Alpaca Trading API integration for Model Context Protocol (MCP)
Galactic is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
On-chain asset, market, and GPU price data for galactic.inc.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http galactic-mcp https://mcp.galactic.inc/mcp
# 2 — ask your agent for something these tools do
# compute_vaults, get_asset, gpu_price_index and 3 more
Galactic costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http galactic-mcp https://mcp.galactic.inc/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
6 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
On-chain figures for the USD.AI and GAIB compute vaults. Call this for tokens outstanding, vault share price, and the trailing 90-day figure. trailing_90d_apy_percent annualizes the change in vault share price over the trailing window. It is not an issuer-quoted yield. loan_count and loan_balance_usd (US dollars) are present only when the loan book is read on-chain. JSON: {"as_of", "vaults": [{i
| Parameter | Type | Required | Notes |
|---|---|---|---|
| asset | string | no | Vault id, usdai or gaib. Empty returns both. |
| response_format | string | no | markdown (default) is a compact reading form. json is the object described below, with source numbers and omitted fields left out. |
One published asset, with per-chain supply and an optional daily price history. Call this after list_assets, or when the id is already known. Pass the id from an ambiguous result. Do not guess among assets that share a display ticker. JSON is the asset card plus by_chain (chain, supply, market_cap_usd, holders where published) and history ([{date, price_usd}], newest days only, only when the pri
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Asset id (slug), registry ticker, or display ticker. A shared display ticker returns an ambiguous error and the matching ids. |
| history_days | integer | no | Daily published prices to include, from 0 to 30. 0 omits history. History is included only when the price itself is published. |
| response_format | string | no | markdown (default) is a compact reading form. json is the object described below, with source numbers and omitted fields left out. |
Latest GPU rental price index, in US dollars per GPU-hour. Call this for the current median rental price of a GPU model, or for prices by GPU memory. Omit model for every published model plus the 16, 64, 256, and 512 GB tiers. Pass one model name for that model only. On-demand is list price. Spot combines spot prices, interruptible prices, and marketplace asking prices. Each class has median_usd
| Parameter | Type | Required | Notes |
|---|---|---|---|
| model | string | no | GPU model name as published, for example H100 SXM. Empty returns every model and the memory tiers. |
| response_format | string | no | markdown (default) is a compact reading form. json is the object described below, with source numbers and omitted fields left out. |
List published tokenized assets. Call this to find an asset by ticker, name, category, chain, or issuer before get_asset. Live assets are the galactic.inc screener universe. Announced listings have a launch date and no supply, price, or holders. JSON shape: {"matched", "offset", "limit", "assets": [cards], "upcoming": [cards]}. A card includes id, ticker, display_ticker, name, category, category
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | Case-insensitive substring of ticker, display ticker, name, issuer, or id. Empty lists the universe. |
| category | string | no | Category slug or English label, such as gold or Treasuries. Empty means every category. Slugs: gold, treasuries, money-market, private-credit, stocks, commodities, funds, real-estate, deposit-token. |
| chain | string | no | Chain id (ethereum, solana, robinhood, liquid, zksync, and the other published chain ids) or the chain display name. Empty means every chain. |
| issuer | string | no | Case-insensitive substring of the published issuer name. |
| limit | integer | no | Page size from 1 to 200. |
| offset | integer | no | Matches to skip. |
| include_upcoming | boolean | no | When true, announced listings with no on-chain figures are included after the live page. |
| response_format | string | no | markdown (default) is a compact reading form. json is the object described below, with source numbers and omitted fields left out. |
Category and chain totals for the published asset universe. Call this for asset counts, pricing coverage, and holder totals. The aggregate market cap is published only when every listed asset has a published on-chain price. Until then market_cap_usd is null, market_cap_withheld is true, every by_category and by_chain row leaves out market_cap_usd, and coverage says how many listed assets are pric
| Parameter | Type | Required | Notes |
|---|---|---|---|
| response_format | string | no | markdown (default) is a compact reading form. json is the object described below, with source numbers and omitted fields left out. |
Search approved galactic.inc newsroom items. Call this for recent headlines about an asset, an issuer, or a topic. Items that are not approved are omitted. The response has no source URL. JSON: {"matched", "items": [{id, date, category, headline, lede, assets}]}. assets is a list of tickers. date is YYYY-MM-DD. limit defaults to 8.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | Case-insensitive substring of headline, lede, category, or asset ticker. Empty returns the latest approved items. |
| limit | integer | no | Maximum items to return, from 1 to 30. |
| response_format | string | no | markdown (default) is a compact reading form. json is the object described below, with source numbers and omitted fields left out. |
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Galactic or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| compute_vaults | no tags | |
| get_asset | no tags | |
| gpu_price_index | no tags | |
| list_assets | no tags | |
| market_totals | no tags | |
| search_news | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 0.1.1.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish Galactic can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.