net.siteborne/utility

Est-ce que net.siteborne/utility est sûr ?

Au dernier audit MCP Hub, le serveur MCP « net.siteborne/utility » 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 10 outils

• siteborne_build_company_evidence_graph≈ 8673 tokens

  Build a proof-carrying graph of public company identity, SEC filings, website observations, regulatory mentions, and repository signals. Use when: the request needs entity-level evidence synthesized across sources. Do not use when: one URL is the subject (use siteborne_retrieve_verified_web_context), one document is the subject (use siteborne_extract_document_evidence_json), or an existing agent output needs evaluation (use siteborne_verify_agent_output). Parameters: authoritative identifiers (cik, lei, isin, cusip, figi) resolve entities more reliably than company_name, ticker or domain alone, and combining them reduces ambiguity; requested_field_groups narrows provider work; maximum_authorized_price only constrains payment and never widens scope. Behavior: open-world: a paid request queries public data providers over the network and persists governed payment, audit, job and Workflow state; an unpaid request returns payment_required; a repeated identical request with the same payment is replay-protected and is not charged twice. This service is currently production-disabled and rejects execution. Economics: exact price of $0.0312 USD per request; the payment challenge requires that amount and the charge settles at exactly that amount. Failure: input that fails schema validation is rejected before any payment challenge; provider or service unavailability returns a structured MCP error. Returns: a company evidence graph with provenance, completeness, verification, and PCC context—not a raw webpage or document extraction.

  Paramètres, retour & exemple (11)

  Paramètres

  • domain · string · optionnel
    Primary website hostname only, without a URL path; links first-party web evidence to the company identity.
  • ticker · string · optionnel
    One-to-five uppercase exchange ticker symbols; narrows public-company resolution but is not globally unique without other signals.
  • buyer_urls · array · optionnel
    Up to twenty public supplemental evidence URLs supplied by the buyer; these are additional sources, not replacements for entity resolution.
  • identifiers · object · optionnel
    Known authoritative entity identifiers; supplying precise identifiers reduces ambiguous name, ticker, or domain matching.
  • company_name · string · optionnel
    Legal or commonly used company name; supplies an entity-resolution signal when authoritative identifiers are unavailable.
  • freshness_seconds · integer · optionnel
    Maximum acceptable source age in seconds, from 0 through 2,592,000; lower values demand fresher evidence.
  • jurisdiction_hints · array · optionnel
    Up to five two-letter uppercase jurisdiction codes used to focus regulatory context; hints do not assert incorporation.
  • minimum_completeness · number · optionnel
    Required completeness ratio from 0 through 1; results below this threshold fail the requested acceptance condition.
  • requested_field_groups · array · optionnel
    Unique evidence categories to collect; omitted values use the schema default, while a smaller list limits provider work and result scope.
  • maximum_authorized_price · object · optionnel
    Buyer’s decimal-safe maximum authorized price; constrains the payment requirement and never expands provider scope.
  • minimum_verification_score · number · optionnel
    Required PCC verification ratio from 0 through 1; raising it makes result acceptance stricter.

  Exemple d'appel

  {"name": "siteborne_build_company_evidence_graph", "arguments": {"domain": "texte", "ticker": "texte", "buyer_urls": [], "identifiers": {}, "company_name": "texte", "freshness_seconds": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": "texte"}}

• siteborne_build_company_evidence_graph_v3_candidate≈ 9259 tokens

  Build a proof-carrying graph of public company identity, SEC filings, website observations, regulatory mentions, and repository signals. Use when: the request needs entity-level evidence synthesized across sources. Do not use when: one URL is the subject (use siteborne_retrieve_verified_web_context), one document is the subject (use siteborne_extract_document_evidence_json), or an existing agent output needs evaluation (use siteborne_verify_agent_output). Parameters: authoritative identifiers (cik, lei, isin, cusip, figi) resolve entities more reliably than company_name, ticker or domain alone, and combining them reduces ambiguity; requested_field_groups narrows provider work; maximum_authorized_price only constrains payment and never widens scope. Behavior: open-world: a paid request queries public data providers over the network and persists governed payment, audit, job and Workflow state; an unpaid request returns payment_required; a repeated identical request with the same payment is replay-protected and is not charged twice. This service is currently production-disabled and rejects execution. Economics: exact price of $0.0312 USD per request; the payment challenge requires that amount and the charge settles at exactly that amount. Failure: input that fails schema validation is rejected before any payment challenge; provider or service unavailability returns a structured MCP error. Returns: a company evidence graph with provenance, completeness, verification, and PCC context—not a raw webpage or document extraction.

  Paramètres, retour & exemple (11)

  Paramètres

  • domain · string · optionnel
    Primary website hostname only, without a URL path; links first-party web evidence to the company identity.
  • ticker · string · optionnel
    One-to-five uppercase exchange ticker symbols; narrows public-company resolution but is not globally unique without other signals.
  • buyer_urls · array · optionnel
    Up to twenty public supplemental evidence URLs supplied by the buyer; these are additional sources, not replacements for entity resolution.
  • identifiers · object · optionnel
    Known authoritative entity identifiers; supplying precise identifiers reduces ambiguous name, ticker, or domain matching.
  • company_name · string · optionnel
    Legal or commonly used company name; supplies an entity-resolution signal when authoritative identifiers are unavailable.
  • freshness_seconds · integer · optionnel
    Maximum acceptable source age in seconds, from 0 through 2,592,000; lower values demand fresher evidence.
  • jurisdiction_hints · array · optionnel
    Up to five two-letter uppercase jurisdiction codes used to focus regulatory context; hints do not assert incorporation.
  • minimum_completeness · number · optionnel
    Required completeness ratio from 0 through 1; results below this threshold fail the requested acceptance condition.
  • requested_field_groups · array · optionnel
    Unique evidence categories to collect; omitted values use the schema default, while a smaller list limits provider work and result scope.
  • maximum_authorized_price · object · optionnel
    Buyer’s decimal-safe maximum authorized price; constrains the payment requirement and never expands provider scope.
  • minimum_verification_score · number · optionnel
    Required PCC verification ratio from 0 through 1; raising it makes result acceptance stricter.

  Exemple d'appel

  {"name": "siteborne_build_company_evidence_graph_v3_candidate", "arguments": {"domain": "texte", "ticker": "texte", "buyer_urls": [], "identifiers": {}, "company_name": "texte", "freshness_seconds": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": "texte"}}

• siteborne_extract_document_evidence_json≈ 9046 tokens

  Extract and verify structured evidence from exactly one authorized artifact, prior SITEBORNE upload, or public document URL. Use when: the source of truth is a PDF or supported image and the desired result is evidence JSON. Do not use when: a webpage alone is sufficient (use siteborne_retrieve_verified_web_context), company-wide public evidence is needed (use siteborne_build_company_evidence_graph), or an existing agent response needs evaluation (use siteborne_verify_agent_output). Parameters: provide exactly one reference mode: artifact_reference (an authorized stored artifact), upload_reference (a prior SITEBORNE upload handle, not document bytes) or document_url (a public URL, no credentials). ocr_permission must be true before image-based content is read by OCR, and OCR pages bill at the OCR tier; extraction_request.extract_tables and table_extraction_request request table extraction, and pages with tables bill at the table tier; declared_page_count and page_range are bounded by the page limit below; maximum_authorized_price only constrains payment. Behavior: open-world: a paid request may read governed artifact storage or fetch a public document URL, calls the document provider, and persists payment, audit, job and Workflow state; an unpaid request returns payment_required; a repeated identical request with the same payment is replay-protected and is not charged twice. This service is currently production-disabled and rejects execution. Economics: upto pricing: the payment challenge authorizes a maximum of $0.19 USD per job; the actual charge is measured per processed page (native-text $0.0098, OCR $0.0156, table $0.0238 per page, the highest applicable tier per page) and never exceeds the authorization. The authorization is a ceiling, not the charge. Documents are limited to 10 pages per job. Failure: schema-invalid input is rejected before any payment challenge; a document over the page limit, an unreadable or encrypted document, or an unavailable provider returns a structured MCP error. Returns: extracted document evidence, integrity/provenance findings, and PCC verification—not an uploaded file.

  Paramètres, retour & exemple (12)

  Paramètres

  • page_range · object · optionnel
    Optional one-indexed inclusive page range to process; both bounds are limited to pages 1 through 10.
  • document_url · string · optionnel
    Public document URL for reference mode 3; use exactly one reference mode and never put credentials in this URL.
  • language_hints · array · optionnel
    Up to five BCP 47 language hints used by OCR and extraction; hints do not translate the document.
  • ocr_permission · boolean · optionnel
    Explicit permission to use OCR for image-based content; false prevents OCR even when text is not embedded.
  • upload_reference · object · optionnel
    Previously issued SITEBORNE upload handle and declared file metadata for reference mode 2; it does not upload document bytes.
  • artifact_reference · object · optionnel
    Authorized stored-artifact descriptor for reference mode 1; use exactly one of artifact_reference, upload_reference, or document_url.
  • extraction_request · object · optionnel
    Selects text, table, key-value, and buyer-schema extraction outputs; omitted switches retain their documented defaults.
  • declared_page_count · integer · optionnel
    Optional declared page count from 1 through 10; enables early scope validation but does not override the observed document.
  • retention_preference · string · optionnel · none | temporary | permanent
    Requested retention class—none, temporary, or permanent—subject to server policy; it cannot override mandatory retention limits.
  • maximum_authorized_price · object · optionnel
    Buyer’s decimal-safe maximum authorized price; constrains the payment requirement and not retention or extraction policy.
  • table_extraction_request · boolean · optionnel
    Explicit top-level request for table extraction; false leaves tables unrequested.
  • minimum_verification_score · number · optionnel
    Required PCC verification ratio from 0 through 1; raising it makes extracted-evidence acceptance stricter.

  Exemple d'appel

  {"name": "siteborne_extract_document_evidence_json", "arguments": {"page_range": {}, "document_url": "texte", "language_hints": [], "ocr_permission": true, "upload_reference": {}, "artifact_reference": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": "texte"}}

• siteborne_extract_document_evidence_json_v3_candidate≈ 9586 tokens

  Extract and verify structured evidence from exactly one authorized artifact, prior SITEBORNE upload, or public document URL. Use when: the source of truth is a PDF or supported image and the desired result is evidence JSON. Do not use when: a webpage alone is sufficient (use siteborne_retrieve_verified_web_context), company-wide public evidence is needed (use siteborne_build_company_evidence_graph), or an existing agent response needs evaluation (use siteborne_verify_agent_output). Parameters: provide exactly one reference mode: artifact_reference (an authorized stored artifact), upload_reference (a prior SITEBORNE upload handle, not document bytes) or document_url (a public URL, no credentials). ocr_permission must be true before image-based content is read by OCR, and OCR pages bill at the OCR tier; extraction_request.extract_tables and table_extraction_request request table extraction, and pages with tables bill at the table tier; declared_page_count and page_range are bounded by the page limit below; maximum_authorized_price only constrains payment. Behavior: open-world: a paid request may read governed artifact storage or fetch a public document URL, calls the document provider, and persists payment, audit, job and Workflow state; an unpaid request returns payment_required; a repeated identical request with the same payment is replay-protected and is not charged twice. This service is currently production-disabled and rejects execution. Economics: upto pricing: the payment challenge authorizes a maximum of $0.19 USD per job; the actual charge is measured per processed page (native-text $0.0098, OCR $0.0156, table $0.0238 per page, the highest applicable tier per page) and never exceeds the authorization. The authorization is a ceiling, not the charge. Documents are limited to 10 pages per job. Failure: schema-invalid input is rejected before any payment challenge; a document over the page limit, an unreadable or encrypted document, or an unavailable provider returns a structured MCP error. Returns: extracted document evidence, integrity/provenance findings, and PCC verification—not an uploaded file.

  Paramètres, retour & exemple (12)

  Paramètres

  • page_range · object · optionnel
    Optional one-indexed inclusive page range to process; both bounds are limited to pages 1 through 10.
  • document_url · string · optionnel
    Public document URL for reference mode 3; use exactly one reference mode and never put credentials in this URL.
  • language_hints · array · optionnel
    Up to five BCP 47 language hints used by OCR and extraction; hints do not translate the document.
  • ocr_permission · boolean · optionnel
    Explicit permission to use OCR for image-based content; false prevents OCR even when text is not embedded.
  • upload_reference · object · optionnel
    Previously issued SITEBORNE upload handle and declared file metadata for reference mode 2; it does not upload document bytes.
  • artifact_reference · object · optionnel
    Authorized stored-artifact descriptor for reference mode 1; use exactly one of artifact_reference, upload_reference, or document_url.
  • extraction_request · object · optionnel
    Selects text, table, key-value, and buyer-schema extraction outputs; omitted switches retain their documented defaults.
  • declared_page_count · integer · optionnel
    Optional declared page count from 1 through 10; enables early scope validation but does not override the observed document.
  • retention_preference · string · optionnel · none | temporary | permanent
    Requested retention class—none, temporary, or permanent—subject to server policy; it cannot override mandatory retention limits.
  • maximum_authorized_price · object · optionnel
    Buyer’s decimal-safe maximum authorized price; constrains the payment requirement and not retention or extraction policy.
  • table_extraction_request · boolean · optionnel
    Explicit top-level request for table extraction; false leaves tables unrequested.
  • minimum_verification_score · number · optionnel
    Required PCC verification ratio from 0 through 1; raising it makes extracted-evidence acceptance stricter.

  Exemple d'appel

  {"name": "siteborne_extract_document_evidence_json_v3_candidate", "arguments": {"page_range": {}, "document_url": "texte", "language_hints": [], "ocr_permission": true, "upload_reference": {}, "artifact_reference": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": "texte"}}

• siteborne_get_quote≈ 1735 tokens

  Build a canonical x402 payment quote for one SITEBORNE service and exact request input. Use when: an agent needs the governed price, payee, network, asset, resource, expiry, and payment requirement before deciding whether to invoke a paid service. Do not use when: evidence work is required now (use the matching siteborne_build_company_evidence_graph, siteborne_retrieve_verified_web_context, siteborne_extract_document_evidence_json, or siteborne_verify_agent_output tool), or only availability is needed (use siteborne_get_service_health). Parameters: scheme must be the one scheme the service is offered under (company_evidence_graph.v2 exact, web_context_verified.v2 exact, document_evidence_json.v2 upto, verify_agent_output.v2 exact, company_evidence_graph.v3 exact, web_context_verified.v3 exact, document_evidence_json.v3 upto, verify_agent_output.v3 exact); any other scheme is rejected with scheme_not_offered. input is hashed, so the quote binds only that exact request. Behavior: quote-only and read-only; it hashes the proposed input, and does not execute the underlying paid service, verify payment, call a provider, create a Workflow, or settle. Economics: free of charge. The returned amount is the exact price, or for upto an authorized maximum whose actual_amount is null because the real charge is measured at settlement and never exceeds it. Failure: a mode that has a governed price but is unavailable returns retrieval_mode_unavailable or verification_mode_unavailable and no quote; a quote expires at expires_at. Returns: an expiring input-bound quote with its x402 payment requirement and the canonical economics block.

  Paramètres, retour & exemple (3)

  Paramètres

  • input · ? · requis
    Complete proposed input for the selected service; its canonical hash binds the quote and later payment requirement to this exact request content.
  • scheme · string · requis · exact | upto
    Pricing mode: exact fixes the required amount, while upto authorizes a maximum whose eventual charge cannot exceed the returned amount.
  • service_id · string · requis · company_evidence_graph.v1 | web_context_verified.v1 | document_evidence_json.v1 | verify_agent_output.v1 | company_evidence_graph.v2 | web_context_verified.v2 | document_evidence_json.v2 | verify_agent_output.v2
    Canonical SITEBORNE service and major version to price; selects that service’s governed pricing key, contract release, and production resource URL.

  Exemple d'appel

  {"name": "siteborne_get_quote", "arguments": {"input": "texte", "scheme": "exact", "service_id": "company_evidence_graph.v1"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"asset": "texte", "payee": "texte", "amount": "texte", "scheme": "exact", "network": "texte", "quote_id": "texte", "economics": {}, "issued_at": "texte", "expires_at": "texte", "input_hash": "texte", "service_id": "texte", "amount_kind": "exact"}}

• siteborne_get_service_health≈ 618 tokens

  Report MCP server readiness and production-enable status for each SITEBORNE service. Use when: an agent must check protocol availability, tool count, or whether a service is currently production-enabled before selecting a paid tool. Do not use when: a quote is needed (use siteborne_get_quote) or company, web, document, or agent-output evidence work is required (use the corresponding SITEBORNE service tool). Behavior: read-only and credential-independent; it does not perform paid evidence work, create quotes, verify payment, call providers, write service state, create Workflows, or settle. Economics: free of charge; it never issues a payment challenge. Failure: it depends on no provider, so it does not fail because a provider is unavailable. Returns: the server and protocol versions plus truthful local, production, and external-publication status for all four evidence services.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "siteborne_get_service_health", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"tools": 1, "status": "texte", "services": {}, "server_name": "texte", "server_version": "texte", "production_ready": true, "protocol_version": "texte", "production_enabled": true, "external_publication": "texte"}}

• siteborne_retrieve_verified_web_context≈ 8184 tokens

  Retrieve and verify evidence from one public web URL using direct HTTP retrieval. Use when: the request is specifically about the content and provenance of a URL. Do not use when: evidence must be synthesized for a company (use siteborne_build_company_evidence_graph), extracted from an authorized document (use siteborne_extract_document_evidence_json), checked against an existing output contract (use siteborne_verify_agent_output), or the page requires JavaScript rendering (rendered retrieval is not available). Parameters: retrieval_mode must be direct; rendered is defined but unavailable and is rejected before any payment challenge, never substituted with direct retrieval. output_mode structured needs buyer_schema and field_selectors to be meaningful; redirect_policy and max_redirects bound redirect following; max_content_size bounds returned bytes; maximum_authorized_price only constrains payment and never changes retrieval scope. Behavior: open-world: a paid request performs bounded outbound HTTP retrieval of the target URL through a safe-egress boundary (private and loopback destinations are refused) and persists governed payment, audit, job and Workflow state; an unpaid request returns payment_required; a repeated identical request with the same payment is replay-protected and is not charged twice. Retrieval admission follows the governed runtime rate policy; no fixed public per-origin rate is promised. This service is currently production-disabled and rejects execution. Economics: exact price of $0.008 USD per request in direct mode; the payment challenge requires that amount and the charge settles at exactly that amount. rendered mode has a governed price of $0.029 USD but is not available: it is rejected before any payment challenge and never substituted. Failure: schema-invalid input and unavailable modes are rejected before any payment challenge; target-site errors, timeouts and unavailable retrieval return a structured MCP error and are never answered with a substitute result. Returns: normalized, source-attributed web context with verification and PCC evidence.

  Paramètres, retour & exemple (12)

  Paramètres

  • target_url · string · requis
    Public HTTP or HTTPS URL to retrieve and verify; private, loopback, and otherwise unsafe network destinations are rejected.
  • locale_hint · string · optionnel
    Optional BCP 47 language or language-region hint used for HTTP content negotiation; it does not translate content.
  • output_mode · string · optionnel · clean_text | markdown | structured
    Result representation: clean_text normalizes prose, markdown preserves document structure, and structured validates selected fields against buyer_schema.
  • buyer_schema · object · optionnel
    Optional JSON Schema governing structured output; meaningful only with output_mode structured and bounded to fifty properties and depth five.
  • max_redirects · integer · optionnel
    Maximum redirect hops from 0 through 10 when the selected redirect policy follows redirects.
  • retrieval_mode · string · requis · direct | rendered
    Retrieval mode. Only direct (plain HTTP retrieval, no JavaScript execution) is available. rendered has a governed price but is not available: it is rejected with retrieval_mode_unavailable before any payment challenge and is never substituted with direct retrieval.
  • field_selectors · array · optionnel
    Up to thirty requested field names for structured extraction; narrows the structured result rather than changing the fetched URL.
  • redirect_policy · string · optionnel · follow | follow_first | manual
    Redirect handling: follow permits the bounded chain, follow_first permits only the first hop, and manual returns redirect evidence without following.
  • max_content_size · integer · optionnel
    Maximum returned content size in bytes, from 1,024 through 10,485,760; smaller limits truncate or reject oversized content sooner.
  • freshness_seconds · integer · optionnel
    Maximum acceptable cached-content age in seconds, from 0 through 2,592,000; zero requests uncached content.
  • maximum_authorized_price · object · optionnel
    Buyer’s decimal-safe maximum authorized price; constrains the payment requirement and never changes retrieval scope.
  • minimum_verification_score · number · optionnel
    Required PCC verification ratio from 0 through 1; raising it makes evidence acceptance stricter.

  Exemple d'appel

  {"name": "siteborne_retrieve_verified_web_context", "arguments": {"target_url": "texte", "retrieval_mode": "direct"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": "texte"}}

• siteborne_retrieve_verified_web_context_v3_candidate≈ 8770 tokens

  Retrieve and verify evidence from one public web URL using direct HTTP retrieval. Use when: the request is specifically about the content and provenance of a URL. Do not use when: evidence must be synthesized for a company (use siteborne_build_company_evidence_graph), extracted from an authorized document (use siteborne_extract_document_evidence_json), checked against an existing output contract (use siteborne_verify_agent_output), or the page requires JavaScript rendering (rendered retrieval is not available). Parameters: retrieval_mode must be direct; rendered is defined but unavailable and is rejected before any payment challenge, never substituted with direct retrieval. output_mode structured needs buyer_schema and field_selectors to be meaningful; redirect_policy and max_redirects bound redirect following; max_content_size bounds returned bytes; maximum_authorized_price only constrains payment and never changes retrieval scope. Behavior: open-world: a paid request performs bounded outbound HTTP retrieval of the target URL through a safe-egress boundary (private and loopback destinations are refused) and persists governed payment, audit, job and Workflow state; an unpaid request returns payment_required; a repeated identical request with the same payment is replay-protected and is not charged twice. Retrieval admission follows the governed runtime rate policy; no fixed public per-origin rate is promised. This service is currently production-disabled and rejects execution. Economics: exact price of $0.008 USD per request in direct mode; the payment challenge requires that amount and the charge settles at exactly that amount. rendered mode has a governed price of $0.029 USD but is not available: it is rejected before any payment challenge and never substituted. Failure: schema-invalid input and unavailable modes are rejected before any payment challenge; target-site errors, timeouts and unavailable retrieval return a structured MCP error and are never answered with a substitute result. Returns: normalized, source-attributed web context with verification and PCC evidence.

  Paramètres, retour & exemple (12)

  Paramètres

  • target_url · string · requis
    Public HTTP or HTTPS URL to retrieve and verify; private, loopback, and otherwise unsafe network destinations are rejected.
  • locale_hint · string · optionnel
    Optional BCP 47 language or language-region hint used for HTTP content negotiation; it does not translate content.
  • output_mode · string · optionnel · clean_text | markdown | structured
    Result representation: clean_text normalizes prose, markdown preserves document structure, and structured validates selected fields against buyer_schema.
  • buyer_schema · object · optionnel
    Optional JSON Schema governing structured output; meaningful only with output_mode structured and bounded to fifty properties and depth five.
  • max_redirects · integer · optionnel
    Maximum redirect hops from 0 through 10 when the selected redirect policy follows redirects.
  • retrieval_mode · string · requis · direct | rendered
    Retrieval mode. Only direct (plain HTTP retrieval, no JavaScript execution) is available. rendered has a governed price but is not available: it is rejected with retrieval_mode_unavailable before any payment challenge and is never substituted with direct retrieval.
  • field_selectors · array · optionnel
    Up to thirty requested field names for structured extraction; narrows the structured result rather than changing the fetched URL.
  • redirect_policy · string · optionnel · follow | follow_first | manual
    Redirect handling: follow permits the bounded chain, follow_first permits only the first hop, and manual returns redirect evidence without following.
  • max_content_size · integer · optionnel
    Maximum returned content size in bytes, from 1,024 through 10,485,760; smaller limits truncate or reject oversized content sooner.
  • freshness_seconds · integer · optionnel
    Maximum acceptable cached-content age in seconds, from 0 through 2,592,000; zero requests uncached content.
  • maximum_authorized_price · object · optionnel
    Buyer’s decimal-safe maximum authorized price; constrains the payment requirement and never changes retrieval scope.
  • minimum_verification_score · number · optionnel
    Required PCC verification ratio from 0 through 1; raising it makes evidence acceptance stricter.

  Exemple d'appel

  {"name": "siteborne_retrieve_verified_web_context_v3_candidate", "arguments": {"target_url": "texte", "retrieval_mode": "direct"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": "texte"}}

• siteborne_verify_agent_output≈ 9135 tokens

  Evaluate a supplied agent output against explicit claims, deterministic requirements, a required JSON Schema, and optional evidence. Use when: the caller already has an output and needs a governed verification verdict. Do not use when: evidence must first be gathered from a company (use siteborne_build_company_evidence_graph), URL (use siteborne_retrieve_verified_web_context), or document (use siteborne_extract_document_evidence_json), or independent reproduction of the output is required (not available). Parameters: verification_mode must be standard; independent_reproduction is defined but unavailable and is rejected before any payment challenge, never downgraded to standard. required_schema must fit SITEBORNE JSON Schema Profile 1 or the request is rejected before payment; minimum_score sets the acceptance threshold; maximum_authorized_price only constrains payment and never relaxes verification policy. Behavior: closed-world: standard mode evaluates only the supplied claims, requirements, output and evidence with no outbound retrieval, and persists governed payment, audit, job and Workflow state; an unpaid request returns payment_required; a repeated identical request with the same payment is replay-protected and is not charged twice. The verification policy and verdict rules do not depend on price or maximum_authorized_price. This service is currently production-disabled and rejects execution. Economics: exact price of $0.017 USD per request in standard mode; the payment challenge requires that amount and the charge settles at exactly that amount. independent_reproduction mode has a governed price of $0.049 USD but is not available: it is rejected before any payment challenge and never substituted. Failure: an unsupported or oversized required_schema, schema-invalid input and unavailable modes are rejected before any payment challenge; a failed verification is a normal fail or conditional verdict, not an error. Returns: claim-level and deterministic-check results, an overall verification verdict, and PCC evidence—not newly gathered source content.

  Paramètres, retour & exemple (9)

  Paramètres

  • minimum_score · number · optionnel
    Minimum overall verification score from 0 through 1; raising it makes the final acceptance verdict stricter.
  • required_schema · object · requis
    JSON Schema the candidate output must satisfy; it constrains validation and cannot change SITEBORNE verifier policy.
  • candidate_output · object · requis
    Agent-produced JSON object to evaluate, bounded to 200 properties and depth 10; it is evidence under test, not trusted policy.
  • supplied_evidence · array · optionnel
    Up to twenty evidence objects supplied with the candidate output and bound to integrity hashes.
  • verification_mode · string · requis · standard | independent_reproduction
    Verification mode. Only standard (deterministic checks of the supplied material, no outbound retrieval) is available. independent_reproduction has a governed price but is not available: it is rejected with verification_mode_unavailable before any payment challenge and is never downgraded to standard.
  • verification_contract · object · requis
    Complete set of claims and deterministic checks against which the supplied candidate output is evaluated.
  • freshness_requirements · object · optionnel
    Optional maximum-age limits for evidence and schemas, each expressed in seconds.
  • allowed_evidence_sources · array · optionnel
    Up to ten permitted evidence source URIs; evidence outside this allowlist cannot satisfy source restrictions.
  • maximum_authorized_price · object · optionnel
    Buyer’s decimal-safe maximum authorized price; constrains the payment requirement and never relaxes verification policy.

  Exemple d'appel

  {"name": "siteborne_verify_agent_output", "arguments": {"required_schema": {}, "candidate_output": {}, "verification_mode": "standard", "verification_contract": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": "texte"}}

• siteborne_verify_agent_output_v3_candidate≈ 9659 tokens

  Evaluate a supplied agent output against explicit claims, deterministic requirements, a required JSON Schema, and optional evidence. Use when: the caller already has an output and needs a governed verification verdict. Do not use when: evidence must first be gathered from a company (use siteborne_build_company_evidence_graph), URL (use siteborne_retrieve_verified_web_context), or document (use siteborne_extract_document_evidence_json), or independent reproduction of the output is required (not available). Parameters: verification_mode must be standard; independent_reproduction is defined but unavailable and is rejected before any payment challenge, never downgraded to standard. required_schema must fit SITEBORNE JSON Schema Profile 1 or the request is rejected before payment; minimum_score sets the acceptance threshold; maximum_authorized_price only constrains payment and never relaxes verification policy. Behavior: closed-world: standard mode evaluates only the supplied claims, requirements, output and evidence with no outbound retrieval, and persists governed payment, audit, job and Workflow state; an unpaid request returns payment_required; a repeated identical request with the same payment is replay-protected and is not charged twice. The verification policy and verdict rules do not depend on price or maximum_authorized_price. This service is currently production-disabled and rejects execution. Economics: exact price of $0.017 USD per request in standard mode; the payment challenge requires that amount and the charge settles at exactly that amount. independent_reproduction mode has a governed price of $0.049 USD but is not available: it is rejected before any payment challenge and never substituted. Failure: an unsupported or oversized required_schema, schema-invalid input and unavailable modes are rejected before any payment challenge; a failed verification is a normal fail or conditional verdict, not an error. Returns: claim-level and deterministic-check results, an overall verification verdict, and PCC evidence—not newly gathered source content.

  Paramètres, retour & exemple (9)

  Paramètres

  • minimum_score · number · optionnel
    Minimum overall verification score from 0 through 1; raising it makes the final acceptance verdict stricter.
  • required_schema · object · requis
    JSON Schema the candidate output must satisfy; it constrains validation and cannot change SITEBORNE verifier policy.
  • candidate_output · object · requis
    Agent-produced JSON object to evaluate, bounded to 200 properties and depth 10; it is evidence under test, not trusted policy.
  • supplied_evidence · array · optionnel
    Up to twenty evidence objects supplied with the candidate output and bound to integrity hashes.
  • verification_mode · string · requis · standard | independent_reproduction
    Verification mode. Only standard (deterministic checks of the supplied material, no outbound retrieval) is available. independent_reproduction has a governed price but is not available: it is rejected with verification_mode_unavailable before any payment challenge and is never downgraded to standard.
  • verification_contract · object · requis
    Complete set of claims and deterministic checks against which the supplied candidate output is evaluated.
  • freshness_requirements · object · optionnel
    Optional maximum-age limits for evidence and schemas, each expressed in seconds.
  • allowed_evidence_sources · array · optionnel
    Up to ten permitted evidence source URIs; evidence outside this allowlist cannot satisfy source restrictions.
  • maximum_authorized_price · object · optionnel
    Buyer’s decimal-safe maximum authorized price; constrains the payment requirement and never relaxes verification policy.

  Exemple d'appel

  {"name": "siteborne_verify_agent_output_v3_candidate", "arguments": {"required_schema": {}, "candidate_output": {}, "verification_mode": "standard", "verification_contract": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": "texte"}}

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://utility.siteborne.net/mcp