MCP servers › com.algotrada.cubicle › cubicle
MCP server · registry snapshot 2026-10-23 · last tested 2026-10-23
com.algotrada.cubicle/cubicle
Agent trading tools: candles, copy-trading, hire a strategy for your Robinhood vault, pay on chain — the publisher's description
Summary
com.algotrada.cubicle/cubicle is a remote MCP server listed in the official MCP registry at version 1.1.0. On 2026-10-23 ProtocolProbe connected to it in read-only mode and read its inventory: 46 tools, 0 resources and 0 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- not applicable: The version the registry lists can be installed and is not withdrawn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 · Is it safe to install?
Key facts
- Runs
- remote (hosted by the publisher)
- Transport
- streamable HTTP
- Sign-in
- none needed to open a session
- Tools
- 46
- Described as changing data
- 12 of 46 toolsAI-classified
- Topic
- finance-and-paymentsAI-classified
- Pricing
- freemiumAI-classified
- Last tested
- 2026-10-23
Observed fact
This server accepted a session without any credential and lists 3 tools whose name or declaration suggests they change data (studio_move, watch_set, erase). That is our reading of the names; we did not call them. Source: our connection, 2026-10-23.
Worth knowing before you connect it
- 12 tools are described as changing something (plan_claim, follow, stream_key, …): our AI model's reading of the descriptions, not something we tested, and the server opened a session without any credential. We did not call them.
Each line comes from a section below, with its source and date.
How fresh this is
- Live-tested
- yes, a real session (not a text-only review)
- Last tested
- 2026-10-23
- Mode
- read-only (no tool calls)
- Latest version
- 1.1.0, published 2026-10-07 (registry, as of the 2026-10-23 snapshot)
- First listed version
- 2026-10-05 (earliest version still in the registry; older removed versions would be earlier)
- Version history
- 2 versions listed, 2026-10-05 to 2026-10-07; 2 in the 90 days before the 2026-10-23 snapshot.(versions still listed in the registry only)
Most recent 2 versions
1.1.0· 2026-10-071.0.0· 2026-10-05
- Registry data
- snapshot 2026-10-23
- Package and repository
- checked 2026-10-22
- Engine
- mcp-runtime-engine@0.1.0 · sdk@1.32.0
Changes since the last refresh
New in the registry: not in the list of 2026-10-04, listed on 2026-10-23 with version 1.1.0 (published 2026-10-07).
Source: the official MCP Registry list on 2026-10-04 and on 2026-10-23.
What it is
What does this server offer?
Observed inventory12 of 46 tools are described as changing something (creating, editing, deleting, sending or running). For 8 the reading was uncertain, so no mark is shown.
“The whole Cubicle API as data: the studio's eight-state machine and what each gate asks, every tool with the tier that opens it (and whether it is open to the caller), and the flows.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
“The caller's Cubicle account: their tier (free, Cubicle Operators holder, pro-50, max premium-99), their plan and until when, and every capability with whether it is open and which tier opens it.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
- planson 3 other servers
“The Cubicle plans (price per 30 days, what each includes) and exactly how to pay on Robinhood Chain in USDG: the treasury, the token, and — when the subscription vault is live — the two wallet transa…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs
planstring“a plan id (pro-50 or premium-99) to prepare the payment steps for”walletstring“the 0x address of the wallet that will pay — needed for the renewing subscription, which is authorized for that wallet only”
- plan_claimdescribed as changing data
“Claim a plan you paid for on chain: give the payment's transaction hash and the paying wallet's EIP-191 signature over the exact message the plans tool returns ("Cubicle plan claim\nagent: <your agen…”
Publisher declares: read-only no · destructive no · idempotent yes · open-world yes
3 inputs, 2 required
tx_hashstringrequired“the payment transaction's hash (0x + 64 hex)”payer_signature_hexstringrequired“the paying wallet's EIP-191 signature (0x + 130 hex) over the claim message”chainstring“the chain the payment was made on (Cubicle takes plans on Robinhood Chain only)”
“The trading LLM models on the Taifoon venue a trader can study and, on the max plan, follow: each with its status (trading or stopped, derived from its last trade), markets, fills, realized PnL and w…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
- desk_readreads or searches
“The house Nemotron desk (llm-nemotron-fest) as it is: its last turn (every 30 minutes), each market's decision and which reader decided it (the vote rule the Nemotron answers, or Jev), the facts it r…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
marketstring“one market, or every market when absent”
- model_recordreads or searches
“One trading model's record from the venue's first-in-first-out paired closes: realized PnL, maximum drawdown, win rate, per market, and the window.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
modelstringrequired“the model's attribution, from the models tool (starts with llm-)”
- follow_quotereads or searches
“Quote following a trading model (max plan): checks the model is live and followable, validates the follower's sizing (fixed_notional usd, or proportional bps of their balance) and caps (max_notional_…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs, 3 required
modelstringrequired“the model's attribution from the models tool”sizingobjectrequired“{"kind":"fixed_notional","usd":50} or {"kind":"proportional","bps":200}”capsobjectrequired“{"max_notional_usd":100,"max_open_positions":3,"max_daily_loss_usd":40,"markets":["BTC"]}”balance_usdnumber“the follower's balance, to show a mirror's size (optional)”
“Follow a trading model (max plan): creates the follow record — the model, your sizing (fixed_notional usd, or proportional bps of your balance), your caps (max_notional_usd, max_open_positions, max_d…”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
4 inputs, 3 required
modelstringrequired“the model's attribution from the models tool”sizingobjectrequired“{"kind":"fixed_notional","usd":50} or {"kind":"proportional","bps":200}”capsobjectrequired“{"max_notional_usd":100,"max_open_positions":3,"max_daily_loss_usd":40,"markets":["BTC"]}”follower_walletstring“the 0x address your runner signs mirrors with (optional now; required once the venue enforces per-order auth)”
- stream_keycreates or changes datadescribed as changing data
“Cubicle's paid signal stream on the Taifoon coordination layer (pro-50 or premium-99): the desks' world-clock signals and Kronos forecasts arrive as kind signal from venue cubicle, sealed with a topi…”
Publisher declares: read-only no · destructive no · idempotent yes · open-world yes
2 inputs
actionstring“register (default: register or refresh your key), status (what is registered, nothing changes) or forget (remove your key)”x25519string“your X25519 public key: 0x and 64 hex characters (needed for register)”
- followsreads or searches
“Your own follow records (max plan): every follow you created, active, stopped or replaced, with its digest and attribution.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
“Stop following a model at once (any tier may stop): the active follow record is marked stopped and kept; open mirror positions stay yours to manage.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
1 input, 1 required
modelstringrequired“the model's attribution”
Show 34 more tools
- strategiesreads or searches
“The strategies anyone can rent to run a Cubicle spot vault (today: accumulate, which buys a fixed amount of ETH or BTC on an interval up to a budget and never sells): what each does, its parameters, …”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
“FREE, no key: the sha256 (or keccak256) digest of a text, as 64 hex characters, computed here.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 1 required
textstringrequired“the text to hash (UTF-8)”algorithmstring“sha256 (default) or keccak256”
“FREE, no key, no sign-in: the tape's latest price for one market (NQ, ES, YM, BTC, ETH or SOL) with the time of that 1-minute close and whether the tape is stale.”
Publisher declares: read-only yes · destructive no · idempotent no · open-world yes
1 input, 1 required
symbolstringrequired“the market, by ticker”
- strategy_quotereads or searches
“A live quote for one accumulate buy on Robinhood Chain: what a USD amount of USDG buys of ETH or BTC on the best Uniswap route right now, the tape's price, the cost against the tape in bps, and wheth…”
Publisher declares: read-only yes · destructive no · idempotent no · open-world yes
2 inputs, 2 required
assetstringrequired“the asset”usdnumberrequired“USD of USDG to spend”
- my_vaultsreads or searches
“The caller's trading vaults, read from the chain: each with whether its funds are devnet (test money) or mainnet (real), what is in it, what is free, what is set aside as margin, the mandate and who …”
Publisher declares: read-only yes · destructive no · idempotent no · open-world yes
Takes no inputs.
- step_up_receiptdoes something else
“A five-minute proof that the account's owner passed their second factor, for the venue's vault: send it as the x-step-up header of POST /vault/withdraw (api.taifoon.dev/vault/withdraw) with your key.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
Takes no inputs.
- vault_preparedescribed as changing data
“The wallet steps for a Cubicle vault as UNSIGNED transactions and EIP-712 typed data for the owner's own wallet.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
11 inputs, 1 required
ownerstringrequired“the 0x address of the wallet that owns (or will own) the vault”chainnumber“4663 Robinhood Chain (real money) or 36927 the devnet (test money); defaults to the devnet”vaultstring“the vault's 0x address (every call after the first)”kindstring“what the account is for: spot (trades on Uniswap today) or futures (margin; settles when the venue sends statements)”namestring“a name for the vault”deposit_usdnumber“USD of the stable to deposit (second call)”administratorstring“who administers the vault under the mandate (second call), e.g.”margin_usdnumber“margin vaults only: the most the mandate may ever lose (second call)”marketstring“spot administrators only: the market it buys”withdraw_sharesstring“withdrawal step one: whole shares to queue (read balanceOf(owner) on the vault)”claim_sharesstring“withdrawal step two: whole shares to claim (read claimableRedeemRequest(0, owner) on the vault)”
- script_validatecalculates or converts
“Validate a cubicle.script v1 (the YAML text) with the reference validator: the JSON report with every diagnostic (codes C000–C095, file:line:col) and the budget (warm-up bars, memory, nodes per bar).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
scriptstringrequired“the cubicle.script v1 YAML text”
- script_rehearse
“Step a cubicle.script v1 over the deck's own bars with the deterministic reference runner (cubicle-script run): one frame per bar (state, every gate's truth and the two sides it compared, fields, var…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
9 inputs
scriptstring“the cubicle.script v1 YAML text (or use example)”examplestring“a bundled example instead of script: bender-corridor | ny-open-breakout | range-aware-stop”marketstring“default NQ”tfstring“default 1m”fromnumber“unix seconds; with `to`, an explicit sealed window”tonumber“unix seconds (in the past)”hoursnumber“crypto only: the last N sealed hours (default 8)”paramsobject“param overrides {name: number}, clamped to the script's min..max”framesnumber“how many frames to return from the END of the run (default 60, max 600); the summary covers the whole run”
“Where a wallet stands on the way to a funded Cubicle vault, read from the chain (gas, USDG in the wallet, its accounts, the factory's invite gate), and the ONE next step with the tool that does it: c…”
Publisher declares: read-only yes · destructive no · idempotent no · open-world yes
2 inputs
ownerstring“the 0x address of the trader's wallet (defaults to the wallet linked to this principal)”chainnumber“4663 Robinhood Chain (real money, the default) or 36927 the devnet (test money)”
- fund_with_carddescribed as changing data
“A link to buy USDG on Robinhood Chain with a card, bank transfer or Apple/Google Pay through MoonPay, paid straight into the trader's own wallet (Cubicle never holds the money).”
Publisher declares: read-only yes · destructive no · idempotent no · open-world yes
2 inputs, 1 required
ownerstringrequired“the 0x address of the trader's wallet on Robinhood Chain”amount_usdnumber“USD to spend (20 to 10,000; default 100)”
- session_sizereads or searches
“How big to trade the crypto session that is open now (BTC, ETH, SOL): full size when the session is expected to move more than usual, reduced when it should be quiet.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
marketstring“BTC, ETH or SOL (default: all three)”
- workflow_readreads or searches
“Read a trading idea the way the studio does: the deterministic reader fills the 7 parts (markets, trigger, direction, stand aside, stop, target, session) from the trader's OWN words and says which re…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
textstringrequired“everything the trader has said about the rule, in their words”
“Reverse-engineer what the trader POSTED before saying anything about it: a rule in words, a pasted Pine script (read statically, never run) or a chat transcript.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
textstringrequired“what the trader posted, verbatim: the rule, the Pine source or the transcript”
- studio_movedescribed as changing data
“Move the trader's rule through the studio's state machine when forge is refused: score_parts (Jev scores clarity — needs the trader's own TypeSafe key), accept_parts (the trader accepts the rule as r…”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
2 inputs, 1 required
movestringrequired“the move”choicestring“for choose_coverage: approximate or stop”
“The studio machine's FORGED move: compiles the trader's strategy from the gates the tape can measure.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
1 input, 1 required
intentstringrequired“the rule in the trader's words, every part included”
“Grade a forge with Jev (RUBRIC_v1): code checks the facts first, then Jev answers whether the code does what the trader said.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
1 input, 1 required
seed_hashstringrequired“the seed hash forge returned”
- rehearseon 1 other server
“Walk a forged machine over the real tape with the canonical stepper (the last week by default): how many trades it took, the R, and a comparison with a random null.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
2 inputs, 1 required
seed_hashstringrequired“the seed hash forge returned”marketstring“the market to walk, defaults to the one the trader named”
- watch_fieldsreads or searches
“What a strategy test reports at every step the strategy takes: the trader's current list, and the whole vocabulary, grouped by indicator (price, volume, RSI 14, EMA 20, EMA 60, VWAP, the Bollinger ba…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
- watch_setcreates or changes datadescribed as changing data
“Set what the trader's strategy tests report at every step: up to 8 items, each a field id from watch_fields or an expression over those fields (numbers, + - * / and brackets, optionally one compariso…”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
1 input, 1 required
itemsarrayrequired“field ids or expressions, in the order they should be shown”
- strategy_stepsreads or searches
“The steps the trader's last tested strategy took on one market, as the test engine reported them: each step's time, the move (ready to in a trade, and so on), the conditions true at that bar, the tra…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs
marketstring“the market the strategy was tested on (defaults to the newest test)”onlystring“trades = only the steps that opened or closed a trade (default); all = every step”
“Read real candles from the Taifoon tape for one market.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs, 4 required
marketstringrequired“the market”tfstringrequired“timeframe (the time machine serves these; build a 15-minute range from 1m or 5m bars)”fromstringrequired“window start, ISO-8601 UTC”tostringrequired“window end, ISO-8601 UTC, in the past”
“The envelope the forecast sidecar had issued for one market and timeframe by a given time: a MAGNITUDE band (how far price may travel over the next 24 bars, as two prices and a width in ATR), the odd…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 2 required
marketstringrequired“the market”tfstringrequired“timeframe the sidecar forecasts”atstring“ISO-8601 UTC time the envelope must have been issued by (defaults to now); for a replay, the logical clock”
“What the deck's chart would show for one market, timeframe and window, as ONE JSON object computed in code: the bars (count, first and last, the last candle), the indicators drawn, the trader's own m…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
5 inputs, 4 required
marketstringrequired“the market”tfstringrequired“timeframe”fromstringrequired“window start, ISO-8601 UTC”tostringrequired“window end, ISO-8601 UTC, in the past (the logical clock for a replay)”indicatorsarray“indicator ids to include, e.g.”
“The deck's own chart plate for one market, timeframe and window, rendered server-side from the same geometry the screen uses (bars, indicators, the envelope cone when its calibration permits) as a PN…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
5 inputs, 4 required
marketstringrequired“the market”tfstringrequired“timeframe”fromstringrequired“window start, ISO-8601 UTC”tostringrequired“window end, ISO-8601 UTC, in the past”indicatorsarray“indicator ids to draw; defaults to ema20 and envelope”
- drawingsreads or searches
“The trader's own drawings on one market's chart: lines, boxes, paths and notes, each anchored at bars (UTC times) and prices.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
marketstringrequired“the market”
“Draw on the trader's chart, as they ask: a line (two points), a box (two corners), a path (2 to 24 points moving forward in time: a zigzag of legs) or a note (one point and a short word).”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
5 inputs, 3 required
marketstringrequired“the market”kindstringrequired“what to draw”pointsarrayrequired“the anchors, earliest first”inkstring“the ink”textstring“a short word beside it (required for a note), at most 48 characters”
“Remove one of the trader's drawings by its id (from the drawings tool).”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
1 input, 1 required
idstringrequired“the drawing's id as the drawings tool lists it (sk_ and 16 hex characters)”
“Seal a past window of the tape into a FILM: the bars replayed one by one with the trader's drawings and marked levels, optionally the structure computed over the bars (pivots, legs, swings and the ra…”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
14 inputs, 4 required
marketstringrequired“the market”tfstringrequired“timeframe”fromstringrequired“window start, ISO-8601 UTC”tostringrequired“window end, ISO-8601 UTC, in the past”headlinestring“the headline's first part (drawn in parchment), at most 44 characters”headline_goldstring“the headline's second part (drawn in gold)”titlestring“a short name beside the wordmark”kickerstring“a short line at the right, e.g.”structureboolean“draw the computed structure and name the chapters after it”drawingsboolean“include the trader's drawings (default true)”marksboolean“include the trader's marked levels (default true)”machineboolean“include the trades of the trader's rehearsed machine on this market, labelled a rehearsal”palettestring“the inks”secondsnumber“length, 8 to 40 seconds (default 18)”
- replay_open
“Put the trader's chart and its time compressor on a past window: the market, the window, the speed to play it at and, optionally, the moment to hold on (a trade, a sweep, a touch of a level).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
6 inputs, 3 required
marketstringrequired“the market”fromstringrequired“window start, ISO-8601 UTC”tostringrequired“window end, ISO-8601 UTC, in the past”speedstring“how fast to play it: 60, 600 or 6000 times real time, or max (default 600)”focusstring“optional: the moment inside the window to hold the clock at, ISO-8601 UTC”notestring“one short sentence shown beside the card: what to watch for (at most 140 characters)”
- replay_record
“Read back what happened in the trader's last replay of one market: every beat on the tape, each of their strategies' trades and state changes, and their own moves (travel, speed, seek), in order with…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 1 required
marketstringrequired“the market”kindsarray“only these sources or kinds (default: all)”
- imageon 4 other servers
“Look at a chart the trader attached (the id is in the studio state).”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
1 input, 1 required
idstringrequired“the attached image's id”
- skillson 1 other server
“List the Cubicle skill bank: every skill's name, family, grade and status (runnable / stub / concluded).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
- skill_readon 1 other server
“Read one skill's method (its SKILL.md) — only the methodology and engineering skills are readable; strategy, lens, pillar and copy skills are sealed and will be refused.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
namestringrequired“the skill's name as the skills tool lists it”
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 2026-10-23.
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
- Says what the tool does
- 100% of 40 tools
- Says what it returns
- 97% of 29 tools
- States limits, defaults or errors
- 0% of 40 tools
- Says when to use it
- 8% of 39 tools
- Items covered per tool
- 1.8 of 4 on average
Counted from the listing
- Parameters with a description
- 100% of 108
- Tools with a description
- 100% of 46
- Typical description length
- 389 characters
The tool set
Counted from the listing
- Tools
- 46
- Size of the list
- about 10,142 tokens for an agent to load (characters ÷ 4)
- Naming
- 23 of 46 names use single lower-case words
AI reading: easy to mix up
No pair found.
The AI items cover 40 of 46 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, comparing tools within groups of 40. 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 2026-10-23 (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://cubicle.algotrada.com/deck/api/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
"mcpServers": {
"cubicle": {
"url": "https://cubicle.algotrada.com/deck/api/mcp"
}
}
}VS Code · .vscode/mcp.json
{
"servers": {
"cubicle": {
"type": "http",
"url": "https://cubicle.algotrada.com/deck/api/mcp"
}
}
}VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"cubicle","type":"http","url":"https://cubicle.algotrada.com/deck/api/mcp"}'Claude Code
claude mcp add --transport http cubicle https://cubicle.algotrada.com/deck/api/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://cubicle.algotrada.com/deck/api/mcp --transport http
- Optional settings the entry also lists (left out above): Authorization.
- The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
- 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). 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.
Does the registry listing match what we found?
Feature #6The registry verifies a package once, when it is published, and does not re-check it. A difference below is about the listing, not a judgement of the publisher.
| Registry says | We found | Result | Source · date |
|---|---|---|---|
| Remote endpoint cubicle.algotrada.com/deck/api/mcp | Session opened | matches | our test · 2026-10-23 |
| No credential declared as required | Opened a session without any credential | matches | our test · 2026-10-23 |
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.
- 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 2026-10-22. 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. How each check works · Leaderboards
Common questions about com.algotrada.cubicle/cubicle
Answered from the data aboveIs com.algotrada.cubicle/cubicle safe to install?
We do not rate servers as safe or unsafe. 1 of its 2 applicable record checks are met (facts from public records, each listed on this page). What the records show: 12 of its tools describe changing data (our AI model's reading of the descriptions). These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.
Is com.algotrada.cubicle/cubicle free to use?
Its website (cubicle.algotrada.com/) describes a freemium pricing model. This is an AI-classified reading of the page on 2026-10-23, so check the page itself before relying on it.
Does com.algotrada.cubicle/cubicle need an API key or sign-in?
It opened a session without any credential on 2026-10-23. The registry entry declares no required credential; no declaration is not a guarantee.
Has com.algotrada.cubicle/cubicle been security tested?
Partly. 2 of the 14 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. No security verdict is published before verification.
What can com.algotrada.cubicle/cubicle do?
It lists 46 tools. In our AI model's reading of their descriptions (two runs had to agree, nobody checked it by hand), they include tools that read or search, create or change data, delete, calculate or convert and do something else. We did not call any tool, so this describes the text, not the behaviour.
Can com.algotrada.cubicle/cubicle change or delete data?
12 of its tools say in their description that they create, edit, delete, send or run something (our AI model's reading). We did not call any tool, so we cannot say what actually happens.
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.
Similar servers
Same topic · AI-read
- io.github.lightningfaucet/lightning-wallet-mcpLightning Walletalso has tools that calculates or converts, creates or changes data, deletes, does something else, reads or searchescompare with this one
- io.github.lightningfaucet/mcp-serveralso has tools that calculates or converts, creates or changes data, deletes, does something else, reads or searchescompare with this one
- io.github.cnghockey/sats4aiSats4AI - Bitcoin-Powered AI Toolsalso has tools that calculates or converts, creates or changes data, deletes, does something else, reads or searchescompare with this one
- io.github.nirholas/pumpfun-solana-mcppump.fun Solana Dataalso has tools that calculates or converts, creates or changes data, does something else, reads or searchescompare with this one
- io.github.longsizhuo/openinvestopenInvestalso has tools that calculates or converts, creates or changes data, deletes, reads or searchescompare with this one
- ai.vaaya/mcpVaayaalso has tools that creates or changes data, deletes, does something else, reads or searchescompare with this one
Active servers whose topic is also “finance-and-payments” and that have at least one tool of the same kind; most kinds in common first, then most GitHub stars. The topic and the tool kinds are an AI model's reading of the publishers' descriptions, not checked by hand. Similar is not a recommendation.
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: not run · nothing to check it against
- Fake assistant turns: not applicable
- Token passthrough: not applicable
- Token audience: not applicable
- Sign-in redirect: not run · our policy
- Consent handling: not testable from outside
- Sign-in metadata: not applicable
2 exercised12 not run (reason given)4 not applicable
Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 2 of the 14 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.
- 1Inventory
tool-listReads the declared tools, resources and prompts.exercised - 2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.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; 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; 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; 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; 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; 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 - 12Hidden content
audience-hidingChecks resources that hide content from the user.This check needs content the server returns, and nothing was read or 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
- 13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable - 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 - 18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.No sign-in (OAuth) metadata is published, so there are no sign-in addresses to check.not applicable
Source: our own test, 2026-10-23, 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
- 1,898 msConnected after 0 redirects. No credential was sent or needed.
- Read the inventory: 46 tools, 0 resources, 0 prompts.
- 5,870 msFinished: 2 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.
“Free tier at launch: metered replay sessions on crypto tapes, full receipts.”
“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. “com.algotrada.cubicle/cubicle: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/com.algotrada.cubicle/cubicle
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/com.algotrada.cubicle/cubicle)
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.
Write to hello@protocolprobe.com · corrections log · methodology