Alpaca Trading API integration for Model Context Protocol (MCP)
BTC DCA Engine 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
Historical dollar-cost-averaging simulator for Bitcoin and other assets.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http btc-dca-engine-mcp https://btcdcaengine.com/mcp
# 2 — ask your agent for something these tools do
# list_assets, data_status, run_dca and 1 more
BTC DCA Engine 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 btc-dca-engine-mcp https://btcdcaengine.com/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.
4 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.
Assets this endpoint can simulate, with the date each series starts and ends. Call before composing a plan so start dates fall inside coverage.
No parameter schema on file.
The vintage of the loaded price data and how often it refreshes.
No parameter schema on file.
Simulate one dollar-cost-averaging plan against real historical closes. Returns totals, end-of-year checkpoints and a share_url that opens the same run in the app.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| asset | string | yes | Asset key from list_assets, e.g. "btc_daily", "Ethereum", "S&P 500". |
| type | string | no | "dca" repeats on the schedule; "lump-sum" buys once at the start. Default "dca". |
| amount | number | yes | USD per contribution, or the single amount for lump-sum. |
| frequency | string | no | Contribution cadence. Default "monthly". Quarterly is the coarsest offered: wider gaps behave like a few lump sums (see the knowledge base, "The gap between buys"). |
| start_date | string | yes | First scheduled contribution. |
| end_date | string | no | Window end. Defaults to the last loaded close, never a relative "today". |
| wait_periods | integer | no | Save this many scheduled contributions as cash before the first purchase. |
| last_buy_date | string | no | Stop buying here and hold to end_date. |
| as_of | string | no | Pin the answer to this data vintage so the share link keeps returning the same number. |
| settings | object | no | Chart overlays carried into share_url, and the figures they add to each summary. Flags marked "Pro only" need a signed-in Pro account or a Pro API key; without one, the call returns an error naming th |
| include | object | no | — |
Run up to 5 plans over the same data and rank them by final value (2 without a signed-in Pro account or a Pro API key). Use to compare assets, cadences or start dates side by side. One share_url opens them all together.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| plans | array | yes | The plans to compare: up to 2 anonymously or on a Free-account key, up to 5 with a signed-in Pro account or a Pro API key. |
| as_of | string | no | — |
| settings | object | no | Chart overlays carried into share_url, and the figures they add to each summary. Flags marked "Pro only" need a signed-in Pro account or a Pro API key; without one, the call returns an error naming th |
| include | object | no | — |
- 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 BTC DCA Engine 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.
This listing is an address its publisher runs, and you connect to it directly — this marketplace is not in the path. The scanner reads packages and public source, and an address is neither. So there is no grade — not a withheld one, an unmeasured one.
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 1.4.0.
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 BTC DCA Engine 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.