Skip to content
Back to search

mcp-price-history

price-history: Pipeworx's own recorded history of things that only exist as history if somebody records them (fleet #4701). A snapshot store plus a recorder; feeds are config rows. First feeds: GPU rental prices and Apple App Store top charts. Writer: scripts/snapshot-store/record.mjs.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/pipeworx-io--mcp-price-history/badge.svg)](/listings/pipeworx-io--mcp-price-history)

HTML

<a href="/listings/pipeworx-io--mcp-price-history"><img src="/api/listings/pipeworx-io--mcp-price-history/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "price-history": {
      "url": "https://gateway.pipeworx.io/price-history/mcp"
    }
  }
}

What this endpoint actually serves

`tools/list` at `https://gateway.pipeworx.io/price-history/mcp` returns the tools in the table above **plus the shared Pipeworx meta-tools** — `ask_pipeworx`, `discover_tools`, `search_within`, `remember`/`recall` and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's `initialize` response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via `ask_pipeworx`, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}

Both URLs reach the same gateway and the same 2024+ data sources. The only difference is which pack's tools are listed **directly**; `ask_pipeworx` reaches all of them from either one.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 157 lines
  1. # @pipeworx/price-history
  2. Pipeworx's own recorded history of data that only exists as history if somebody records it: GPU rental prices and Apple App Store top charts, kept as one row per change from the day recording began.
  3. Part of [Pipeworx](https://pipeworx.io) — an MCP gateway connecting AI agents to 2024+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.
  4. ## Tools
  5. - `price_history_feeds()` — the recorded feeds, each with its publisher, what is compared, cadence, `first_observed` (the date its history begins) and `data_as_of`.
  6. - `price_history_latest(feed, group?, query?, limit?)` — current value of every entity in a feed, with the date each value has held since.
  7. - `price_history_entity(feed, entity_id, limit?)` — every recorded change for one entity, oldest first, including when it entered or left the listing.
  8. - `price_history_movers(feed, from, to?, group?, limit?)` — what moved between two dates: entities whose compared value changed (largest move first), entities that appeared, entities that left.
  9. Every response carries `history_begins` and a `coverage_note`. History starts the day the feed's recorder first ran; nothing earlier is held and nothing is backfilled, so an absence before that date means nothing.
  10. ## Feeds (first two)
  11. **gpu-rental** — `$/hr`, daily.
  12. - Microsoft Azure, public retail price list: Linux pay-as-you-go ND- and NC-series GPU VMs, East US and West Europe.
  13. - Amazon Web Services, EC2 on-demand list prices (us-east-1) for the p5, p4d, p4de, p3, g6e, g6 and g5 families, read through a public price relay.
  14. - RunPod, GPU cloud: lowest on-demand price per GPU type.
  15. - Vast.ai marketplace: cheapest and median rentable single-GPU offer per model (H200, H100 SXM and PCIE, A100 SXM4 and PCIE, L40S, RTX 5090, RTX 4090, RTX 3090). Marketplace figures are the cheapest listing, not a posted rate.
  16. **appstore-charts** — chart rank, daily. Apple, App Store top free and top paid app charts, top 50, for six storefronts: US, GB, DE, JP, BR, IN (the largest English, European, Asian and Latin American markets, kept to six so the row count stays small). Apple's feed carries two app charts and no category split, so there are no category charts. A row is written when an app changes rank, enters or leaves a chart.
  17. ## How history is recorded
  18. A recorder (`scripts/snapshot-store/record.mjs`) polls each source once a day and compares every entity with its latest stored value. It inserts a row only when the value changed, or the entity appeared or left a complete fetch. An unchanged entity writes nothing. There is no per-entity last-seen column: a run log holds one row per feed run, and an entity is considered still listed at a time T if its latest observation at or before T is a value (not a removal) and a successful run exists at or after T. A group whose fetch failed is never marked as removed, and a fetch returning under half of a group's prior entities is treated as broken, not as a market collapse.
  19. Adding a feed is one config object plus a fetcher in `scripts/snapshot-store/feeds.mjs`. The tables (`snapshot_feeds`, `snapshot_observations`, `snapshot_runs`, function `snapshot_as_of`) do not change.
  20. ## Budget (fleet #4701)
  21. Store: tables in the existing Supabase Postgres (migration 289). No new Cloudflare binding, no D1/KV/DO/R2 use, no per-row billing. Worst case, every one of ~600 App Store entities and ~160 GPU entities changes every day: ~760 rows/day, ~280k rows/year, ~250 bytes each, ~70 MB/year against an 8 GB plan. One-time load: $0. Steady state: $0 marginal on the database; one scheduled workflow run a day (~2 minutes of runner time). Measured on 2026-11-20: first run wrote 156 GPU rows and 547 chart rows (one of twelve charts timed out and was left untouched, not marked removed); a second run 90 seconds later wrote 13 GPU rows (RunPod stock listings appearing and leaving, Vast.ai cheapest-offer moves, one Azure SKU) out of 154 entities and 49 chart rows, all from the chart that had timed out, with the 547 unchanged chart entities writing nothing. Steady state is expected well under the worst case. Cheaper alternatives considered: R2 JSONL (no migration, but history and as-of queries need a read-modify-write per feed and a scan per question) and D1 (priced per row written, and needs a new binding on a gateway at 243 of 250). Neither meets the need more cheaply.
  22. ## Auth
  23. Keyless. The sources are public and keyless; the recorder identifies itself with an honest User-Agent and reads each source once a day, serially.
  24. ## Data sources
  25. - Microsoft, Azure retail price list (virtual machines).
  26. - Amazon Web Services, EC2 on-demand list prices, via a public price relay.
  27. - RunPod, GPU cloud public GPU-type pricing.
  28. - Vast.ai, public marketplace listings.
  29. - Apple, App Store top charts (Apple Marketing Tools).
  30. The figures are the publishers' listed prices and chart positions at the time of each daily read. They are not quotes, and marketplace entries move between reads.
  31. ## Quick Start
  32. Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
  33. ```json
  34. {
  35. "mcpServers": {
  36. "price-history": {
  37. "url": "https://gateway.pipeworx.io/price-history/mcp"
  38. }
  39. }
  40. }
  41. ```
  42. ### What this endpoint actually serves
  43. `tools/list` at `https://gateway.pipeworx.io/price-history/mcp` returns the tools in the table
  44. above **plus the shared Pipeworx meta-tools** — `ask_pipeworx`,
  45. `discover_tools`, `search_within`, `remember`/`recall` and the rest of the
  46. gateway-wide set. So the tool count you see is larger than this table: a
  47. single-pack endpoint currently lists roughly 30 shared tools alongside the
  48. pack's own. The connection's `initialize` response states its exact scope, and
  49. is the authoritative answer for a given day.
  50. This is deliberate, not multiplexing by accident. The meta-tools are what let a
  51. scoped connection answer a question this pack does not cover — via
  52. `ask_pipeworx`, which routes across the whole catalog — without you adding a
  53. second MCP server. There is currently no way to mount a pack endpoint without
  54. them; if the extra schemas cost you more context than the routing is worth,
  55. connect to the full gateway once rather than to several pack endpoints.
  56. Or connect to the full Pipeworx gateway to get every pack's tools listed
  57. directly, instead of just this one's:
  58. ```json
  59. {
  60. "mcpServers": {
  61. "pipeworx": {
  62. "url": "https://gateway.pipeworx.io/mcp"
  63. }
  64. }
  65. }
  66. ```
  67. Both URLs reach the same gateway and the same 2024+ data sources. The
  68. only difference is which pack's tools are listed **directly**; `ask_pipeworx`
  69. reaches all of them from either one.
  70. ## No MCP client? Call it over HTTP
  71. ```bash
  72. curl -X POST https://gateway.pipeworx.io/v1/tools/price_history_feeds \
  73. -H 'Content-Type: application/json' \
  74. -d '{}'
  75. ```
  76. No account needed for the first calls. Inspect any tool: `GET https://gateway.pipeworx.io/v1/tools/price_history_feeds`. Find one: `POST https://gateway.pipeworx.io/v1/tools/search_packs` with `{"query":"..."}`.
  77. ## Run it from npm
  78. `@pipeworx/mcp-price-history` is a local stdio bridge to the Pipeworx gateway: your MCP client
  79. starts it with `npx`, and it forwards every call to the same
  80. `https://gateway.pipeworx.io/price-history/mcp` endpoint shown above. It needs network access;
  81. there is no offline mode.
  82. ```json
  83. {
  84. "mcpServers": {
  85. "price-history": {
  86. "command": "npx",
  87. "args": ["-y", "@pipeworx/mcp-price-history"]
  88. }
  89. }
  90. }
  91. ```
  92. Without a key it calls anonymously, capped at 50 calls a day. A free account
  93. raises that to 200 a day: get a key at https://pipeworx.io/signup and add
  94. `"env": { "PIPEWORX_API_KEY": "<your key>" }` to the server entry.
  95. The key is sent as a Bearer token, the same way a hosted connection sends it,
  96. so calls are metered and billed exactly as they are there.
  97. It lists **only** this pack's tools by default. Set `PIPEWORX_META_TOOLS=1` to
  98. also list `ask_pipeworx` and the other gateway-wide tools.
  99. Behind an HTTPS proxy: Node's built-in `fetch` does not read `HTTPS_PROXY` by
  100. default. Newer Node releases honour it when `NODE_USE_ENV_PROXY=1` is set; check
  101. your Node version's documentation.
  102. ## Using with ask_pipeworx
  103. Instead of calling tools directly, you can ask questions in plain English —
  104. this works on the pack endpoint above as well as on the full gateway:
  105. ```
  106. ask_pipeworx({ question: "your question about Price History data" })
  107. ```
  108. The gateway picks the right tool and fills the arguments automatically.
  109. ## More
  110. - [Docs and guides](https://pipeworx.io/docs)
  111. - [pipeworx.io](https://pipeworx.io)
  112. ## License
  113. MIT

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.