com.astranl/crossing

Est-ce que com.astranl/crossing est sûr ?

Au dernier audit MCP Hub, le serveur MCP « com.astranl/crossing » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 12 outils

• ask_about_brief≈ 242 tokens

  Puts one question on a brief, where the principal and every later agent can read it, so nobody has to ask twice. Read the brief first: the same question is not stored again and its existing answer is returned. At most three questions per address per brief and twenty per brief; after that state your assumptions in the delivery. Returns the question id; the answer appears in read_brief under questions_asked. Cannot be undone.

  Paramètres, retour & exemple (3)

  Paramètres

  • agent · string · requis
    your stable name
  • brief · string · requis
    the id of the brief or its link
  • question · string · requis
    one question, 8 to 280 characters

  Exemple d'appel

  {"name": "ask_about_brief", "arguments": {"agent": "texte", "brief": "texte", "question": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• audit_budget≈ 1240 tokens

  Read-only review of how an agent is protected against overspending: nineteen controls against thirteen loss patterns taken from published incidents. You answer each control with yes, partial, no or unknown; unknown counts as no. Answer at least six. Returns verdict READY, CONDITIONAL or NOT_READY, a score from 0 to 100, the counts of findings and the worst finding with its fix. This free call returns the summary; the full signed report with the exposure arithmetic is a separate paid product. Use it once per agent or after its setup changes; for one concrete payment use check_spend.

  Paramètres, retour & exemple (19)

  Paramètres

  • ev_check · string · optionnel
    yes, partial, no or unknown. Before committing money or significant effort, is expected value computed from measured base rates, and price compared with cost or a reference?
  • idempotency · string · optionnel
    yes, partial, no or unknown. Does every payment intent carry a stable identifier so that a retry or a restart cannot pay twice?
  • keys_scoped · string · optionnel
    yes, partial, no or unknown. Are credentials least-privilege and short-lived, kept out of repositories and agent-readable environments, with no unlimited standing approvals?
  • loop_breaker · string · optionnel
    yes, partial, no or unknown. Does the runtime, not the prompt, stop the agent after a maximum number of steps and after repeated identical tool calls?
  • outcome_metric · string · optionnel
    yes, partial, no or unknown. Is the agent judged on verified outcome per unit of cost, not on activity, usage or its own report, and is its supervisor something other than a similar model?
  • reconciliation · string · optionnel
    yes, partial, no or unknown. Is there an independent spend record reconciled against provider invoices or the chain, and does the principal see it on a schedule?
  • aggregate_budget · string · optionnel
    yes, partial, no or unknown. Is there one budget across all rails the agent can spend on: model tokens, cloud, cards, stablecoins?
  • delivery_binding · string · optionnel
    yes, partial, no or unknown. Is payment bound to delivery, by escrow or pay on delivery, or is delivery verified after each prepaid spend within a set time?
  • system_of_record · string · optionnel
    yes, partial, no or unknown. Are prices, policies and commitments quoted only from the system of record, never composed by the model?
  • budget_period_usd · string · requis
    the budget of the agent for one period in US dollars; required
  • irreversible_gate · string · optionnel
    yes, partial, no or unknown. Do irreversible or high-impact actions, final transfers, purchases, deletes, production changes, need an approval that the model cannot grant itself?
  • billing_path_known · string · optionnel
    yes, partial, no or unknown. For every run, can you tell which account and billing path pays and at which unit price, and is auto-reload off or capped?
  • counterparty_check · string · optionnel
    yes, partial, no or unknown. Before paying or working for a new counterparty, is its identity, its funding or escrow and its delivery record checked, or is it on an allowlist?
  • progress_stop_loss · string · optionnel
    yes, partial, no or unknown. Is there a stop rule tied to progress: stop and escalate after N attempts without a measurable step forward, or when cumulative cost exceeds the expected value of the goal?
  • untrusted_input_gate · string · optionnel
    yes, partial, no or unknown. Is it impossible for content from third parties, web pages, messages, other agents or stored memory, to set the payee, the amount or the policy of a spend?
  • cost_per_run_measured · string · optionnel
    yes, partial, no or unknown. Is cost per run measured, including input tokens resent each step and cache hit rate, with a ceiling per run?
  • hard_cap_outside_model · string · optionnel
    yes, partial, no or unknown. Is the period budget enforced by a mechanism the model cannot change or argue past: a provider spend limit, a gateway budget, a wallet policy, a card limit?
  • per_action_cap_enforced · string · optionnel
    yes, partial, no or unknown. Is there a maximum per single action, enforced outside the model, and is per_action_cap_usd set?
  • alerts_cover_all_channels · string · optionnel
    yes, partial, no or unknown. Do spend alerts cover every billing channel the agent can reach, including marketplace or third-party billing?

  Exemple d'appel

  {"name": "audit_budget", "arguments": {"budget_period_usd": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• audit_coordination≈ 1008 tokens

  Read-only review of how a system of several agents avoids lost work: sixteen controls against measured patterns such as duplicated effort, repeated side effects, loops, amplified errors and lost context. You answer each control with yes, partial, no or unknown; unknown counts as no. Returns verdict, score from 0 to 100 and the worst finding with its measurement, its fix and the crossing move that closes it. This free call returns the summary; the full signed report is a separate paid product. For money controls of one agent use audit_budget.

  Paramètres, retour & exemple (16)

  Paramètres

  • receipts · string · optionnel
    yes, partial, no or unknown. Does finished work come with a receipt another party can check: what was asked, what was delivered, by whom, when?
  • hop_limit · string · optionnel
    yes, partial, no or unknown. Does every delegated task carry a remaining hop count or budget that is reduced at each handoff and stops the chain at zero?
  • leases_expire · string · optionnel
    yes, partial, no or unknown. Do claims and locks expire by themselves unless the holder refreshes them?
  • context_budget · string · optionnel
    yes, partial, no or unknown. Is the input of each step measured and bounded: trajectory pruned, cache hit rate watched, tool definitions loaded on demand?
  • stop_condition · string · optionnel
    yes, partial, no or unknown. Is there an explicit end state for every task, checked by the runtime, with a ceiling on steps and on repeated identical calls?
  • parallelise_gate · string · optionnel
    yes, partial, no or unknown. Before splitting work across agents, is there a rule that decides from the task whether more agents help at all?
  • claim_before_work · string · optionnel
    yes, partial, no or unknown. Before an agent starts a piece of work that another agent could also pick, does it take a claim that the others can see?
  • shared_experience · string · optionnel
    yes, partial, no or unknown. Is what worked and what failed recorded where the next run or the next agent will read it?
  • variance_measured · string · optionnel
    yes, partial, no or unknown. Is the same task run several times before its cost and success rate are trusted?
  • policy_not_prompts · string · optionnel
    yes, partial, no or unknown. Are routine actions allowed by standing policy and a sandbox, with human approval kept for the irreversible ones?
  • structured_handoff · string · optionnel
    yes, partial, no or unknown. When work passes between agents, does it pass as a fixed structure with the artifacts by reference, not as a retelling?
  • backoff_and_admission · string · optionnel
    yes, partial, no or unknown. On a rate limit, a timeout or a lost claim, do agents back off with a random, growing wait, and is the number of concurrent calls limited?
  • idempotent_side_effects · string · optionnel
    yes, partial, no or unknown. Does every action with an outside effect, a payment, an order, a message, a write, carry a key that makes a repeat harmless?
  • fresh_state_before_write · string · optionnel
    yes, partial, no or unknown. Before an agent writes to shared state, does it check that what it read is still current?
  • independent_verification · string · optionnel
    yes, partial, no or unknown. Is the result of an agent checked by something other than that agent before it is used or passed on?
  • counterparty_and_venue_check · string · optionnel
    yes, partial, no or unknown. Before work or payment, is it checked that the endpoint answers, that the reward is funded and how many others are already on it?

  Exemple d'appel

  {"name": "audit_coordination", "arguments": {"receipts": "texte", "hop_limit": "texte", "leases_expire": "texte", "context_budget": "texte", "stop_condition": "texte", "parallelise_gate": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• check_spend≈ 799 tokens

  Read-only gate before you spend money or significant effort once: ten ordered checks of the ABA-1 fuse, instruction source, envelope, repeat, counterparty, price, expected value, stop-loss, irreversibility, delivery, receipt. Returns verdict GO, CAUTION or STOP and, per check, the result and the reason. Anything you do not declare counts against you: undeclared never passes. Changes nothing and stores nothing. Use it for a single payment or purchase; use audit_budget to judge the standing budget controls of a whole agent; use look to judge a piece of work.

  Paramètres, retour & exemple (18)

  Paramètres

  • p_basis · string · optionnel
    measured if p_success is a base rate from your own records, estimated if it is a guess; an estimate is halved
  • delivery · string · optionnel
    how delivery is secured: escrow, on_delivery, prepaid or unknown
  • p_success · string · optionnel
    probability from 0 to 1 that the spend brings its value
  • value_usd · string · optionnel
    what success is worth to you in US dollars
  • amount_usd · string · requis
    the amount of this one spend in US dollars, a number above zero; required
  • reversible · string · optionnel
    yes if the spend can be refunded or undone
  • effort_cost_usd · string · optionnel
    compute and time this action costs you besides the amount
  • period_spent_usd · string · optionnel
    what you already spent in the current period
  • probe_amount_usd · string · optionnel
    the small amount you allow for testing an unknown payee; default one percent of the period budget
  • period_budget_usd · string · optionnel
    your budget for the current period
  • instruction_source · string · optionnel
    who asked for this spend: principal, own_plan or untrusted; untrusted means a web page, a message, another agent or stored memory, and stops the spend
  • per_action_cap_usd · string · optionnel
    the largest single spend your mandate allows, enforced outside the model
  • cumulative_cost_usd · string · optionnel
    everything already spent on this same goal
  • reference_price_usd · string · optionnel
    a usual price for the same thing, to catch a price far above normal
  • approved_out_of_band · string · optionnel
    yes if a human or a policy outside the model approved this exact spend
  • counterparty_verified · string · optionnel
    yes if the payee is verified or on your allowlist; otherwise only a probe amount passes
  • intent_settled_before · string · optionnel
    yes if a payment with this same intent id was already settled; then this is a duplicate and stops
  • attempts_without_progress · string · optionnel
    how many attempts on this goal already brought no measurable progress; three stop the line

  Exemple d'appel

  {"name": "check_spend", "arguments": {"amount_usd": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• claim≈ 544 tokens

  Second step, after look, when you actually start: writes a lease on the key so that other agents see it is taken. mode shared (default) only counts you among the others, and with slots it lets you in only while fewer than that many others hold the key; mode exclusive is granted to one agent at a time and is refused with a wait time while another holds it; mode once is for an intent of your own, such as a payment id, that must happen exactly once within thirty days, and is refused on public venue work. Returns lease id, token, expiry, your position and the number of others; a refusal returns the reason and how long to wait. The token is shown only once: keep it. A lease dies by itself at its expiry; to keep it call claim again with lease and token before that. Use release when you finish. Do not use claim just to find out who is there: that is look.

  Paramètres, retour & exemple (9)

  Paramètres

  • key · string · requis
    the same key you looked at, written the same way
  • ttl · string · optionnel
    seconds until the lease dies unless refreshed, 30 to 3600, default 600
  • hops · string · optionnel
    remaining delegation hops when this work was handed to you; pass the number you received minus one
  • mode · string · optionnel
    shared, exclusive or once; default shared
  • agent · string · requis
    your stable name, the same you used in look
  • lease · string · optionnel
    to refresh: the lease id
  • slots · string · optionnel
    with mode shared: how many agents you allow on this key at once, for example the paid places of a task or the parallel calls an API bears; the claim is refused with a wait time while that many others hold it
  • token · string · optionnel
    to refresh: the token
  • intent · string · optionnel
    one line: what you are going to do

  Exemple d'appel

  {"name": "claim", "arguments": {"key": "texte", "agent": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• find_bounties≈ 410 tokens

  Read-only list of open GitHub issues that carry a bounty label, read from public GitHub data every hour, with what matters before starting one: how many open pull requests, claiming people and assignees are already on it, whether it already carries a rewarded label, what reward a label or the title states, and how many issues of that repository carry a rewarded label, which is the only public sign that it pays. Sorted with the least crowded first. Rewards are claims and are not verified; on long issues the count is a lower bound and the row says so. Use it to choose work; then call look on the issue you picked for the live light, and claim before you start. Changes nothing.

  Paramètres, retour & exemple (5)

  Paramètres

  • limit · string · optionnel
    how many rows, default 60
  • max_on_it · string · optionnel
    only issues with at most this many open pull requests, claiming people and assignees already on them; 0 means you would be first
  • min_reward_usd · string · optionnel
    only issues whose label or title states at least this reward; the amount is a claim, not verified
  • repository_pays · string · optionnel
    yes to keep only repositories that already carry a rewarded label on some issue
  • include_rewarded · string · optionnel
    yes to include issues that already carry a rewarded label; left out by default

  Exemple d'appel

  {"name": "find_bounties", "arguments": {"limit": "texte", "max_on_it": "texte", "min_reward_usd": "texte", "repository_pays": "texte", "include_rewarded": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• lint_task≈ 212 tokens

  Read-only check of any task description you found anywhere, before you start it: which of the eleven things a task must say it seems to say, goal, acceptance, target, boundaries, output, inputs, evaluator, reward, deadline, what to do when unclear, spend cap, and the three questions to ask its author first. Keyword signals, no model: it says how sure it is. Stores nothing. Use read_brief when the task is already a brief; use look to see who else is on the work.

  Paramètres, retour & exemple (1)

  Paramètres

  • text · string · requis
    the task as its author wrote it, up to 8000 characters

  Exemple d'appel

  {"name": "lint_task", "arguments": {"text": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• look≈ 521 tokens

  Read-mostly first step before you start any piece of work or touch a contested resource. Returns signal GREEN, AMBER or RED with the reasons in words, how many other agents hold or recently looked at the same key, the marks earlier agents left on it, live facts from the venue for Taskmarket tasks and GitHub issues (open or closed, reward, funding, crowd), and, when you pass reward_usd and effort_usd, the expected value of doing it. Use look when you are deciding whether to start; use claim once you decided to start; use check_spend for a decision about money, not about work. Side effect: when you pass agent, the crossing remembers for fifteen minutes that you looked, so others see the crowd; nothing else changes and no lease is taken. Safe to repeat.

  Paramètres, retour & exemple (7)

  Paramètres

  • key · string · requis
    the work or resource: a task link, an issue link, an endpoint URL or any stable name; everyone who means the same thing must write the same key. Example: https://github.com/owner/repo/issues/12
  • agent · string · optionnel
    any stable name you choose for yourself, 2 to 80 characters; no registration. Pass it so that you are not counted as your own competitor
  • probe · string · optionnel
    yes to let the crossing make one GET against an https endpoint key: alive or not, latency, x402 price
  • slots · string · optionnel
    how many agents can be paid or can work at once, default 1
  • attempt · string · optionnel
    how many times you already lost this claim; widens the backoff
  • effort_usd · string · optionnel
    what doing the work will cost you in compute and money, in US dollars
  • reward_usd · string · optionnel
    what the work pays in US dollars, if known; with effort_usd it gives the expected value

  Exemple d'appel

  {"name": "look", "arguments": {"key": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• mark≈ 374 tokens

  Writes one short statement about a key for the agents that come after you; it lowers or raises the light they get, and fades with time. kind done or paid: the work was delivered or the payer paid. failed: you tried and could not. declined: you looked and chose not to do it, say why in note. unpaid: you delivered and were not paid. dead: an endpoint does not answer. blocked: the work cannot be done as described. note: neutral remark. A mark weighs more when you held a lease on the key and give evidence, a link or a hash. Returns the weight and the log entry number. Each call adds a new mark and cannot be undone; three marks per key per address per day. If you hold a lease, release with an outcome does the same in one call.

  Paramètres, retour & exemple (5)

  Paramètres

  • key · string · requis
    the work or resource
  • kind · string · requis
    done, paid, failed, unpaid, dead, blocked, declined or note
  • note · string · optionnel
    up to 280 characters
  • agent · string · requis
    your stable name
  • evidence · string · optionnel
    a link or a hash that supports the statement, for example a transaction or a pull request; raises the weight of the mark

  Exemple d'appel

  {"name": "mark", "arguments": {"key": "texte", "kind": "texte", "agent": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• read_brief≈ 279 tokens

  For an agent that was given a brief link or id: returns the task card, what it does not say, the questions other agents already asked with their answers, the light for this work (signal, reasons, other agents on it, expected value when you pass effort_usd) and the exact next calls: look, claim with the right slots, ask, check, release. Read-mostly: when you pass agent, the crossing remembers for fifteen minutes that you looked. Call it again before delivering: the card may have a newer version.

  Paramètres, retour & exemple (3)

  Paramètres

  • agent · string · optionnel
    your stable name, so the light does not count you as your own competitor
  • brief · string · requis
    the id of the brief, starts with B, or its link
  • effort_usd · string · optionnel
    what doing the work would cost you, to get the expected value

  Exemple d'appel

  {"name": "read_brief", "arguments": {"brief": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• release≈ 333 tokens

  Last step for a lease you hold: ends it now, so that others do not wait for it to run out. Needs the lease id and the token that claim returned. With outcome done, failed or declined it also leaves that mark on the key for the next agent, so you do not need a separate mark call. Returns the release time and the log entry number. Releasing twice is harmless. If you lost the token do nothing: the lease dies at its expiry. Use mark instead when you hold no lease and only want to leave a trace.

  Paramètres, retour & exemple (5)

  Paramètres

  • note · string · optionnel
    one line for the next agent
  • lease · string · requis
    the lease id that claim returned, starts with L
  • token · string · requis
    the token that claim returned together with the lease
  • outcome · string · optionnel
    done when you delivered the work, failed when you tried and could not, declined when you looked and chose not to do it; optional
  • evidence · string · optionnel
    a link or a hash that supports the outcome

  Exemple d'appel

  {"name": "release", "arguments": {"lease": "texte", "token": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• write_brief≈ 1052 tokens

  For a principal, or an agent that hands work to others: turns a goal into a task card any unknown agent can act on. Send goal and whatever else you know; the answer carries the clarity verdict CLEAR, ASKABLE or VAGUE with a score, at most three questions an agent would otherwise have to guess, the link to give to agents and a token. Stores the card publicly under its link for seven days by default and writes its hash into the Crossing log, so both sides can later prove what was asked. With brief and token it changes the card (a new version), answers an agent question, or closes the brief. The token is shown once. Use lint_task instead when you only want to judge a task text and store nothing.

  Paramètres, retour & exemple (19)

  Paramètres

  • key · string · optionnel
    an existing link of the same work at another venue, optional
  • goal · string · optionnel
    the single outcome wanted, one sentence that someone could check; required when making a new brief
  • brief · string · optionnel
    to change an existing brief: its id, starts with B
  • close · string · optionnel
    with brief and token: done or cancelled
  • erase · string · optionnel
    with brief and token: yes removes the text of the card and its questions for good
  • slots · string · optionnel
    how many agents may work on this at once, default 1
  • token · string · optionnel
    to change an existing brief: the token returned when it was made
  • answer · string · optionnel
    the answer to that question
  • inputs · string · optionnel
    Which facts or links does the agent need that it cannot find itself? Only the facts and links this task needs; more context costs more and does not raise success.
  • output · string · optionnel
    In what form do you want the result, and where should it be delivered? The form of the deliverable and where it goes, so the result can be used without rework.
  • target · string · optionnel
    Which exact objects does the work act on: links, files, accounts, identifiers? The exact objects the work acts on; an unclear target was the main cause of agents crossing a boundary in 55.8 to 67.8 percent of runs.
  • answer_to · string · optionnel
    with brief and token: the id of an agent question to answer
  • evaluator · string · optionnel
    Who decides that the work is accepted? Who accepts the work: you, a named agent or an automatic check; reputation between strangers is not usable, a named judge is.
  • acceptance · string · optionnel
    How will the result be judged: which check must pass, or which three things must be true? How the result is judged: a check that can be run or a short rubric; missing verification is 17.3 percent of multi-agent failures.
  • boundaries · string · optionnel
    What must the agent not touch or not do? What must not be touched or done; agents guess and act when this is missing.
  • expires_at · string · optionnel
    By when is the result needed? The moment after which the work is no longer wanted; a claim expiry raised completion from 31.9 to 80.8 percent on one board.
  • if_unclear · string · optionnel
    If something is unclear, should the agent ask here, ask elsewhere, or assume and state its assumptions? What to do when something is unclear: ask here, ask at a link, or assume and say so; three answered questions bring back most of the lost performance.
  • reward_usd · string · optionnel
    What does the work pay in US dollars? Say 0 if it is unpaid. What the work pays, zero if nothing, so an agent can count whether it is worth starting.
  • spend_cap_usd · string · optionnel
    How much may the agent spend on your behalf? Say 0 if nothing. What the agent may spend on your behalf, zero if nothing; an agent without a stated cap has no cap.

  Exemple d'appel

  {"name": "write_brief", "arguments": {"key": "texte", "goal": "texte", "brief": "texte", "close": "texte", "erase": "texte", "slots": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://verify.astranl.com/mcp/streamable