Alpaca Trading API integration for Model Context Protocol (MCP)
Nothing to run from here
Coinopai 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
15
downloads a day
local
runs on your machine
1k
downloads in 30d
What it does
Auditable market intelligence MCP with x402 payments, calibrated forecast ranges, anomaly review, risk context, and outcome audits
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'WALLET_PRIVATE_KEY=${WALLET_PRIVATE_KEY}' --transport stdio coinopai-mcp '--' npx -y coinopai-mcp
# 2 — ask your agent for something these tools do
# search_agent_automations, get_agent_automation, list_automation_categories and 12 more
It needs WALLET_PRIVATE_KEY: this reads it from your environment, so export it first.
Coinopai costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publisher
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Coinopai as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads WALLET_PRIVATE_KEY (Dedicated low-balance Base wallet private key for x402 USDC micropayments. Do not use your primary wallet) from your environment each time it starts the server, so the value stays out of its config: export it in your shell profile (macOS, Linux), or run setx WALLET_PRIVATE_KEY … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'WALLET_PRIVATE_KEY=${WALLET_PRIVATE_KEY}' --transport stdio coinopai-mcp '--' npx -y coinopai-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: WALLET_PRIVATE_KEY — Dedicated low-balance Base wallet private key for x402 USDC micropayments. Do not use your primary wallet.. You set it 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
15 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.
Search 819 agent automation prompts by keyword. Returns matching automations with title, description, complexity and services. Costs $0.01 USDC.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Search keyword (e.g. 'slack', 'notion', 'github') |
| limit | number | no | Max results to return (default 20, max 50) |
Get the full agent automation prompt and workflow steps by slug. Costs $0.01 USDC.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | Automation slug (e.g. 'slack-to-notion') |
List all 35 automation categories with counts. Costs $0.005 USDC.
No parameter schema on file.
Latest Kronos model context for BTC, ETH, SOL, XRP, ADA. Directional values are supporting context, not standalone trade instructions; use them with the calibrated range, risk state, and audit record. Costs $0.05 USDC.
No parameter schema on file.
Current market risk state and cooldown context for Kronos decisions. Useful as supporting context, not a standalone trading command. Costs $0.02 USDC.
No parameter schema on file.
Recent Kronos context history for BTC/ETH/SOL/XRP/ADA. Use it to inspect model context and freshness before or after a decision. Costs $0.05 USDC.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| hours | number | no | Hours of history to fetch (default 24, max 168) |
Create a market-intelligence journal entry from Kronos context. Returns directional_bias, confidence context, compliance metadata, regime, anomaly/calibration context, and a decision_id. Call audit_trade_decision with that ID after the evaluation window to see what happened. Costs $0.15 USDC.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| symbol | string | yes | Symbol to evaluate: BTC, ETH, SOL, XRP, or ADA |
Step 1 of the auditable decision loop. Checks market state, cooldown, data freshness, and model context before calling get_crypto_decision. Costs $0.05 USDC.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| symbol | string | yes | Symbol to check: BTC, ETH, SOL, XRP, or ADA |
The accountability step. Verify a Kronos decision_id against later market prices. Returns whether direction held, PnL%, and a verdict: GOOD_DECISION, BAD_DIRECTION, NOISE, or NO_ACTION_TAKEN. Costs $0.07 USDC.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| decision_id | string | yes | UUID from a previous get_crypto_decision call |
| window | string | no | Evaluation window: 1h, 4h, or 24h (default: 4h) |
Kronos Futures: perpetual-futures decision package. Direction LONG / SHORT / FLAT from the Kronos signal, stop-loss and take-profit on the calibrated 80% range, leverage cap keeping liquidation outside 2x the stop, liquidation price, risk-based position size for your equity, and live perp funding…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| symbol | string | no | Symbol: BTC, ETH, SOL, XRP, ADA (default: BTC) |
| equity | number | no | Account equity in USD for position sizing (optional) |
| max_loss_pct | number | no | Max loss per position as a fraction of equity (default 0.01) |
| max_leverage | number | no | Your leverage ceiling, 1-5 (default 5) |
Kronos Futures: live perpetual funding rates (1h, 8h, annualized), mark/index price, open interest, and crowding label (LONG_CROWDED / SHORT_CROWDED / BALANCED) for BTC, ETH, SOL, XRP, ADA from Kraken Futures and Hyperliquid. Costs $0.02 USDC.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| symbol | string | no | Optional single symbol; omit for all five |
Kronos Futures: will a leveraged perp position survive the calibrated range? Returns liquidation price and distance, adverse range bound, verdict (SURVIVES_RANGE / THIN_BUFFER / LIQUIDATION_INSIDE_RANGE), max surviving leverage, P&L at both range bounds, and funding cost. Costs $0.05 USDC.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| symbol | string | no | Symbol: BTC, ETH, SOL, XRP, ADA (default: BTC) |
| side | string | yes | LONG or SHORT |
| leverage | number | yes | Leverage to test (1-125) |
| entry | number | no | Entry price (defaults to current perp mark) |
| notional | number | no | Position notional in USD for funding cost (optional) |
| horizon_hours | number | no | Hours held for funding cost (optional) |
Conformally-calibrated price forecast: an honest 80% prediction interval (range_80, ~0.80 empirical coverage) plus point return and upside probability for BTC/ETH/SOL/XRP/ADA. Directional bias is supporting context; the calibrated range is the validated product. Costs $0.05 USDC.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| symbol | string | no | Symbol: BTC, ETH, SOL, XRP, ADA (default: BTC) |
Free. Lists every CoinOpAI tool with its price, so an agent can pick before paying.
No parameter schema on file.
Score a market signal feature set for unusual conditions before downstream analysis. Returns anomaly_score, anomaly_level, review_label, drivers, component scores, and market-intelligence disclaimers. Not financial advice and not a market activity instruction. Costs $0.07 USDC.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| symbol | string | yes | Symbol to review, e.g. BTC, ETH, SOL, XRP, ADA, AAPL, SPY |
| window | string | no | Observation window label, e.g. 24h (default: 24h) |
| features | object | yes | Numeric feature values to score, such as price_change, volume_change, volatility, signal_confidence, risk_score, social_velocity, or onchain_velocity. |
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 Coinopai 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 2.2.2 · 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 · 1 capability
Capabilitymoderate
Coveragesource
Verificationrepo
Surface digest819bc13ff4cc40fa8121a5b417d1f7daa60f4d329cdba77ef77231f38b65bf1c
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 (15 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 |
|---|---|---|
| search_agent_automations | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_agent_automation | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_automation_categories | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_crypto_signals | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_crypto_risk | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_crypto_signal_history | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_crypto_decision | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| check_trade_preflight | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| audit_trade_decision | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_futures_decision | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| get_perp_funding | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| check_futures_risk | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_crypto_forecast | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_tools | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| review_signal_anomaly | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
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.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digest819bc13ff4cc40fa
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 2.2.2. Pin a release below and the command asks for exactly that one.
2.2.2
8 Oct 2026
latestNo release note was published with this version.
2.2.0
25 Sep 2026
No release note was published with this version.
2.1.0
23 Sep 2026
No release note was published with this version.
2.0.2
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
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 Coinopai 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.