# Acubic Muse connector

From musedirectory.ai, the independent directory of Meta Muse connectors. Not affiliated with Meta.

## Acubic

Build, screen and backtest systematic stock and ETF portfolios for eToro and Trading 212.

- Record: https://musedirectory.ai/connector/acubic
- Category: Finance & Bills
- Developer: Acubic (https://acubic.ai)
- Muse status: Extra setup. Not in Muse's Connectors list yet. Muse can still use it: its page gives you a request to paste into Muse.
- Health: Working, 87ms, checked 2026-11-20T14:31:07Z
- Endpoint: https://mcp.acubic.ai/mcp
- Auth: No account needed; Pricing: unknown
- Screening: Screened, no issues found (2026-11-17T22:16:25Z)
- Source: Found in the official MCP Registry (ai.acubic/acubic) https://registry.modelcontextprotocol.io/v0/servers?search=ai.acubic%2Facubic

Connects to Acubic's strategy builder for the eToro and Trading 212 universes. Muse can screen stocks and ETFs by market cap, P/E and sector, rank candidates, save portfolio drafts, run walk-forward backtests against the S&P 500, project Monte Carlo scenarios, and return a signed link to connect a broker and automate a strategy.

Example request: "Build me a medium-risk ETF portfolio from the Trading 212 universe and backtest it over the last five years."

How to connect: Not in Muse's Connectors list yet, but Muse can still use it. Paste this into Muse: "Use Acubic to help me. It is a free service with an MCP server at https://mcp.acubic.ai/mcp. It does not need an API key. Ask me before you share anything with it." Muse asks before it shares anything with the app's site. Meta does not review apps used this way, so only use ones you trust. We tested this in the Muse app on September 24, 2026: Muse used an app's link directly this way and returned a live answer.

Tools:
- acubic_search_knowledge: Searches what Acubic publishes (blog, guides, methodology, FAQ, pricing) and returns passages with links to cite. Use it for how Acubic builds and backtests strategies, plan limits and the broker connections. It does not look up individual stocks (use acubic_lookup_instrument); f
- acubic_list_strategy_templates: Lists the ready preset strategies, one per experience level and risk level (largest accepted drawdown), plus Custom (advanced): the full engine. Each preset gives its universe rules, recommended pair and the arguments for acubic_create_strategy. Use it to explore or compare prese
- acubic_lookup_instrument: Looks up a stock, ETF, crypto asset or currency pair by ticker, ISIN or name: its identity, whether it is in Acubic's tradable universe, whether eToro and Trading 212 list it, and any equivalent product Acubic substitutes (e.g. a UCITS ETF). Identity only: no price, return or rat
- acubic_screen_universe: Applies filter rules (e.g. market cap at least $10 billion, P/E at most 25; AND, up to 20) to the universe eToro and Trading 212 both hold, after optional asset class, region, sector and include narrowing. Returns how many pass, per asset class, with up to 25 example rows, from t
- acubic_explain: Explains one investing term or Acubic setting in plain language (a metric such as P/E or maximum drawdown, a filter, ranking or weighting method, risk level, rebalance or backtest term): its meaning, how Acubic uses it, default, caveats and its page. Use it whenever the user asks
- acubic_list_strategy_options: Lists every choice the strategy builder offers, with ids, trade-offs and defaults: universe, filter metrics, include lists, ranking methods, weighting methods, rebalance, backtest settings and recipes. Optionally one section. It describes options; the choice is the person's. For 
- acubic_get_account: Returns the signed-in person's plan, allowance used and when it resets, live-portfolio limits, language, experience level, and a plan comparison with an upgrade link. It does not return the email, payment or broker details. For live holdings use acubic_get_portfolio.
- acubic_list_strategies: Lists the signed-in person's saved strategies, newest first: name, kind (draft, paper or live), holdings count, method, backtest date and link; mode archived shows the archive. It has no performance figures: use acubic_get_strategy for one strategy, acubic_get_backtest for result
- acubic_get_strategy: Returns one saved strategy: holdings and weights, its settings (experience and risk level, ranking, weighting, asset count, filters, locks), data date, the summary of its latest saved backtest and its broker connection. It also accepts the build_id of a finished build (while it r
- acubic_get_backtest: Returns the latest saved walk-forward backtest of one strategy: assumptions, CAGR, volatility, Sharpe and Sortino, maximum drawdown and total return against the S&P 500 (SPY), yearly returns, drawdown episodes and last holdings; include adds the equity curve. Figures are hypothet
- acubic_get_backtest_status: Checks a run of acubic_run_backtest without opening a card: percent done and poll_after_seconds, then the headline figures (hypothetical, with a disclosure). A run that failed or was cancelled is an error and nothing was charged. Use it to wait; read the full result once with acu
- acubic_get_build_status: Tracks a new draft from acubic_create_strategy by its build_id while it is assembled: progress and poll_after_seconds, then the saved strategy's id to open once. A failed or cancelled build is an error that cost nothing. Backtests have acubic_get_backtest_status.
- acubic_get_portfolio: Returns holdings, value, return since activation and the last rebalance outcome of the person's live or paper-money strategies, from Acubic's latest daily snapshot (as_of); it does not contact the broker and never returns credentials or account numbers. Use it for how a running p
- acubic_create_strategy: Creates and saves a new draft strategy from the acubic.ai builder's choices: universe, include lists, asset count, sizes, ranking, weighting, filter rules, limits, and tickers to add, exclude or lock. A preset (template_id) fixes the menu; without one every engine argument is ope
- acubic_update_strategy: Updates the name, description, filter rules, include lists or Exclude list of one saved strategy, and lists each previous value. Holdings are not recomputed. It cannot change the ranking, weighting, limits or sizes: for that build a new strategy with acubic_create_strategy. A str
- acubic_run_backtest: Runs a walk-forward backtest of one saved strategy and saves it in place of the previous one: at each rebalance the strategy is rebuilt from the data then available, with transaction costs, against the S&P 500 (SPY). 1 to 10 years, monthly, quarterly or annual rebalancing, 0 to 2
- acubic_delete_strategy: Deletes a draft or paper-money strategy by archiving it together with its saved backtest; it can be restored within 30 days (acubic_restore_strategy). A strategy with a broker connection is removed on acubic.ai. The person is asked to confirm, or the result gives a confirm_token 
- acubic_rank_candidates: Ranks the candidates of a design before anything is saved (Order & Select on acubic.ai): the ranked list, page by page, with score, per-factor values (vs industry: also the peers' median), sector, country and asset class, and the pick the site would make. A fresh ranking uses one
- acubic_regenerate_suggestion: Regenerates the suggested portfolio of one saved strategy with its saved settings, like Regenerate on acubic.ai, and returns the holdings and weights; the saved strategy is not changed. It never changes the ranking or the weighting: for another one, build with acubic_create_strat
- acubic_go_live: Returns a signed link, valid 15 minutes, to automate one strategy on acubic.ai with the person's own eToro or Trading 212 account, where they connect the broker and activate it. It also says whether the plan includes live portfolios. Use it whenever the person wants to automate o
- acubic_project_strategy: Runs a Monte Carlo of 500 paths over 1, 3, 5 or 10 years for one saved strategy, from its walk-forward backtest (the AI Scenario Simulation of acubic.ai): bear case (5th percentile), median, bull case (95th) and the percentile fan. Hypothetical, with a disclosure. Paid plans only
- acubic_get_strategy_history: Returns the Historical tab of one saved strategy: its saved weights bought and held over 1 month to 5 years, with return, CAGR, volatility, Sharpe and maximum drawdown beside the S&P 500 or a custom benchmark, and the daily series. Hypothetical, with a disclosure. For the walk-fo
- acubic_cancel_backtest: Cancels a backtest that is still running, like Cancel on acubic.ai: the allowance it used is returned and the previous saved result stays. Needs the run_id from acubic_run_backtest. To remove a strategy use acubic_delete_strategy.
- acubic_restore_strategy: Restores a strategy deleted with acubic_delete_strategy, with its holdings, settings and backtest, within 30 days. acubic_list_strategies with mode archived lists the ones that can be restored.

Screening checks:
- MCP handshake: pass (Answered in 92ms)
- Domain against threat feeds (Cloudflare security DNS): pass (mcp.acubic.ai, acubic.ai not flagged)
- Published packages against the OSV malicious-package database: n/a (No npm or PyPI package published)
- Hidden instructions or invisible characters in tool text: pass (24 tools read, nothing found)
- Inputs asking for passwords, card numbers or seed phrases: pass (None found)
- Domain and redirects: pass (No redirects off the domain)
- AI review of purpose and tool behavior: pass (No concerns)
