com.straelo/relay

Est-ce que com.straelo/relay est sûr ?

Au dernier audit MCP Hub, le serveur MCP « com.straelo/relay » 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

• blockchain_intelligence≈ 788 tokens

  Inspect exactly one Base or Ethereum transaction, address, or contract with bounded read-only RPC calls and return deterministic context, observed signals, evidence, coverage, and recommended follow-up. USE WHEN: agent needs broader deterministic investigation of a transaction hash, EVM address, or contract address. DO NOT USE WHEN: agent only needs a single read-only smart-contract call; use chain-contract-call instead. Parameter semantics: `chain` is required; exactly one of `transaction_hash`, `address`, or `contract_address` must be provided.

  Paramètres, retour & exemple (5)

  Paramètres

  • chain · string · requis · ethereum | base
    EVM network containing the target.
  • address · string · optionnel
    One EVM address to inspect.
  • previous_state · object · optionnel
    Optional prior new_state for stateless change detection.
  • contract_address · string · optionnel
    One EVM contract address to inspect.
  • transaction_hash · string · optionnel
    One transaction hash to inspect.

  Exemple d'appel

  {"name": "blockchain_intelligence", "arguments": {"chain": "ethereum"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"issues": [], "target": {}, "changes": [], "summary": "texte", "activity": {}, "coverage": {}, "evidence": [], "new_state": {}, "observed_at": "texte", "risk_signals": [], "current_state": {}, "value_and_fee": {}}}

• chain_contract_call≈ 427 tokens

  Execute one read-only EVM smart contract call on Ethereum or Base and return the normalized result without managing an RPC provider. USE WHEN: agent needs one read-only smart-contract call on a supported chain. DO NOT USE WHEN: agent needs broader transaction, address, or contract investigation with evidence and context. USE blockchain-intelligence FOR: broader deterministic inspection of a transaction, address, or contract.

  Paramètres, retour & exemple (3)

  Paramètres

  • data · string · requis
    Read-only hexadecimal ABI calldata.
  • chain · string · requis · ethereum | base
    EVM network for the read-only call.
  • contract_address · string · requis
    Target EVM contract address.

  Exemple d'appel

  {"name": "chain_contract_call", "arguments": {"data": "texte", "chain": "ethereum", "contract_address": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"chain": "texte", "result": "texte", "provider": "texte", "latency_ms": 1, "contract_address": "texte"}}

• change_intelligence≈ 940 tokens

  Return durable historical ADDED (ABSENT -> PRESENT) and REMOVED (PRESENT -> ABSENT) customer-domain changes for a vendor in a UTC time window; REMOVED does not prove contract cancellation and ADDED does not prove commercial purchase. USE WHEN: agent needs durable historical ADDED/REMOVED customer-domain changes for a vendor in a UTC time window. DO NOT USE WHEN: current confirmed customer base; technologies on one domain; competitor replacement/switch inference. USE installed-base-intelligence FOR: confirmed customer domains currently known for a technology/vendor. USE technology-intelligence FOR: technologies detected on a public domain. USE competitor-switch-intelligence FOR: competitor replacement/switch signals.

  Paramètres, retour & exemple (4)

  Paramètres

  • end · string · requis
    Exclusive UTC end boundary (ISO-8601, timezone-aware).
  • limit · integer · optionnel
    Maximum confirmed changes to return (1-100).
  • start · string · requis
    Inclusive UTC start boundary (ISO-8601, timezone-aware).
  • vendor · string · requis
    Technology/vendor to query confirmed changes for (e.g., klaviyo, yotpo, judge.me).

  Exemple d'appel

  {"name": "change_intelligence", "arguments": {"end": "texte", "start": "texte", "vendor": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"end": "texte", "start": "texte", "vendor": "texte", "changes": [], "product": "texte", "observed_at": "texte", "change_count": 1}}

• competitor_switch_intelligence≈ 502 tokens

  Return existing STRAELO competitor-switch/replacement signals and prioritized leads for supported competitors (yotpo, judge.me); unsupported competitors return UNSUPPORTED_COMPETITOR with charged=false. USE WHEN: agent needs competitor replacement/switch signals and prioritized leads for yotpo or judge.me. DO NOT USE WHEN: agent needs confirmed customer domains, vendor ADDED/REMOVED history, or technology detection on one domain. USE installed-base-intelligence FOR: confirmed customer domains currently known for a technology/vendor. USE change-intelligence FOR: durable ADDED/REMOVED changes for a vendor within a UTC time window. USE technology-intelligence FOR: technologies detected on a public domain.

  Paramètres, retour & exemple (1)

  Paramètres

  • competitor · string · requis · yotpo | judgeme
    Competitor technology to prospect against (yotpo, judge.me).

  Exemple d'appel

  {"name": "competitor_switch_intelligence", "arguments": {"competitor": "yotpo"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"error": "texte", "leads": [], "demand": {}, "reason": "texte", "status": "OK", "charged": true, "targets": [], "supported": true, "competitor": "texte"}}

• defi_execution_snapshot≈ 957 tokens

  Compare read-only Base swap quotes from 1inch and KyberSwap, returning normalized comparable output, consensus, dispersion, quote evidence, and provider limitations without executing a swap. USE WHEN: agent needs comparative swap-quote intelligence before executing a trade. DO NOT USE WHEN: agent wants actual swap or transaction execution. Parameter semantics: `chain` is Base-only; `token_in`/`token_out` are symbols from USDC, USDT, ETH, WETH; `amount_in` is a positive decimal; `slippage_bps` is required (0-10000); optional `baseline_provider` selects oneinch or kyberswap for direct economic comparison.

  Paramètres, retour & exemple (6)

  Paramètres

  • chain · string · requis · base
    Base Mainnet only in this quote-only MVP.
  • token_in · string · requis · USDC | USDT | ETH | WETH
    Input Base asset symbol.
  • amount_in · string · requis
    Positive decimal input amount, converted exactly to raw token units.
  • token_out · string · requis · USDC | USDT | ETH | WETH
    Output Base asset symbol; must differ from token_in.
  • slippage_bps · integer · requis
    Slippage tolerance in basis points; it is not treated as a cost.
  • baseline_provider · string · optionnel · oneinch | kyberswap
    Optional provider used only for a direct economic comparison.

  Exemple d'appel

  {"name": "defi_execution_snapshot", "arguments": {"chain": "base", "token_in": "USDC", "amount_in": "texte", "token_out": "USDC", "slippage_bps": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"usage": {}, "quotes": [], "status": "COMPARISON_AVAILABLE", "partial": true, "consensus": {}, "economics": {}, "confidence": "LOW", "observed_at": "texte", "best_provider": "texte", "evidence_quality": {}, "provider_failures": [], "economic_advantage": {}}}

• domain_intelligence≈ 616 tokens

  Inspect consolidated domain health — DNS, HTTP, HTTPS, TLS, redirects, MX, SPF, DMARC, email posture, security posture, and agent readiness — returning structured issues, evidence, actions, and stateless changes. USE WHEN: agent needs a comprehensive single-call domain inspection across DNS, web, email, security, and agent-readiness signals. DO NOT USE WHEN: agent only needs DNS records; narrower domain/DNS products are not exposed through MCP. Parameter semantics: `domain` is required; optional `previous_state` enables stateless change detection against a prior `new_state`.

  Paramètres, retour & exemple (2)

  Paramètres

  • domain · string · requis
    Public domain name for consolidated domain health, DNS, TLS, and email-posture inspection; localhost and IP literals are rejected.
  • previous_state · object · optionnel
    Optional prior new_state for stateless change detection.

  Exemple d'appel

  {"name": "domain_intelligence", "arguments": {"domain": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"dns": {}, "domain": "texte", "health": {}, "issues": [], "actions": [], "changes": [], "evidence": [], "new_state": {}, "observed_at": "texte", "data_quality": {}, "current_state": {}, "email_posture": {}}}

• email_validator_basic≈ 284 tokens

  Validate email syntax, domain, and MX records for basic automated checks without SMTP mailbox verification; cannot prove a mailbox exists or can receive mail. USE WHEN: agent needs inexpensive structural and mail-domain validation before using an email address. DO NOT USE WHEN: agent requires proof that a mailbox exists or can receive mail.

  Paramètres, retour & exemple (1)

  Paramètres

  • email · string · requis
    Email address for syntax, domain and MX validation.

  Exemple d'appel

  {"name": "email_validator_basic", "arguments": {"email": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"valid": true, "domain": "texte", "reasons": [], "mx_found": true}}

• installed_base_intelligence≈ 748 tokens

  Return confirmed customer domains currently known for a specified technology/vendor; STRAELO-confirmed coverage, not a complete global installed base. USE WHEN: agent needs confirmed customer domains currently known for a specified technology/vendor. DO NOT USE WHEN: domain -> technologies; vendor + time -> ADDED/REMOVED; competitor switch/replacement signals. USE technology-intelligence FOR: technologies detected on a public domain. USE change-intelligence FOR: durable ADDED/REMOVED changes for a vendor within a UTC time window. USE competitor-switch-intelligence FOR: competitor switch/replacement signals.

  Paramètres, retour & exemple (2)

  Paramètres

  • limit · integer · optionnel
    Maximum confirmed customers to return (1-100).
  • vendor · string · requis
    Technology/vendor to query confirmed customers for (e.g., klaviyo, yotpo, judge.me).

  Exemple d'appel

  {"name": "installed_base_intelligence", "arguments": {"vendor": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"vendor": "texte", "product": "texte", "customers": [], "returned_count": 1, "confirmed_customer_count": 1}}

• pay_decision_snapshot≈ 848 tokens

  Compare one supplied x402 v2 exact Base USDC payment requirement against declared intent and return deterministic consistency, mismatch, change, fingerprint, and coverage evidence without executing a payment. USE WHEN: agent needs deterministic verification of a payment requirement before deciding whether to pay. DO NOT USE WHEN: agent expects this tool to execute the payment. Parameter semantics: supply `intent` (seller, service, resource, plus optional expected fields) and `payment_required` (decoded x402 challenge); optional `previous_snapshot` enables stateless material-change detection against a prior result.

  Paramètres, retour & exemple (3)

  Paramètres

  • intent · object · requis
  • payment_required · object · requis
    Observed x402 v2 PAYMENT-REQUIRED challenge decoded as JSON.
  • previous_snapshot · object · optionnel
    Optional prior snapshot for stateless material-change detection.

  Exemple d'appel

  {"name": "pay_decision_snapshot", "arguments": {"intent": {}, "payment_required": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"changes": [], "matched": {}, "coverage": {}, "evidence": {}, "snapshot": {}, "assessment": "CONSISTENT", "mismatched": {}, "reason_codes": [], "checks_skipped": [], "external_calls": [], "checks_performed": [], "payment_fingerprint": "texte"}}

• technology_intelligence≈ 706 tokens

  Return technologies deterministically detected on one specified public domain; deterministic observations, not an exhaustive proof that no other technology exists. USE WHEN: agent needs technologies currently detected on one specific public domain. DO NOT USE WHEN: vendor -> current confirmed customers; vendor + time -> ADDED/REMOVED; competitor replacement/switch signals. USE installed-base-intelligence FOR: confirmed customer domains using a technology/vendor. USE change-intelligence FOR: durable ADDED/REMOVED changes for a vendor within a UTC time window. USE competitor-switch-intelligence FOR: competitor replacement/switch signals.

  Paramètres, retour & exemple (1)

  Paramètres

  • domain · string · requis
    Public domain to scan for detectable technologies; localhost and IP literals are rejected.

  Exemple d'appel

  {"name": "technology_intelligence", "arguments": {"domain": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"domain": "texte", "product": "texte", "observed_at": "texte", "technologies": [], "technology_count": 1, "response_validity": "texte"}}

• url_clean_content≈ 348 tokens

  Extract clean, boilerplate-free readable text from one known public HTTP(S) URL for LLM research or RAG ingestion; private, local, authenticated, paywalled, or blocked resources are not supported. USE WHEN: agent already knows the URL and needs clean page text. DO NOT USE WHEN: agent needs web search, multi-page research, comparison, structured web workflow, or change detection. USE web-intelligence FOR: those broader live-web operations.

  Paramètres, retour & exemple (1)

  Paramètres

  • url · string · requis
    Public HTTP(S) page URL to fetch. Private, local, authenticated, paywalled, or blocked resources are not supported.

  Exemple d'appel

  {"name": "url_clean_content", "arguments": {"url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"url": "texte", "text": "texte", "title": "texte", "metadata": {}}}

• web_intelligence≈ 859 tokens

  Execute one live-web operation — search, read, extract, evidence, research, compare, or changes — in a single paid request without orchestrating multiple web APIs. USE WHEN: agent needs a live web search, multi-page read, structured extraction, comparative research, evidence gathering, or web change detection. DO NOT USE WHEN: agent already has a single known URL and only needs its clean readable text; use url-clean-content instead. Parameter semantics: supply `intent` plus only that intent's fields; without `intent`, supply legacy `topic` and `objective` together.

  Paramètres, retour & exemple (9)

  Paramètres

  • url · string · optionnel
    Public HTTP(S) URL for read or changes.
  • query · string · optionnel
    Live-web query for search, extract, evidence, or compare.
  • topic · string · optionnel
    Legacy structured-research topic, used with objective only when intent is omitted.
  • fields · array · optionnel
    Unique source fields for extract.
  • intent · string · optionnel · search | read | extract | evidence | research | compare | changes
    Selected Web Intelligence operation.
  • targets · array · optionnel
    Two to five named targets for compare.
  • question · string · optionnel
    Natural-language question for research.
  • objective · string · optionnel
    Legacy structured-research objective, used with topic only when intent is omitted.
  • previous_state · object · optionnel
    Optional client-supplied prior read state for stateless changes detection.

  Exemple d'appel

  {"name": "web_intelligence", "arguments": {"url": "texte", "query": "texte", "topic": "texte", "fields": [], "intent": "search", "targets": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"usage": {}, "intent": "texte", "result": {}, "missing": [], "sources": [], "economics": {}, "freshness": "texte", "observed_at": "texte", "data_quality": {}}}

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://relay.straelo.com/mcp/