Alpaca Trading API integration for Model Context Protocol (MCP)
Nothing to run from here
Gainium 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.
96/100
trust score
8
downloads a day
local
runs on your machine
213
downloads in 30d
What it does
MCP server for Gainium — manage trading bots, deals, and balances via AI assistants
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'GAINIUM_API_KEY=${GAINIUM_API_KEY}' --env 'GAINIUM_API_SECRET=${GAINIUM_API_SECRET}' --transport stdio gainium-mcp '--' npx -y gainium-mcp
# 2 — ask your agent for something these tools do
# list_bots, get_bot, create_bot and 16 more
It needs GAINIUM_API_KEY, GAINIUM_API_SECRET: this reads them from your environment, so export them first.
Gainium costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
GAAll 1 server
gainium1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Gainium as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads GAINIUM_API_KEY (Gainium API key (https://app.gainium.io → Settings → API)), GAINIUM_API_SECRET (Gainium API secret (paired with GAINIUM_API_KEY)) from your environment each time it starts the server, so the value stays out of its config: export them in your shell profile (macOS, Linux), or run setx GAINIUM_API_KEY …, setx GAINIUM_API_SECRET … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'GAINIUM_API_KEY=${GAINIUM_API_KEY}' --env 'GAINIUM_API_SECRET=${GAINIUM_API_SECRET}' --transport stdio gainium-mcp '--' npx -y gainium-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
It reaches a system of yours, so it needs your own credential rather than the publisher’s: GAINIUM_API_KEY — Gainium API key (https://app.gainium.io → Settings → API); GAINIUM_API_SECRET — Gainium API secret (paired with GAINIUM_API_KEY). You set them in your own client’s config, on your machine — this marketplace never holds it.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
19 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.
List the authenticated user's bots of one type (DCA, Combo, or Grid), with status/pagination/paper-context filters.
No parameter schema on file.
Read a single bot by its MongoDB ObjectId or UUID. Returns the full bot record (fields controlled by the same fields preset/csv as list_bots).
No parameter schema on file.
Create a new bot in a single step — no follow-up update needed.
No parameter schema on file.
Patch the settings of an existing DCA or Combo bot (Grid has no update endpoint — clone-and-recreate it instead).
No parameter schema on file.
Duplicate an existing bot — copies all configured settings into a new bot and returns the new bot id. Open deals on the source are NOT copied; the clone starts empty.
No parameter schema on file.
Bot lifecycle actions: start, stop (requires closeType for DCA/Combo or closeGridType for Grid — controls how open deals are unwound), archive, restore, or changePairs (DCA only — requires pair array).
No parameter schema on file.
List the user's deals of one type (DCA, Combo, or Terminal) with status, botId, and paper-context filters. Returns one page; fields accepts a preset or comma-separated list.
No parameter schema on file.
Read a single deal by its MongoDB ObjectId — returns the full record (entries, exits, current PnL, settings). fields uses the same preset/csv shape as list_deals.
No parameter schema on file.
Open a new deal — places real entry orders immediately. Two modes by dealType:
No parameter schema on file.
Patch the settings of an existing open deal (e.g. take-profit %, stop-loss, trailing TP). Pass only the fields you want to change inside settings; empty settings is rejected.
No parameter schema on file.
Lifecycle actions on a single open deal: close (terminal — requires closeType), addFunds, or reduceFunds (both require qty, type, and — when type="fixed" — asset).
No parameter schema on file.
Submit a backtest of a candidate bot configuration. Four modes by mode:
No parameter schema on file.
Read-only access to backtest metadata, results, and templates. Four targets by target:
No parameter schema on file.
Read-only catalog of available bot types, fields, defaults, and indicators — the source of truth for what create_bot / update_bot accept. Six targets by target:
No parameter schema on file.
Read-only account information selected via info: balances (per-exchange holdings — exchangeId, asset/assets filters apply), exchanges (connected exchange accounts and their UUIDs — needed as exchangeUUID when creating bots), globalVariables (user-defined constants accessible in…
No parameter schema on file.
Create, update, or delete a global variable. Variables are user-defined constants referenced by name inside bot strategy expressions.
No parameter schema on file.
Read-only cryptocurrency screener — browse live price, 24h % change, volume, and market-cap data across hundreds of pairs.
No parameter schema on file.
Read-only curated bot-strategy presets ranked by backtested performance. Each coin returns tiers (short/mid/long) × strategy (long/short) with ROI, drawdown, and the full strategy settings.
No parameter schema on file.
Create a real bot from a curated preset in a single call — equivalent to list_presets → pick row → create_bot collapsed into one step.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- 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 Gainium or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 96 / 100
Release 3.3.0 · scanned 14 Oct 2026
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.
Threat score100
Client score96
Findings0 threat · 0 capability
Capabilitymoderate
Coveragesource
Verificationrepo
Surface digest42291a6e70bd997c7143b7553e24798347085f49ae31a56e1f7b231a28549fc6
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
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.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (19 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
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. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| list_bots | untrusted-input | untrusted-input: keyword "browse" |
| get_bot | untrusted-input | untrusted-input: keyword "browse" |
| create_bot | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| update_bot | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| clone_bot | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| manage_bot | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| list_deals | no tags | |
| get_deal | untrusted-input | untrusted-input: keyword "browse" |
| create_deal | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| update_deal | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| manage_deal | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| run_backtest | untrusted-inputstate-write | untrusted-input: keyword "fetch"; state-write: declares readOnlyHint: false |
| backtest_info | no tags | |
| discover | no tags | |
| get_account | no tags | |
| manage_global_variable | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| get_screener | untrusted-input | untrusted-input: keyword "browse" |
| list_presets | no tags | |
| apply_preset | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
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
Integrityfirst-seen
Surface digest42291a6e70bd997c
Scanned2026-10-14
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
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 3.3.0. Pin a release below and the command asks for exactly that one.
3.3.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
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.
Sign in to write one
Any signed-in account that does not publish Gainium can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
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.