MCP servers › ai.acubic › acubic
MCP server · registry snapshot 2026-11-18 · last tested 2026-11-18
acubic MCP server
Registry name ai.acubic/acubic
by acubic.ai · domain (the registry's namespace rule)Website ↗
Explain, screen, build and backtest systematic portfolios from eToro and Trading 212 universes. — the publisher's description
Summary
ai.acubic/acubic is a remote MCP server listed in the official MCP registry at version 1.0.0, under the namespace of the domain acubic.ai. On 2026-11-18 ProtocolProbe connected to it in read-only mode and read its inventory: 24 tools, 12 resources and 3 prompts.
Record checks
1 of 2 record checks met · 7 do not apply
- met: Registry entry is active and says how to run it
- not met: Source repository link opens
- not applicable: Repository is not archived
- not applicable: Code pushed to the repository in the 90 days before our check
- not applicable: Repository publishes a security policy (SECURITY.md)
- not applicable: Package names its licence with a standard (SPDX) identifier
- not applicable: The version the registry lists can be installed and is not withdrawn
- not applicable: npm package carries build provenance (attestation)
- not applicable: No known critical or high advisory in the package or its dependencies
- Not ranked by downloads: a remote server publishes no download figure
- Not ranked by stars: no public GitHub repository
From public records, not a safety rating. Each check with its reason
Operate this server? Correct a fact · README badge · Run the checks yourself · Claim it
Key facts
- Runs
- remote (hosted by the publisher)
- Transport
- streamable HTTP
- Your own values
- none declared (not a guarantee)
- Sign-in
- none needed to open a session
- Tools
- 24
- Last tested
- 2026-11-18
Tool list size
18,920 tokens on Claude Opus 5.5
Added to every request that loads this server's tools (24 tools). Counted with Anthropic's token counter on 2026-11-18, from the tool list we read on 2026-11-18. Median across 28,560 counted servers: 2,657 tokens. How it is counted
How a client gets in
Connects without signing in
Read from the server's public metadata on 2026-11-18 (mcp.acubic.ai), in our read-only connection; no tool was called. It may have changed since. How it is read
Tool list at the three APIs
Not sent yet for this version (1.0.0).
Observed fact
This server accepted a session without any credential and lists 4 tools whose name or declaration suggests they change data (acubic_create_strategy, acubic_update_strategy, acubic_run_backtest, acubic_delete_strategy). That is our reading of the names; we did not call them. Source: our connection, 2026-11-18.
How fresh this is
- Live-tested
- yes, a real session (not a text-only review)
- Last tested
- 2026-11-18
- Mode
- read-only (no tool calls)
- Latest version
- 1.0.0, published 2026-11-17 (registry, as of the 2026-11-18 snapshot)
- First listed version
- 2026-11-17 (earliest version still in the registry; older removed versions would be earlier)
- Registry data
- snapshot 2026-11-18
- Package and repository
- checked 2026-11-18
- Engine
- mcp-runtime-engine@0.1.0 · sdk@1.32.0
Dead or stale signals
None found in the records we hold
Looked for and not found: deprecated in the registry. Does not apply: listed version cannot be installed or is withdrawn; repository link does not open; repository archived; no push in over 365 days. Each line is a dated fact from a public record. It does not say whether the server still works, and a record can change after the date shown.
Changes since the last refresh
New in the registry: not in the list of 2026-11-17, listed on 2026-11-18 with version 1.0.0 (published 2026-11-17).
Source: the official MCP Registry list on 2026-11-17 and on 2026-11-18.
What it is
What does this server offer?
Observed inventoryNone of its 24 tools are described as changing anything. For 24 the reading was uncertain, so no mark is shown.
- acubic_search_knowledge
“Searches what Acubic publishes (blog, guides, methodology, FAQ, pricing) and returns passages with links to cite.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
6 inputs, 1 required
querystringrequired“What to look for, in plain words.”kindsarray“Limit to some kinds of content.”limitinteger“Page size.”cursorstring“A previous next_cursor.”response_formatstringlocalestring“The language of this conversation.”
- 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.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs
experiencestring“Limit to one experience level.”risk_levelstring“One risk level only (largest accepted drawdown).”response_formatstringlocalestring“The language of this conversation.”
- 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 prod…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
5 inputs, 1 required
querystringrequired“A ticker (AAPL, BTCUSD), an ISIN (US0378331005) or part of a name.”asset_classstring“Limit to one asset class.”limitinteger“Maximum matches.”response_formatstringlocalestring“The language of this conversation.”
- acubic_screen_universe
“Applies filter rules (e.g.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
11 inputs
filter_rulesarray“Rules combined with AND.”asset_classesarray“Narrow to these asset classes first.”regionsarray“Narrow to these regions first.”sectorsarray“Narrow to these sectors first.”includeobject“Ids per acubic_list_strategy_options section (index: indices).”order_bystring“Order the example rows by this metric.”orderstring“Sort direction.”limitinteger“Page size.”cursorstring“A previous next_cursor.”response_formatstringlocalestring“The language of this conversation.”
- 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,…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs, 1 required
topicstringrequired“A term or option id, e.g.”kindstring“Limit to one kind of term.”response_formatstringlocalestring“The language of this conversation.”
- 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 recipe…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs
experiencestring“Keep only the options available at this experience level.”sectionstring“One section, or all (always concise).”response_formatstringlocalestring“The language of this conversation.”
- 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.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
localestring“The language of this conversation.”
- 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.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
6 inputs
modestring“Kind of strategy.”name_containsstring“Case-insensitive part of the name.”limitinteger“Page size.”cursorstring“A previous next_cursor.”response_formatstringlocalestring“The language of this conversation.”
- 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 it…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
5 inputs
strategy_idstring“The strategy to read.”build_idstring“A build_id of acubic_create_strategy; resolves to the strategy once saved.”holdings_limitinteger“Holdings to return.”response_formatstringlocalestring“The language of this conversation.”
- 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, drawdow…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
5 inputs, 1 required
strategy_idstringrequired“The strategy whose latest saved backtest to read.”run_idstring“A finished run of acubic_run_backtest to read.”includearray“equity_series: curves vs SPY (up to 200 points); performance_summary: report rows.”response_formatstringlocalestring“The language of this conversation.”
- 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).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 2 required
strategy_idstringrequired“The strategy the run belongs to.”run_idstringrequired“The run_id acubic_run_backtest returned.”localestring“The language of this conversation.”
- 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.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 1 required
build_idstringrequired“The build_id acubic_create_strategy returned.”localestring“The language of this conversation.”
Show 12 more tools
- 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 br…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
5 inputs
strategy_idstring“One strategy; omit for all that have a live or paper book.”limitinteger“Page size.”cursorstring“A previous next_cursor.”response_formatstringlocalestring“The language of this conversation.”
- 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.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
29 inputs, 1 required
namestringrequireddescriptionstringtemplate_idstring“An id from acubic_list_strategy_templates: a preset, or advanced for the engine.”experiencestring“Legacy: beginner or intermediate with risk_level selects a preset; prefer template_id.”risk_levelstring“Preset only (legacy path): largest acceptable drawdown; prefer template_id.”asset_classesarrayregionsarraysectorsarrayincludeobject“Ids per acubic_list_strategy_options section (index: indices).”asset_countinteger“Number of assets.”asset_count_rangeobject“Instead of asset_count (default 15 to 25).”position_sizingobject“Default: the sizes recommended for the number of assets.”class_position_sizingobject“Per-asset-class sizes overriding position_sizing.”rankingobject“A preset: card (its menu: acubic_list_strategy_templates).”allocationstring“Weighting id (acubic_list_strategy_options, weighting); default: the recommended one.”filter_rulesarray“Each rule: metric, op, value in the metric's unit (US dollars for market_cap, percent for pct metrics: 40 = 40%).”excluded_symbolsarray“Names removed from the screened pool (Step 1).”locked_symbolsarray“Always held, exempt from every filter.”custom_symbolsarray“Tickers to add to the pool, checked as on acubic.ai.”correlation_limitnumber“Not offered yet: omit it unless acubic_list_strategy_options shows it offered; then 0.50-0.95, step 0.05 (preset: 0.80).”selection_limitsobject“Min/max share of the selection per sector, country or asset class.”candidates_idstring“A ranked list from acubic_rank_candidates (valid 1 hour).”selected_symbolsarray“Hand-picked names of the candidates_id list (not with allocation or correlation limits).”select_countinteger“Top N to select (10, 15, 20, 30 or 50 within the count range; see selection.select_counts).”index_cardboolean“Build the level's index card (template level_mix.index_card) instead of ranked stocks; no ranking or allocation.”
and 4 more not listed here.
- acubic_update_strategy
“Updates the name, description, filter rules, include lists or Exclude list of one saved strategy, and lists each previous value.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
8 inputs, 1 required
strategy_idstringrequired“The strategy to change.”namestringdescriptionstring or null“null clears it.”filter_rulesarrayexcluded_symbolsarray“The whole Exclude list (replaces the saved one; [] clears it; up to 200 tickers, none locked).”includeobject“Ids per acubic_list_strategy_options section (index: indices).”response_formatstringlocalestring“The language of this conversation.”
- 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 t…”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
7 inputs, 1 required
strategy_idstringrequired“The saved strategy to backtest.”yearsinteger“Length of the test in years.”rebalance_freqstring“M monthly, Q quarterly, A annual (needs at least 3 years).”transaction_cost_bpsnumber“Cost of each buy and sell in basis points.”client_request_idstring“Idempotency key.”response_formatstringlocalestring“The language of this conversation.”
- 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).”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
3 inputs, 1 required
strategy_idstringrequired“The draft or paper-money strategy to delete.”confirm_tokenstring“For clients without elicitation: the confirm_token from the first call's confirmation_required result, sent once the person agreed.”localestring“The language of this conversation.”
- 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, co…”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
27 inputs
candidates_idstring“A ranked list from acubic_rank_candidates (valid 1 hour).”template_idstring“An id from acubic_list_strategy_templates: a preset, or advanced for the engine.”experiencestring“Legacy: beginner or intermediate with risk_level selects a preset; prefer template_id.”risk_levelstring“Preset only (legacy path): largest acceptable drawdown; prefer template_id.”asset_classesarrayregionsarraysectorsarrayincludeobject“Ids per acubic_list_strategy_options section (index: indices).”asset_countinteger“Number of assets.”asset_count_rangeobject“Instead of asset_count (default 15 to 25).”position_sizingobject“Default: the sizes recommended for the number of assets.”class_position_sizingobject“Per-asset-class sizes overriding position_sizing.”rankingobject“A preset: card (acubic_list_strategy_templates).”filter_rulesarray“Each rule: metric, op, value in the metric's own unit.”excluded_symbolsarray“Names removed from the screened pool (Step 1).”locked_symbolsarray“Always selected, exempt from every filter.”custom_symbolsarray“Tickers to add to the pool, checked as on acubic.ai.”correlation_limitnumber“Not offered yet: omit it unless acubic_list_strategy_options shows it offered; then 0.50-0.95, step 0.05 (preset: 0.80).”selection_limitsobject“Min/max share of the selection per sector, country or asset class.”selected_symbolsarray“Preview a hand-picked selection of candidates_id (not with allocation or correlation limits).”select_countinteger“Top N to select (10, 15, 20, 30 or 50 within the count range; see selection.select_counts).”recipe_idstring“A recipe id (acubic_list_strategy_options, recipes): sets ranking, sectors, allocation and asset count unless given; your filter_rules add to its own.”limitinteger“Rows per page.”cursorstring“A previous next_cursor.”client_request_idstring“Idempotency key.”
and 2 more not listed here.
- 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.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
4 inputs
strategy_idstring“The saved strategy whose suggested portfolio is regenerated.”suggestion_idstring“Read a suggestion still being computed (from a running result).”client_request_idstring“Idempotency key.”localestring“The language of this conversation.”
- 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.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 1 required
strategy_idstringrequired“The strategy to continue on acubic.ai.”localestring“The language of this conversation.”
- 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 cas…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs, 1 required
strategy_idstringrequired“The saved strategy to project.”horizonstring“How far ahead to simulate.”response_formatstringlocalestring“The language of this conversation.”
- 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 …”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
5 inputs, 1 required
strategy_idstringrequired“The saved strategy.”horizonstring“Defaults to 1y, as on acubic.ai.”custom_benchmarkarray“Up to 10 instruments with weights.”response_formatstringlocalestring“The language of this conversation.”
- 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.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
3 inputs, 2 required
strategy_idstringrequired“The strategy the run belongs to.”run_idstringrequired“The run_id acubic_run_backtest returned.”localestring“The language of this conversation.”
- acubic_restore_strategy
“Restores a strategy deleted with acubic_delete_strategy, with its holdings, settings and backtest, within 30 days.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
2 inputs, 1 required
strategy_idstringrequired“A deleted strategy (acubic_list_strategies mode archived).”localestring“The language of this conversation.”
Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-11-18.
How well are its tools described?
Features #4 and #5
How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.
Descriptions
AI reading of each description
No AI reading was available for this server's tools (the two runs did not agree, or the listing was not reviewed).
Counted from the listing
- Parameters with a description
- 83% of 155
- Tools with a description
- 100% of 24
- Typical description length
- 366 characters
The tool set
Counted from the listing
- Tools
- 24
- Size of the list
- about 36,136 tokens for an agent to load (characters ÷ 4)
- Naming
- 24 of 24 names use snake_case
AI reading: easy to mix up
No pair found.
The AI items cover 0 of 24 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.
How do I add it to my client?
Config from the registry entry
From the remote endpoint (Streamable HTTP)
We connected to this URL on 2026-11-18 (a read-only session: no tool was called).
Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.
Claude Desktop or claude.ai
Settings → Connectors → Add custom connector, then paste: https://mcp.acubic.ai/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
"mcpServers": {
"acubic": {
"url": "https://mcp.acubic.ai/mcp"
}
}
}VS Code · .vscode/mcp.json
{
"servers": {
"acubic": {
"type": "http",
"url": "https://mcp.acubic.ai/mcp"
}
}
}VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"acubic","type":"http","url":"https://mcp.acubic.ai/mcp"}'Claude Code
claude mcp add --transport http acubic https://mcp.acubic.ai/mcp
Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)
{
"mcpServers": {
"acubic": {
"type": "streamableHttp",
"url": "https://mcp.acubic.ai/mcp",
"disabled": false,
"autoApprove": []
}
}
}Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project
{
"mcpServers": {
"acubic": {
"httpUrl": "https://mcp.acubic.ai/mcp"
}
}
}OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project
[mcp_servers.acubic] url = "https://mcp.acubic.ai/mcp"
Zed · Zed settings file (command: zed: open settings file)
{
"context_servers": {
"acubic": {
"url": "https://mcp.acubic.ai/mcp"
}
}
}Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 --server-url https://mcp.acubic.ai/mcp --transport http
- The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
- Zed's docs we read on 2026-10-26 describe remote servers by URL and do not name the transport.
- The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.
Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21; Cline, Gemini CLI, OpenAI Codex and Zed 2026-10-26). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.
What do the published files and outside lists say?
Read as text · nothing run · no tool called
Package files
- MCP SDK in the package files. Not read yet: added with the next daily run.
- Build workflow. Not read yet: added with the next daily run.
Outside lists
- CVE records (NVD). No CVE record in the NVD feeds we read links this server's repository. Source: read 2026-11-18. This product uses the NVD API but is not endorsed or certified by the NVD.
- GitHub advisories. No GitHub advisory names this entry's listed package. Source: read 2026-11-18. GitHub Advisory Database, CC BY 4.0
- Docker MCP catalogue. Not in the Docker MCP catalogue on 2026-11-18. Source: read 2026-11-18.
- Cline marketplace. Not in the Cline marketplace on 2026-11-18. Source: read 2026-11-18.
Own host
- security.txt. No security.txt at https://mcp.acubic.ai/.well-known/ (HTTP 404, 2026-11-18). security.txt found at https://acubic.ai/.well-known/security.txt (Contact given; expires 2027-10-01). Source: mcp.acubic.ai/.well-known/security.txt · read 2026-11-18.
- A2A agent card. No A2A agent card at https://mcp.acubic.ai/.well-known/ (HTTP 404, 2026-11-18). No A2A agent card at https://acubic.ai/.well-known/ (HTTP 404, 2026-11-18). Source: mcp.acubic.ai/.well-known/agent-card.json · read 2026-11-18.
Read as text from published files and outside lists. Nothing was installed or run, and no tool was called. A fact, not a rating. How each fact is read
Does the registry listing match what we found?
Feature #6The registry checks an entry when it is published (each new version), and nothing re-checks it on a schedule. A difference below is about the listing, not a judgement of the publisher.
| Registry says | We found | Result | Source · date |
|---|---|---|---|
| Remote endpoint mcp.acubic.ai/mcp | Session opened | matches | our test · 2026-11-18 |
| No credential declared as required | Opened a session without any credential | matches | our test · 2026-11-18 |
Choosing
Record checks
Public records · not a safety rating1 of 2 record checks met · 7 do not apply
- Not ranked by downloads: a remote server publishes no download figure
- Not ranked by stars: no public GitHub repository
- MetRegistry entry is active and says how to run itActive, with a package or a remote address.
- Not metSource repository link opensThe registry entry gives no repository link.What changes this check: This check opens the repository link in the registry entry. GitHub's documentation describes changing a repository's visibility in its Settings, under Danger Zone, Change visibility. GitHub: setting repository visibility
- Does not applyRepository is not archivedNo public GitHub repository to read.
- Does not applyCode pushed to the repository in the 90 days before our checkNo public GitHub repository to read.
- Does not applyRepository publishes a security policy (SECURITY.md)No public GitHub repository to read.
- Does not applyPackage names its licence with a standard (SPDX) identifierRemote server: it ships no package.
- Does not applyThe version the registry lists can be installed and is not withdrawnRemote server: it ships no package.
- Does not applynpm package carries build provenance (attestation)Remote server: it ships no package.
- Does not applyNo known critical or high advisory in the package or its dependenciesRemote server: it ships no package.
Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-11-18. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating, and the same rules apply to every server. How each check works · Leaderboards · How we stay neutral
Common questions about ai.acubic/acubic
Answered from the data aboveWho publishes ai.acubic/acubic?
The registry ties the namespace ai.acubic to the domain acubic.ai; only its owner can publish under it. These are facts from the registry and GitHub, not a rating.
Does ai.acubic/acubic need an API key or sign-in?
It opened a session without any credential on 2026-11-18. The registry entry declares no required credential; no declaration is not a guarantee.
Has ai.acubic/acubic been security tested?
Partly. 5 of the 16 checks that apply to it were exercised. It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. ProtocolProbe publishes no security verdict for a named server.
Found this page useful?
Anonymous · no sign-inA quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.
Compare with another server
Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.
Security testing
What did we test, and what did we leave out?
18 checks · features #1, #2
Open without sign-in
It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security score is given; a check we did not run is never counted as passed.
- Inventory: exercised
- Hidden instructions: exercised
- Real execution: not run · our policy
- Secret leak: not run · nothing to check it against
- Internal addresses: not run · our policy
- Unconfirmed changes: not run · our policy
- Bad input: not run · our policy
- Model requests: not run · nothing to check it against
- Sensitive questions: not run · nothing to check it against
- Folder boundary: not run · our policy
- Log leaks: not run · nothing to check it against
- Hidden content: exercised
- Fake assistant turns: exercised
- Token passthrough: not applicable
- Token audience: not applicable
- Sign-in redirect: not run · our policy
- Consent handling: not testable from outside
- Sign-in metadata: exercised
5 exercised11 not run (reason given)2 not applicable
Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 5 of the 16 checks that apply to it were exercised. We do not publish security-check outcomes for named servers. These 18 checks are separate from the record checks at the top of this page, which read public records only.
- 1Inventory
tool-listReads the declared tools, resources and prompts.exercised - 2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised - 12Hidden content
audience-hidingChecks resources that hide content from the user.exercised - 13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.exercised - 18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.exercised
- 3Real execution
real-executionCalls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy - 4Secret leak
canary-leakPlants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 5Internal addresses
ssrfChecks whether a tool can be steered to internal addresses.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy - 6Unconfirmed changes
write-without-confirmationChecks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy - 7Bad input
error-handlingSends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy - 8Model requests
samplingChecks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 9Sensitive questions
elicitation-sensitive-dataChecks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 10Folder boundary
root-boundaryChecks whether the server reaches outside the folders it was given.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy - 11Log leaks
logging-side-channelChecks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 16Sign-in redirect
open-redirectChecks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy - 17Consent handling
confused-deputyChecks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside
- 14Token passthrough
token-passthroughChecks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable - 15Token audience
token-audience-validationChecks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable
Source: our own test, 2026-11-18, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.
What happened during the test?
Feature #8
The steps in order, as the test record holds them.
- 0 msStarted a read-only session with the server's remote endpoint
- 2,590 msConnected after 0 redirects. No credential was sent or needed.
- Read the inventory: 24 tools, 12 resources, 3 prompts.
- 16,240 msFinished: 5 checks exercised.
Reference
How is it classified?
18 fields
One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.
“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.
Cite or correct this page
Sources and corrections
Suggested citation
ProtocolProbe. “ai.acubic/acubic: MCP server record.” Data checked 2026-11-18. https://protocolprobe.com/mcp/servers/ai.acubic/acubic
Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.
As JSON: this record in the API · API documentation.
Badge for your README
[](https://protocolprobe.com/mcp/servers/ai.acubic/acubic)
It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.
Something wrong, or is this yours?
If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here, except for a server whose operator has claimed it and given permission (that server's page says so).
Write to hello@protocolprobe.com · corrections log · methodology