.3.10
- [functional] Package version: 0.3.6 → 0.3.8

## MCP tools (9)

### `compare_gpu_prices` (~667 tokens)

Compare tracked GPU rental prices for one model (e.g. 'H100', 'A100 SXM', 'RTX 4090', 'L40S'), cheapest first. If a result looks wrong, give the user its report_issue_url.

Same data as https://thelanternworks.com/api/v1/gpu-prices.json. Sorted by hourly_usd ascending; each result
has source_url and checked_at. 'Cheapest' means cheapest among tracked providers, not the whole market.
limit 1-25. Unknown model returns not_found listing tracked models.
H100/A100: cheapest_by_form_factor gives one pick per form_factor (tier_class, interruptible, in_stock); same rule as the site. 'NVLink' rows are form 'not stated': NVLink is the bridge, and the vendor doesn't say SXM or PCIe.
Each result has tier_class: on-demand | community | marketplace | interruptible (spot/preemptible) |
reserved | dedicated-monthly. Reserved (reservation/commitment 'starting from') rates are left out unless
include_reserved=true, and even then they are never reported as cheapest. DEFAULT on_demand_only=true: results[0] is the cheapest
on-demand rate. Pass on_demand_only=false to include spot/interruptible, community and marketplace capacity (each
such row is labelled by tier_class and interruptible); the summary then names the cheapest on-demand rate when the
overall cheapest isn't. If a model has no on-demand rate, the default falls back to all rates and says so in
on_demand_fallback.
include_history=true adds each result's price_history (daily-snapshot change points) and history.recent_changes
(price changes for this model among tracked providers, last 30 days) from /api/v1/gpu-prices/history.json.
Each result has data_age_hours (hours since its price was last verified), degraded (> 48 h) and stale (> 7 days).
By default a rate whose price is older than 168 h is never ranked or named cheapest: it is listed in stale_prices
('stale price (N days old)'); if every rate is stale, results is empty and the summary says no current cheapest.
max_data_age_hours (optional) replaces the 168 h default and dr…

Input parameters:

- `gpu` (string, required)
- `include_history` (boolean)
- `include_reserved` (boolean)
- `limit` (integer)
- `max_data_age_hours`
- `mode` (string)
- `on_demand_only` (boolean)
- `region`

Output parameters:

- `error` (object)
- `mode` (string)
- `ok` (boolean)
- `results` (array)

### `get_price_changes` (~252 tokens)

GPU rental price changes among tracked providers, each with old/new hourly price, change_pct, direction,
the vendor source_url, a stable event_id (dedupe key) and rate_id.

since: 'YYYY-MM-DD' returns every change on or after that date, newest first (daily snapshots in
/api/v1/gpu-prices/history.json); omitted returns the latest day's moves (/api/v1/gpu-price-changes.json).
cursor: pass next_cursor from a previous call to get every change after it, oldest first, with has_more;
loop until has_more is false, and store next_cursor only after processing (a watcher never misses or repeats
events). error cursor_expired means re-sync with since and dedupe by event_id.
kinds: optional subset of down, up, new, removed, same. gpu: optional model filter (substring, e.g. 'H100').
limit 1-200. Includes data_checked_at and next_refresh_utc (prices refresh daily at about 10:23 UTC).

Input parameters:

- `cursor`
- `gpu`
- `kinds`
- `limit` (integer)
- `mode` (string)
- `since`

Output parameters:

- `changes` (array)
- `error` (object)
- `has_more` (boolean|null)
- `last_seq` (integer|null)
- `mode` (string)
- `next_cursor` (string|null)
- `ok` (boolean)

### `optimize_stack` (~268 tokens)

Cheapest suitable stack among tracked providers for monthly needs (set the quantities you need, rest 0).

scrape_pages: pages/month without JS rendering. scrape_pages_js: pages/month needing JS rendering.
proxy_gb: residential proxy GB/month. emails_sent: transactional emails/month. search_queries: search API
queries/month. gpu_hours: GPU-hours/month (1 GPU), optionally gpu_model e.g. 'H100', 'A100', 'RTX 4090'.
Each line has the chosen plan, monthly_cost_usd, calc, vendor quote, source_url, checked_at and assumptions,
plus alternatives. A vendor price that isn't published is 'unknown' (never estimated). manual_signup_only=true
means a human must sign up (never automate it); exclude_manual_signup=true drops those plans. Same data as
https://thelanternworks.com/api/v1/stack-pricing.json and /tools/stack-optimizer/.

Input parameters:

- `emails_sent` (integer)
- `exclude_manual_signup` (boolean)
- `gpu_hours` (number)
- `gpu_model`
- `mode` (string)
- `proxy_gb` (number)
- `scrape_pages` (integer)
- `scrape_pages_js` (integer)
- `search_queries` (integer)

Output parameters:

- `error` (object)
- `issued_at` (string)
- `lines` (array)
- `mode` (string)
- `ok` (boolean)
- `quote_basis` (object)
- `quote_id` (string)
- `receipt` (object)

### `optimize_agent_stack` (~436 tokens)

Estimate a monthly stack cost from a short description of the agent being built.

description: free text, e.g. 'scrapes 20k JS pages/month via 5 GB residential proxies, 3k search queries,
summarizes with an LLM, budget $300/mo'. Parsed deterministically (keywords/regex, no LLM) into components:
gpu, scraping, proxy, search, llm_api, email, hosting, database, monitoring. Optional fields override the parse:
gpu_hours (GPU-hours/month), gpu_model ('H100', 'A100', 'RTX 4090'), model_size_b (billions of params; sets a
minimum VRAM using FP16 x 1.2), scrape_pages, js_rendering, proxy_gb, search_queries, emails_sent, llm_api,
monthly_budget_usd. Each component gets the cheapest option with a cited price among tracked providers, with
calc, source_url, verified_at, referral_disclosure (set when the link is a referral link) and manual-signup
notes. Components with no cited price say 'no sourced price tracked' (nothing is estimated). Totals show the
math and say whether they are complete. Pulled listings are excluded. Every option has data_age_hours, degraded (> 48 h) and stale (> 7 days); GPU prices older than 168 h never rank by default (listed in the line's stale_prices); max_data_age_hours replaces that default and drops older options (excluded_too_old counts them). Same data as optimize_stack,
compare_gpu_prices and the deal feed.

Input parameters:

- `description` (string)
- `emails_sent`
- `exclude_manual_signup` (boolean)
- `gpu_hours`
- `gpu_model`
- `js_rendering`
- `llm_api`
- `max_data_age_hours`
- `mode` (string)
- `model_size_b`
- `monthly_budget_usd`
- `proxy_gb`
- `scrape_pages`
- `search_queries`
- `workload`

Output parameters:

- `error` (object)
- `issued_at` (string)
- `lines` (array)
- `mode` (string)
- `ok` (boolean)
- `quote_basis` (object)
- `quote_id` (string)
- `receipt` (object)

### `estimate_job_cost` (~346 tokens)

Cost of one GPU job (not cost per hour) among tracked providers, cheapest compute subtotal first.

You supply the duration: job_hours, OR work_units plus throughput_units_per_gpu_hour from your own benchmark
(job_hours = work_units / (throughput x gpus_per_job)). If you give workload + work_units but no throughput,
a directly applicable published figure (closed-division MLPerf Inference, exact GPU variant, inference only)
is used: throughput_basis='published_benchmark' with throughput_source {url, quote, date, benchmark, derived,
caveats}; your throughput always wins. Otherwise not_found 'missing: throughput for {gpu}'. Whole-instance billing:
instances = ceil(gpus_per_job / gpus_per_instance), all allocated GPUs billed (9 GPUs on an 8-GPU-only
offer bill 16). Reserved and held-stale rates are never ranked; spot/interruptible only if allow_interruptible.
Each result has rate_id, source_url, verified_at, data_age_hours/degraded/stale. Response has assumptions,
citations, missing_costs, budget_verdict (unresolved: extras unknown) and a quote_id. Compute subtotal only.

Input parameters:

- `allow_interruptible` (boolean)
- `gpu_family` (string, required)
- `gpus_per_job` (integer, required)
- `job_hours`
- `max_data_age_hours`
- `min_vram_gb`
- `mode` (string)
- `region`
- `runs_per_month`
- `throughput_units_per_gpu_hour`
- `top_n` (integer)
- `work_units`
- `workload`

Output parameters:

- `budget_verdict` (string)
- `error` (object)
- `issued_at` (string)
- `mode` (string)
- `ok` (boolean)
- `quote_basis` (object)
- `quote_id` (string)
- `receipt` (object)
- `results` (array)

### `rebuild_quote` (~159 tokens)

Reopen a past quote. Pass the `receipt` object returned by optimize_stack, optimize_agent_stack or
estimate_job_cost. Returns receipt_intact (unkeyed sha256 matches), reproduced (true only if each line's subtotal
recomputes AND its rate_id and price match the pinned feed revision or that date's published daily snapshot;
"arithmetic_only" with provenance_verified=false when that can't be confirmed), per-line provenance, and
revalidation against today's feed: per GPU line unchanged | price_changed | evidence_changed | held_today |
not_in_feed_today (flat plans: not_revalidated), with revision 'same' or 'new'. Nothing is re-ranked.

Input parameters:

- `mode` (string)
- `receipt` (object, required)

Output parameters:

- `error` (object)
- `lines` (array)
- `mode` (string)
- `ok` (boolean)

### `search_deals` (~127 tokens)

Search agent work-stack deals (compute, search, email, unblock, hosting...).

offer_type: verified_discount | listed_discount (not confirmed; verified_at null) | free_tier | trial | standard_referral | credit_only_referral.
max_price excludes deals with unknown price. limit 1-25. Pass next_cursor back as cursor to page.

Input parameters:

- `category`
- `cursor`
- `limit` (integer)
- `max_price`
- `mode` (string)
- `offer_type`
- `query`
- `tags`

Output parameters:

- `error` (object)
- `mode` (string)
- `ok` (boolean)
- `results` (array)

### `compare_deals` (~48 tokens)

Compare 2-5 deals side by side (price, unit, offer type, code, verification), best value first.

Input parameters:

- `ids` (array, required)
- `mode` (string)

Output parameters:

- `deals` (array)
- `error` (object)
- `mode` (string)
- `ok` (boolean)

### `get_deal` (~40 tokens)

Get one deal's public record by id, including redeem_url and agent_instructions.

Input parameters:

- `id` (string, required)
- `mode` (string)

Output parameters:

- `error` (object)
- `mode` (string)
- `ok` (boolean)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/connormatthewdouglas-lantern-works-deals/lantern-works-deals-mcp#diagnostics

## Score history

- 2026-11-05: 52
- 2026-11-04: 67
- 2026-11-03: 66
- 2026-11-02: 51
- 2026-11-01: 66
- 2026-10-31: 65
- 2026-10-30: 50
- 2026-10-29: 49
- 2026-10-28: 50
- 2026-10-27: 50

## Common questions

### What is the Lantern Works GPU Prices: daily GPU rental price comparison MCP server?

Lantern Works GPU Prices: daily GPU rental price comparison is an MCP server listed in the public MCP registry as io.github.connormatthewdouglas/lantern-works-deals. GPU rental prices checked daily, with price history and change feed; stack optimizer; AI-infra deals. This page covers its PyPI package (lantern-works-deals-mcp).

### Is the Lantern Works GPU Prices: daily GPU rental price comparison MCP server safe to use?

Lantern Works GPU Prices: daily GPU rental price comparison scores 52 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. 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 Lantern Works GPU Prices: daily GPU rental price comparison MCP server expose?

Lantern Works GPU Prices: daily GPU rental price comparison exposes 9 tools: compare_gpu_prices, get_price_changes, optimize_stack, optimize_agent_stack, estimate_job_cost, and 4 more. Their descriptions and schemas cost roughly 2,343 tokens of context every time the server is loaded.

### Is the Lantern Works GPU Prices: daily GPU rental price comparison MCP server still maintained?

Lantern Works GPU Prices: daily GPU rental price comparison 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 Lantern Works GPU Prices: daily GPU rental price comparison MCP server under?

Lantern Works GPU Prices: daily GPU rental price comparison declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/lantern-works-deals-mcp/
- Socket report: https://socket.dev/pypi/package/lantern-works-deals-mcp
- Repository: https://github.com/connormatthewdouglas/agent-work-stack-deals
- Website: https://thelanternworks.com/for-agents/?ref=mcp-registry
- Changelog RSS feed: https://verifymcp.io/servers/connormatthewdouglas-lantern-works-deals/lantern-works-deals-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/connormatthewdouglas-lantern-works-deals/lantern-works-deals-mcp.json
- HTML version of this page: https://verifymcp.io/servers/connormatthewdouglas-lantern-works-deals/lantern-works-deals-mcp