MCP servers › com.vectorialdata › terminal
MCP server · registry snapshot 2026-11-07 · last tested 2026-11-07
terminal MCP server
Registry name com.vectorialdata/terminal
Vectorial Data Terminal: Hyperliquid, Polymarket & yield for AI agents — the publisher's title
by vectorialdata.com · domain (the registry's namespace rule)repository owner on GitHub: vectorialdata (organization)Source ↗Website ↗
Self-custodial Hyperliquid perps, Polymarket, staking and yield for AI agents, with a kill switch. — the publisher's description
Summary
com.vectorialdata/terminal is a remote MCP server listed in the official MCP registry at version 1.3.1, under the namespace of the domain vectorialdata.com. Its linked repository is github.com/vectorialdata/terminal-mcp; GitHub reports its owner as vectorialdata, an organization. On 2026-11-07 ProtocolProbe connected to it in read-only mode and read its inventory: 68 tools, 0 resources and 0 prompts.
Record checks
5 of 5 record checks met · 4 do not apply
- met: Registry entry is active and says how to run it
- met: Source repository link opens
- met: Repository is not archived
- met: Code pushed to the repository in the 90 days before our check
- met: 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- not applicable: The version the registry lists can be installed and is not withdrawn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: 0 stars (ranked from 10)
From public records, not a safety rating. Each check with its reason · Is it safe to install?
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
- Repository
- public
- Tools
- 68
- Last tested
- 2026-11-07
Tool list size
18,173 tokens on Claude Opus 5.5
Added to every request that loads this server's tools (68 tools). Counted with Anthropic's token counter on 2026-11-09, from the tool list we read on 2026-11-07. 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 2026-11-07 (terminal.vectorialdata.com), 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 (1.3.1).
Observed fact
This server accepted a session without any credential and lists 19 tools whose name or declaration suggests they change data (place_order, submit_order, close_position, cancel_order, submit_intent and 14 more). That is our reading of the names; we did not call them. Source: our connection, 2026-11-07.
How fresh this is
- Live-tested
- yes, a real session (not a text-only review)
- Last tested
- 2026-11-07
- Mode
- read-only (no tool calls)
- Latest version
- 1.3.1, published 2026-11-06 (registry, as of the 2026-11-07 snapshot)
- First listed version
- 2026-11-06 (earliest version still in the registry; older removed versions would be earlier)
- Version history
- 5 versions listed, all on 2026-11-06; 5 in the 90 days before the 2026-11-07 snapshot.(versions still listed in the registry only)
Most recent 5 versions
1.3.1· 2026-11-061.3.0· 2026-11-061.2.0· 2026-11-061.1.0· 2026-11-061.0.0· 2026-11-06
- Registry data
- snapshot 2026-11-07
- Package and repository
- checked 2026-11-07
- 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; repository link does not open; repository archived; no push in over 365 days. Does not apply: listed version cannot be installed or is withdrawn. 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 2026-11-06, listed on 2026-11-07 with version 1.3.1 (published 2026-11-06).
Source: the official MCP Registry list on 2026-11-06 and on 2026-11-07.
What it is
What does this server offer?
Observed inventoryNone of its 68 tools are described as changing anything. For 68 the reading was uncertain, so no mark is shown.
- get_docson 16 other servers
“The complete Agent API manual (markdown): auth, trading, limits, withdrawals, error catalog.”
Publisher declares: read-only yes · open-world no
Takes no inputs.
- list_marketson 65 other servers
“Tradeable markets with live prices and the precision metadata needed to size orders (size_decimals, min_size, price rules, $10 min notional).”
Publisher declares: read-only yes · open-world yes
Takes no inputs.
- get_registration_challengeon 3 other servers
“Step 1 of creating an agent account: get a nonce+message to sign (EIP-191) with the agent's own EVM wallet.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
1 input, 1 required
addressstringrequired“The agent wallet address (0x…)”
- register_agenton 212 other servers
“Step 2: register with the signed challenge.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
4 inputs, 4 required
addressstringrequired“Your agent wallet address (0x…): the same one you passed to get_registration_challenge”noncestringrequired“The nonce returned by get_registration_challenge”signaturestringrequired“EIP-191 signature of the challenge message”labelstringrequired“A name for this agent, 1–60 characters, shown on your account”
- get_accounton 181 other servers
“Your agent account: status, mode (paper|live), scopes, live balances, deposit address, limits.”
Publisher declares: read-only yes · open-world yes
Takes no inputs.
- get_positionson 28 other servers
“Open positions (live: venue truth; paper: from your fills).”
Publisher declares: read-only yes · open-world yes
Takes no inputs.
- list_orderson 47 other servers
“Your authoritative order ledger (cursor-paginated).”
Publisher declares: read-only yes · open-world yes
3 inputs
statusstring“Filter: prepared|submitted|resting|filled|rejected|cancelled|expired”limitinteger“Page size, 1–200”beforestring“Cursor from a previous page's next_cursor”
- get_metricson 15 other servers
“Your tear-sheet: win rate, net PnL, fees, drawdown, Sharpe, equity curve — computed server-side from the authoritative ledger.”
Publisher declares: read-only yes · open-world yes
2 inputs
windowstring“Stats window: 7d, 30d, 90d or all”modestring“Which ledger to measure: paper or live”
- place_orderon 54 other servers
“Place an order.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world yes
11 inputs, 3 required
marketstringrequired“Symbol, e.g.”sidestringrequired“buy = go long (or reduce a short); sell = go short (or reduce a long)”typestringrequired“market = fills now at a protected price; limit = rests at limit_price”sizenumber“Size in coins, e.g.”risk_usdnumber“Risk-first sizing: dollars at risk to the stop”stop_pricenumber“Required with risk_usd; also becomes the SL”limit_pricenumber“Limit price in USD; required when type is limit”tpnumber“Take-profit trigger price in USD (optional reduce-only bracket)”slnumber“Stop-loss trigger price in USD (optional reduce-only bracket)”reduce_onlyboolean“true = this order can only reduce an existing position, never open or flip one”client_order_idstring“Idempotency key”
- submit_orderon 8 other servers
“Execute a prepared LIVE order with your trading key's signatures (one per typed_data, in order).”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world yes
2 inputs, 2 required
order_idstringrequired“The order_id returned by place_order”signaturesarrayrequired“One 0x… EIP-712 signature per actions[i].typed_data from place_order, in order”
- close_positionon 6 other servers
“Close an open position (fully or size_pct).”
Publisher declares: read-only no · destructive yes · idempotent no · open-world yes
2 inputs, 1 required
marketstringrequired“Symbol of the open position, e.g.”size_pctnumber“Percent of the position to close; omit to close all of it”
- protect_position
“Attach post-hoc reduce-only TP/SL triggers to an open position.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
3 inputs, 1 required
marketstringrequired“Symbol of the open position, e.g.”tpnumber“Take-profit trigger price in USD”slnumber“Stop-loss trigger price in USD”
Show 56 more tools
- cancel_orderon 58 other servers
“Cancel a resting order by ledger id.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world yes
1 input, 1 required
order_idstringrequired“The order_id of a resting order (see list_orders)”
- submit_intenton 2 other servers
“Execute a prepared intent (cancel/protect/withdraw) with the wallet's signatures.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world yes
2 inputs, 2 required
intent_idstringrequired“The intent_id returned by close_position, protect_position, cancel_order or prepare_withdrawal”signaturesarrayrequired“One 0x… EIP-712 signature per actions[i].typed_data of the intent, in order”
- log_decisionon 3 other servers
“Log WHY you traded (your audit trail and future public track record).”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
3 inputs, 1 required
reasoningstringrequired“Why you traded (or didn't), in plain words; kept in your audit trail”order_idstring“The order_id this decision belongs to, to correlate them (optional)”modelstring“The model or strategy that made the decision (optional)”
- get_limitson 11 other servers
“Your bounded-autonomy rails (caps, allowlists, pending loosenings).”
Publisher declares: read-only yes · open-world yes
Takes no inputs.
- update_limits
“Adjust rails.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world yes
4 inputs
max_order_notional_usdnumber or null“Max USD notional of a single order; null = no cap (loosening waits 24h)”max_position_notional_usdnumber or null“Max total exposure in USD across perps, predictions and Earn; null = no cap”max_daily_loss_usdnumber or null“Daily realized-loss breaker in USD (UTC day); null = no cap”asset_allowlistarray or null“Markets you may open, e.g.”
- set_modeon 1 other server
“Flip paper ↔ live.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world yes
1 input, 1 required
modestringrequired“paper = simulated fills, nothing to sign; live = real funds from your trading wallet”
- kill_switchon 1 other server
“Instant pause: every subsequent prepare/submit is rejected until resume_trading (which needs the wallet's signature).”
Publisher declares: read-only no · destructive no · idempotent yes · open-world yes
Takes no inputs.
- resume_trading
“Reactivate after kill_switch.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
2 inputs
noncestring“Second call only: the nonce returned by the first call”signaturestring“EIP-191 signature of the challenge message, by the account wallet”
- get_withdrawals_config
“Money-out policy: mode (disabled|autonomous|human_passkey), strict destinations, guardian link.”
Publisher declares: read-only yes · open-world yes
Takes no inputs.
- list_pending_withdrawals
“Your withdraw intents and their approval lifecycle (human_passkey).”
Publisher declares: read-only yes · open-world yes
Takes no inputs.
- prepare_withdrawalon 2 other servers
“Prepare a withdrawal (USDC → Arbitrum).”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
2 inputs, 2 required
destinationstringrequired“0x address that receives the USDC; it must already be in your withdrawal allowlist”amount_usdnumberrequired“USDC to withdraw from Hyperliquid”
- guardian_status
“Human guardian link state (human_passkey mode).”
Publisher declares: read-only yes · open-world yes
Takes no inputs.
- invite_guardian
“Mint a single-use invite (48h) for a human to become this agent's withdrawal guardian.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
Takes no inputs.
- list_webhookson 73 other servers
“Your webhook endpoints (max 5): url, subscribed event types, status, failure counters.”
Publisher declares: read-only yes · open-world yes
Takes no inputs.
- create_webhookon 39 other servers
“Register a webhook endpoint (public https).”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
2 inputs, 1 required
urlstringrequired“Public https endpoint that accepts POSTed JSON events”event_typesarray“Subset of the catalog from list_webhooks; omit = all”
- get_webhookon 26 other servers
“One webhook + its last 20 delivery attempts (status codes, retries, dead letters) — the delivery debugging surface.”
Publisher declares: read-only yes · open-world yes
1 input, 1 required
webhook_idstringrequired“The webhook id (see list_webhooks)”
- delete_webhookon 56 other servers
“Remove a webhook endpoint (its queued deliveries are dropped).”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world yes
1 input, 1 required
webhook_idstringrequired“The webhook id to delete (see list_webhooks)”
- test_webhookon 30 other servers
“Send a synchronous signed test event to a webhook and report the receiver's response — verify your endpoint + HMAC handling before relying on real events.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
1 input, 1 required
webhook_idstringrequired“The webhook id to send a test event to (see list_webhooks)”
- list_copy_leaders
“Strategies available to copy, with the SAME numbers a human sees, as a DAILY snapshot (UTC: the same object all day): time-weighted return net of fees (immune to the leader's deposits and withdrawals…”
Publisher declares: read-only yes · open-world yes
Takes no inputs.
- get_copy_status
“What this agent is copying, per leader.”
Publisher declares: read-only yes · open-world yes
Takes no inputs.
- follow_leader
“Start copying a leader with real funds: mode 'live' mirrors from your copy wallet — create and fund it first with create_copy_wallet.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world yes
3 inputs, 3 required
leader_idintegerrequired“The leader's numeric id (see list_copy_leaders)”allocation_usdnumberrequired“Recorded with the follow.”modestringrequired“'live' = real funds from your copy wallet.”
- unfollow_leader
“Stop copying a leader.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world yes
1 input, 1 required
leader_idintegerrequired“The numeric id of the leader you stop copying (see get_copy_status)”
- create_copy_wallet
“Create the copy wallet needed for LIVE copying.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world yes
3 inputs, 1 required
owner_public_keystringrequired“Your P-256 PUBLIC key in SPKI form (PEM or base64).”noncestring“Second call only: the nonce returned by the first call.”signaturestring“Second call only: EIP-191 signature of the returned message by your agent wallet.”
- get_trading_wallet
“Your trading wallet — the Hyperliquid account LIVE orders trade from: address and balances, trading key status (and when to renew it), how to fund it, fees (0.25% per perps trade, the same everyone p…”
Publisher declares: read-only yes · open-world yes
Takes no inputs.
- create_trading_wallet
“Create your trading wallet (required for LIVE trading; your agent wallet must have nothing open).”
Publisher declares: read-only no · destructive no · idempotent yes · open-world yes
3 inputs, 1 required
owner_public_keystringrequired“Your P-256 PUBLIC key in SPKI form (PEM or base64).”noncestring“Second call only: the nonce returned by the first call.”signaturestring“Second call only: EIP-191 signature of the returned message by your agent wallet.”
- authorize_trading_key
“Authorize the key that signs your LIVE orders.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
4 inputs
trading_key_addressstring“A NEW 0x address whose key you generated to sign orders (not your agent wallet nor the trading wallet)”trading_key_proofstring“EIP-191 signature of trading_key_message by the trading key”timeinteger“Last call only: the `time` returned by the previous call”owner_signaturestring“Last call only: your OWNER key's signature over payload_b64”
- send_trading_funds_home
“Move USDC from your trading wallet back to your agent wallet, inside Hyperliquid (the destination is always your own agent wallet).”
Publisher declares: read-only no · destructive yes · idempotent no · open-world yes
3 inputs, 1 required
amount_usdnumberrequired“At most 2 decimals (it is exactly what gets signed).”timeinteger“Second call only: the `time` returned by the first call (the nonce you signed)”owner_signaturesobject“Second call only: { sendAsset?: sig, usdSend?: sig }”
- get_copy_wallet
“Your copy wallet: address to fund, whether it is ready for live copying, and the custody terms.”
Publisher declares: read-only yes · open-world yes
Takes no inputs.
- get_scope_challenge
“Step 1 of gaining a new scope ('copy' to follow leaders, 'withdraw' to move funds).”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
1 input, 1 required
intentstringrequired“enable_copy = gain the copy scope; enable_withdraw = gain the withdraw scope”
- escalate_scope
“Step 2: submit the signature from get_scope_challenge and receive a NEW api key carrying the scope.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
3 inputs, 3 required
noncestringrequired“The nonce returned by get_scope_challenge”signaturestringrequired“EIP-191 signature of the challenge message”intentstringrequired“The same intent you passed to get_scope_challenge”
- rotate_keyon 13 other servers
“Mint a fresh api key, optionally NARROWING its scopes.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
1 input
scopesarray“Subset of your current scopes.”
- list_prediction_marketson 2 other servers
“Prediction markets you can trade now (Polymarket): events with their markets and, per outcome, the CLOB token_id you trade and its price (a probability 0–1 = USD per share; a winning share pays $1).”
Publisher declares: read-only yes · open-world yes
5 inputs
querystring“Free-text search, e.g.”event_slugstring“Return one event by its slug (from an earlier listing)”tagstring“A Polymarket tag slug, e.g.”limitinteger“Events per page, 1–50”offsetinteger“How many events to skip (pagination)”
- get_prediction_book
“Live order book of one prediction outcome (best first): best bid/ask, mid, tick size and the top levels with sizes in shares.”
Publisher declares: read-only yes · open-world yes
1 input, 1 required
token_idstringrequired“The outcome's decimal CLOB token id (from list_prediction_markets)”
- get_predictions_account
“Your predictions account: your deposit wallet (a Polymarket smart wallet only your agent wallet controls), activation steps, cash (pUSD = USD), WHERE TO DEPOSIT (any supported chain; lands as pUSD in…”
Publisher declares: read-only yes · open-world yes
Takes no inputs.
- activate_predictions
“Enable prediction markets (once, gasless).”
Publisher declares: read-only no · destructive no · idempotent yes · open-world yes
2 inputs
activation_idstring“Second call only”signaturesarray“Second call only: one 0x… signature per action, in order”
- place_prediction_orderon 1 other server
“Buy or sell a prediction outcome with a fill-or-kill market order (fills entirely at a protected price or nothing happens).”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
7 inputs, 2 required
token_idstringrequired“The outcome's CLOB token id (decimal string) from list_prediction_markets”sidestringrequired“buy = buy shares of this outcome; sell = sell shares you hold”amount_usdnumber“BUY only: USD to spend (min $1; fees go on top)”max_spend_usdnumber“BUY only: cap on the all-in spend, fees included”sharesnumber“SELL only: how many shares to sell”limit_pricenumber“Optional worst price as a probability 0–1 (buy: max, sell: min); it can only tighten the house guard”client_order_idstring“Your own id for this order (up to 64 characters)”
- submit_prediction_order
“Execute a prepared prediction order with your agent wallet's signature over its typed_data.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world yes
2 inputs, 2 required
order_idstringrequired“The order_id returned by place_prediction_order”signaturestringrequired“0x… EIP-712 signature by your agent wallet”
- get_prediction_positions
“Your open prediction positions (Polymarket's numbers): shares, average and current price, cost, value, P&L, and whether a resolved winner is waiting to be collected (collectable).”
Publisher declares: read-only yes · open-world yes
Takes no inputs.
- send_predictions_home
“Move predictions cash back to YOUR agent wallet as native USDC (polygon, arbitrum or base; min $2) through Polymarket's bridge — the destination is always your own agent wallet.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
3 inputs
amount_usdnumber“USD of predictions cash to send (min $2)”allboolean“true = send all your predictions cash”to_chainstring“Chain where your agent wallet receives native USDC: polygon, arbitrum or base”
- collect_prediction_winnings
“Collect resolved WINNING positions into your predictions cash (Polymarket usually does this automatically at resolution; use this if get_prediction_positions shows collectable: true).”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
1 input
condition_idstring“Collect only this market (0x condition id); omit to collect every resolved winner”
- submit_predictions_batch
“Execute a prepared send_predictions_home or collect_prediction_winnings batch with your agent wallet's signature (gasless, via Polymarket's relayer).”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world yes
2 inputs, 2 required
batch_idstringrequired“The batch_id returned by send_predictions_home, collect_prediction_winnings or move_funds”signaturestringrequired“0x… EIP-712 signature by your agent wallet”
- get_earn
“Earn for agents: HLP (Hyperliquid's market-making vault), HYPE staking and USDC lending — rates, fees, lockups and validators; whether you can enter (live, 'earn' in venue_allowlist, certification); …”
Publisher declares: read-only yes · open-world yes
Takes no inputs.
- certify_earn
“One-time Earn eligibility certification (valid 1 year): the agent's OPERATOR certifies it is not in an excluded jurisdiction (read get_earn → certification_text first).”
Publisher declares: read-only no · destructive no · idempotent yes · open-world yes
1 input
confirm_operator_locationboolean“true only if the agent's OPERATOR is outside the excluded jurisdictions although this request comes from one”
- earn_hlp_deposit
“Deposit USDC from your trading wallet into HLP.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
1 input, 1 required
amount_usdnumberrequired“USDC to put into HLP (min $5.03); the 0.55% entry fee is taken from it”
- earn_hlp_withdraw
“Withdraw from HLP back to your trading wallet (free; after the 4-day lockup).”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
2 inputs
amount_usdnumber“USD to withdraw from HLP”allboolean“true = withdraw your whole HLP position”
- buy_hype
“Buy HYPE with USDC in your trading wallet (spot, immediate-or-cancel at up to +1% from mid; fee 0.25% in USDC; Hyperliquid's minimum order is $10).”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
1 input, 1 required
amount_usdnumberrequired“USDC to spend on HYPE (Hyperliquid's minimum spot order is $10)”
- sell_hype
“Sell spot HYPE for USDC in your trading wallet (immediate-or-cancel at no less than -1% from mid; the same spot sell fee everyone pays).”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
2 inputs
amount_hypenumber“Spot HYPE to sell”allboolean“true = sell all your free spot HYPE”
- stake_hype
“Stake spot HYPE with a validator (get_earn → products.staking.validators, neutral order).”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
2 inputs, 2 required
amount_hypenumberrequired“Spot HYPE to stake; the 0.25% entry fee is kept from it”validatorstringrequired“0x validator address”
- delegate_hype
“Delegate HYPE that is already in your staking balance (free): finishes a stake whose delegation didn't go through, or re-delegates after an undelegate.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
2 inputs, 2 required
amount_hypenumberrequired“HYPE already in your staking balance to delegate”validatorstringrequired“0x address of the validator (see get_earn → products.staking.validators)”
- unstake_hype
“Unstake HYPE (free): with validator, undelegate it first (a delegation is locked 1 day); then Hyperliquid's 7-day withdrawal to spot starts.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
2 inputs, 1 required
amount_hypenumberrequired“HYPE to unstake”validatorstring“The validator to undelegate from; omit to only withdraw HYPE already undelegated”
- earn_usdc_deposit
“Lend USDC on Base in our Earn USDC vault (Morpho, Gauntlet USDC Prime) from your trading wallet's address on Base — move USDC there first with move_funds perps → earn_usdc.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
2 inputs
amount_usdnumber“USDC on Base to lend”allboolean“true = lend all your USDC on Base except what gas needs”
- earn_usdc_withdraw
“Withdraw from the Earn USDC vault to your USDC on Base (free; then move_funds earn_usdc → perps to trade with it).”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
2 inputs
amount_usdnumber“USDC to withdraw from the vault to your USDC on Base”allboolean“true = withdraw your whole Earn USDC position”
- transfer_spot_perps
“Move USDC between spot and perps inside your trading wallet (classic accounts only; free).”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
2 inputs, 2 required
amount_usdnumberrequired“USDC to move”tostringrequired“Where the USDC goes: perps or spot”
- move_funds
“Move money between YOUR accounts, in any direction: perps (trading wallet on Hyperliquid), predictions (your Polymarket deposit wallet) and earn_usdc (your trading wallet's USDC on Base).”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
4 inputs, 2 required
fromstringrequired“Account the money leaves: perps (trading wallet), predictions (deposit wallet) or earn_usdc (trading wallet on Base)”tostringrequired“Account the money goes to (different from `from`)”amount_usdnumber“USD to move”allboolean“true = move everything that can be moved”
- submit_operation
“Execute a prepared Earn / move operation with your signatures, one per step and in order (owner steps: base64 P-256 signature over payload_b64; trading_key steps: 0x… EIP-712 signature).”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world yes
3 inputs, 2 required
operation_idstringrequired“The operation_id returned by the prepare tool”signaturesarrayrequired“One signature per signatures_needed step, in order: base64 P-256 for owner steps, 0x… EIP-712 for trading_key steps”owner_public_keystring“Your OWNER P-256 public key (SPKI PEM or base64).”
- list_operationson 11 other servers
“Your last Earn / move operations: what each did, step by step, and how it ended.”
Publisher declares: read-only yes · open-world yes
1 input
limitinteger“How many recent operations, 1–50”
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 2026-11-07.
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
- 100% of 120
- Tools with a description
- 100% of 68
- Typical description length
- 275 characters
The tool set
Counted from the listing
- Tools
- 68
- Size of the list
- about 13,157 tokens for an agent to load (characters ÷ 4)
- Naming
- 68 of 68 names use snake_case
AI reading: easy to mix up
No pair found.
The AI items cover 0 of 68 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 2026-11-07 (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://terminal.vectorialdata.com/api/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
"mcpServers": {
"terminal": {
"url": "https://terminal.vectorialdata.com/api/mcp"
}
}
}VS Code · .vscode/mcp.json
{
"servers": {
"terminal": {
"type": "http",
"url": "https://terminal.vectorialdata.com/api/mcp"
}
}
}VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"terminal","type":"http","url":"https://terminal.vectorialdata.com/api/mcp"}'Claude Code
claude mcp add --transport http terminal https://terminal.vectorialdata.com/api/mcp
Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)
{
"mcpServers": {
"terminal": {
"type": "streamableHttp",
"url": "https://terminal.vectorialdata.com/api/mcp",
"disabled": false,
"autoApprove": []
}
}
}Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project
{
"mcpServers": {
"terminal": {
"httpUrl": "https://terminal.vectorialdata.com/api/mcp"
}
}
}OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project
[mcp_servers.terminal] url = "https://terminal.vectorialdata.com/api/mcp"
Zed · Zed settings file (command: zed: open settings file)
{
"context_servers": {
"terminal": {
"url": "https://terminal.vectorialdata.com/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://terminal.vectorialdata.com/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.
- 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.
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 terminal.vectorialdata.com/api/mcp | Session opened | matches | our test · 2026-11-07 |
| No credential declared as required | Opened a session without any credential | matches | our test · 2026-11-07 |
| Repository github.com/vectorialdata/terminal-mcp | Opens publicly | matches | api.github.com · 2026-11-07 |
Who made it?
Feature #7 · lineage
Facts about the publisher. We do not turn them into a trust score.
- Namespace
- com.vectorialdata
- GitHub owner
- an organization (vectorialdata)
- Repository
- github.com/vectorialdata/terminal-mcp
- Stars
- 0
- Repository age
- 0–30 days
- Last push
- 0–30 days ago
- Archived
- no
- Security policy
- SECURITY.md
Source: the registry entry and api.github.com · 2026-11-07; security policy read from GitHub · 2026-11-07.
Publish this server? Run these checks against it yourself before release, from your own machine: a server the command starts, or your own server at its URL after a one-time proof that you control it: npx protocolprobe-selftest.
Choosing
Record checks
Public records · not a safety rating5 of 5 record checks met · 4 do not apply
- Not ranked by downloads: a remote server publishes no download figure
- Not ranked by stars: 0 stars (ranked from 10)
- MetRegistry entry is active and says how to run itActive, with a package or a remote address.
- MetSource repository link opensThe linked GitHub repository is public.
- MetRepository is not archivedNot archived.
- MetCode pushed to the repository in the 90 days before our checkLast push 0-30 days before our check.
- MetRepository publishes a security policy (SECURITY.md)SECURITY.md found.
- 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 2026-11-07 (security policy 2026-11-07). 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 com.vectorialdata/terminal
Answered from the data aboveWho publishes com.vectorialdata/terminal?
The registry ties the namespace com.vectorialdata to the domain vectorialdata.com; only its owner can publish under it. Its linked repository is github.com/vectorialdata/terminal-mcp; GitHub reports its owner as vectorialdata, an organization. These are facts from the registry and GitHub, not a rating.
Is com.vectorialdata/terminal safe to install?
We do not rate servers as safe or unsafe. 5 of its 5 applicable record checks are met (facts from public records, each listed on this page). What the records show: Its source repository opens publicly. Its repository had a push in the last 90 days. These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.
Does com.vectorialdata/terminal need an API key or sign-in?
It opened a session without any credential on 2026-11-07. The registry entry declares no required credential; no declaration is not a guarantee.
Has com.vectorialdata/terminal 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. ProtocolProbe publishes no security verdict for a named server.
Does com.vectorialdata/terminal publish a security policy?
Yes: its repository has a public security policy (github.com/vectorialdata/terminal-mcp/blob/HEAD/SECURITY.md). That is the publisher's statement, not permission for us to test the server, and we call none of its tools.
Where is the source code of com.vectorialdata/terminal?
In github.com/vectorialdata/terminal-mcp, which opens publicly.
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: 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. 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
- 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 - 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, 2026-11-07, 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
- 2,231 msConnected after 0 redirects. No credential was sent or needed.
- Read the inventory: 68 tools, 0 resources, 0 prompts.
- 6,770 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.
“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.vectorialdata/terminal: MCP server record.” Data checked 2026-11-07. https://protocolprobe.com/mcp/servers/com.vectorialdata/terminal
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.vectorialdata/terminal)
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