ai.nothumansearch/search

Est-ce que ai.nothumansearch/search est sûr ?

Au dernier audit MCP Hub, le serveur MCP « ai.nothumansearch/search » 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 14 outils

• check_url≈ 197 tokens

  On-demand agentic-readiness check for any URL. Runs the NHS 7-signal crawler live (llms.txt, ai-plugin.json, OpenAPI, structured API, MCP server, robots.txt AI rules, Schema.org) and returns a score 0-100 with per-signal breakdown. Use before calling an unfamiliar API to confirm it's agent-usable. Re-runnable without the submissions-table side-effect of submit_site — ideal for verify-before-use workflows.

  Paramètres, retour & exemple (1)

  Paramètres

  • url · string · requis
    Full URL or bare domain (e.g. 'stripe.com' or 'https://stripe.com'). Homepage works best — NHS probes the /.well-known/ paths, /robots.txt, /llms.txt relative to the site root.

  Exemple d'appel

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

  Exemple de retour

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

• find_mcp_servers≈ 284 tokens

  List sites in the index that expose a live MCP server, ranked by agentic readiness. The result set carries a query-free discovery receipt and any eligible provider-funded actions appear separately without changing organic order. Pairs naturally with verify_mcp for a probe-before-use workflow.

  Paramètres, retour & exemple (3)

  Paramètres

  • limit · integer · optionnel
    Max results (default 10, max 20)
  • query · string · optionnel
    Optional keyword to narrow results (e.g. 'payments', 'jobs', 'weather')
  • category · string · optionnel · ai-tools | developer | data | finance | ecommerce | jobs | security | health
    Filter by public category (ai-tools, developer, data, finance, ecommerce, jobs, security, health, education, communication, productivity, news). Audit-only buckets may appear in /api/v1/categories as other or spam, but are not promoted as discovery inventory. Omit for all categories.

  Exemple d'appel

  {"name": "find_mcp_servers", "arguments": {"limit": 1, "query": "texte", "category": "ai-tools"}}

  Exemple de retour

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

• get_site_details≈ 264 tokens

  Get the full agentic readiness report for a specific domain: score, category, all 7 signal checks (llms.txt, ai-plugin.json, OpenAPI, structured API, MCP server, robots.txt AI rules, Schema.org), plus any cached llms.txt content and OpenAPI summary. When an exact search_id newly records this organic-result selection, the response also carries an optional record_action_interest opportunity for this domain. Selection alone is never interest and never contacts the provider.

  Paramètres, retour & exemple (2)

  Paramètres

  • domain · string · requis
    Domain to look up (e.g. 'stripe.com'). Do not include scheme or path.
  • search_id · string · optionnel
    Optional receipt returned by a receipt-bearing NHS discovery tool. If this domain was returned, NHS records a detail selection and may return a separate, noncommercial action-interest opportunity requiring explicit current-principal attestation.

  Exemple d'appel

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

  Exemple de retour

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

• get_stats≈ 79 tokens

  Current Not Human Search index stats: total sites, average agentic score, top category, sites added in the last 7 days, count of sites exposing an MCP server, and count scoring a perfect 100/100.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_stats", "arguments": {}}

  Exemple de retour

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

• get_top_sites≈ 272 tokens

  Get the highest-scored agent-ready sites in the index, optionally filtered by category. Organic order is always readiness-score order. A supported category creates a query-free discovery receipt that can support separately disclosed provider-funded actions and explicit action interest; unfiltered browsing stays free and does not enter the Stage 1 demand cohort.

  Paramètres, retour & exemple (2)

  Paramètres

  • limit · integer · optionnel
    Max results (default 10, max 50)
  • category · string · optionnel · ai-tools | developer | data | finance | ecommerce | jobs | security | health
    Filter by public category (ai-tools, developer, data, finance, ecommerce, jobs, security, health, education, communication, productivity, news). Audit-only buckets may appear in /api/v1/categories as other or spam, but are not promoted as discovery inventory. Omit for all categories.

  Exemple d'appel

  {"name": "get_top_sites", "arguments": {"limit": 1, "category": "ai-tools"}}

  Exemple de retour

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

• handoff_provider_action≈ 528 tokens

  Present the exact ticket bearer returned by prepare_provider_action. NHS records one privacy-safe handoff receipt, then returns the attributed provider action URL. Optionally and separately, the principal may authorize the exact DNS-verified provider to resolve only the ticket's controlled topic, region, USD budget band, urgency, and allowlisted requirement flags. Declining that optional disclosure does not block the handoff. No query, contact detail, agent/principal identity, network address, referrer, or user-agent is disclosed. The handoff and resolver charge neither party; only the provider's configured downstream outcome can create a provider charge.

  Paramètres, retour & exemple (6)

  Paramètres

  • ticket_id · string · requis
    Action ticket ID returned by prepare_provider_action.
  • attribution_token · string · requis
    Exact bearer returned by prepare_provider_action; NHS does not store the raw token.
  • handoff_consent_version · string · requis · nhs-provider-handoff-consent-v1
    https://nothumansearch.ai/privacy#handoff-consent-v1
  • principal_handoff_consent · boolean · requis
    Caller attests the principal authorized the separate observed handoff under the exact published wording.
  • controlled_intent_disclosure_consent_version · string · optionnel · nhs-provider-controlled-intent-disclosure-consent-v1
    https://nothumansearch.ai/privacy#controlled-intent-disclosure-consent-v1; required only when the optional disclosure consent is true.
  • principal_controlled_intent_disclosure_consent · boolean · optionnel
    Optional separate authorization for the exact DNS-verified provider to resolve the bounded controlled-intent bundle after handoff. False or omitted does not block handoff.

  Exemple d'appel

  {"name": "handoff_provider_action", "arguments": {"ticket_id": "texte", "attribution_token": "texte", "handoff_consent_version": "nhs-provider-handoff-consent-v1", "principal_handoff_consent": true}}

  Exemple de retour

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

• list_categories≈ 94 tokens

  List all categories in the Not Human Search index with site counts and average agentic scores. Use this to understand what kinds of agent-ready services exist before searching — counts are live, so the distribution shifts as the index grows.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_categories", "arguments": {}}

  Exemple de retour

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

• prepare_provider_action≈ 610 tokens

  Prepare a signed action ticket for a separately disclosed provider-funded offer returned beside a receipt-bearing NHS discovery result. This step never returns the provider action URL or records a handoff. It requires the discovery receipt and the caller's explicit ticket-authorization attestation. It accepts controlled constraints only—no name, email, contact detail, raw prompt, agent identity, or principal identity fields. Discovery and direct provider access remain free; preparing a ticket charges neither party. Exact v1 wording: https://nothumansearch.ai/privacy#consent-v1

  Paramètres, retour & exemple (9)

  Paramètres

  • urgency · string · optionnel · unspecified | now | 7_days | 30_days | researching
  • offer_id · string · requis
    Provider-funded offer ID returned separately beside a receipt-bearing NHS discovery result.
  • search_id · string · requis
    Discovery receipt proving the provider appeared organically.
  • budget_band · string · optionnel · unspecified | under_100 | 100_499 | 500_1999 | 2000_plus
  • region_code · string · optionnel
    Optional uppercase ISO country or country-region code.
  • demand_topic · string · requis · payments | commerce | jobs | data | search | weather | maps | email
    One controlled topic already present on the referenced search receipt.
  • consent_version · string · requis · nhs-principal-consent-v1
    https://nothumansearch.ai/privacy#consent-v1
  • principal_consent · boolean · requis
    Caller attests that the human/company principal authorized this ticket preparation under the published versioned wording.
  • requirement_flags · array · optionnel

  Exemple d'appel

  {"name": "prepare_provider_action", "arguments": {"offer_id": "texte", "search_id": "texte", "demand_topic": "payments", "consent_version": "nhs-principal-consent-v1", "principal_consent": true}}

  Exemple de retour

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

• recent_additions≈ 296 tokens

  List agent-ready sites newly added to the Not Human Search index, sorted newest first. A supported category creates a query-free discovery receipt that can support separately disclosed provider-funded actions and explicit action interest; unfiltered catalog watching stays free and does not enter the Stage 1 demand cohort.

  Paramètres, retour & exemple (3)

  Paramètres

  • days · integer · optionnel
    Look back window in days (default 7, max 90)
  • limit · integer · optionnel
    Max results (default 10, max 50)
  • category · string · optionnel · ai-tools | developer | data | finance | ecommerce | jobs | security | health
    Filter by public category (ai-tools, developer, data, finance, ecommerce, jobs, security, health, education, communication, productivity, news). Audit-only buckets may appear in /api/v1/categories as other or spam, but are not promoted as discovery inventory. Omit for all categories.

  Exemple d'appel

  {"name": "recent_additions", "arguments": {"days": 1, "limit": 1, "category": "ai-tools"}}

  Exemple de retour

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

• record_action_interest≈ 424 tokens

  Record the caller's attestation that its human or company principal currently wants one controlled next step with a site returned organically by a receipt-bearing NHS discovery tool. This creates a private Stage 1 demand receipt that expires with the source discovery receipt, no later than 30 days after it. It does not contact the provider, create an action ticket or charge, change rank or score, or count as commercial proof. No query, contact data, free-form text, or agent/principal identity is accepted. Exact v1 wording: https://nothumansearch.ai/privacy#action-interest-v1

  Paramètres, retour & exemple (5)

  Paramètres

  • domain · string · requis
    Bare domain that appeared in the referenced organic results; no scheme or path.
  • search_id · string · requis
    Committed privacy-safe receipt returned by a receipt-bearing NHS discovery tool.
  • action_type · string · requis · quote | trial | demo | booking | application | signup | purchase
    The one next step the principal currently wants.
  • confirmation_version · string · requis · nhs-action-interest-v1
    https://nothumansearch.ai/privacy#action-interest-v1
  • caller_attests_principal_interest · boolean · requis
    Caller attests current principal interest under the exact published v1 wording; this is not authority to contact the provider.

  Exemple d'appel

  {"name": "record_action_interest", "arguments": {"domain": "texte", "search_id": "texte", "action_type": "quote", "confirmation_version": "nhs-action-interest-v1", "caller_attests_principal_interest": true}}

  Exemple de retour

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

• register_monitor≈ 171 tokens

  Register an email to get alerted when the indicated domain's agentic readiness score drops. Useful for agents tracking a dependency's agent-readiness health — e.g. an agent that relies on stripe.com's MCP surface wants to know the moment it regresses. Returns an unsubscribe URL. Multiple monitors per email allowed, one per domain.

  Paramètres, retour & exemple (2)

  Paramètres

  • email · string · requis
    Email address to receive alert
  • domain · string · requis
    Domain to monitor (no scheme, e.g. 'stripe.com')

  Exemple d'appel

  {"name": "register_monitor", "arguments": {"email": "texte", "domain": "texte"}}

  Exemple de retour

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

• search_agents≈ 431 tokens

  Search for websites, APIs, and services that AI agents can actually use. Results are ranked by agentic readiness score (0-100) based on llms.txt, OpenAPI specs, ai-plugin.json, structured APIs, and MCP server availability. Use this to discover payment APIs, job boards, data sources, or any web service your agent needs to call.

  Paramètres, retour & exemple (8)

  Paramètres

  • limit · integer · optionnel
    Max results (default 10, max 20)
  • query · string · optionnel
    Keyword query (e.g. 'payment API', 'weather data', 'job board')
  • has_api · boolean · optionnel
    Only return sites with a documented structured API
  • has_mcp · boolean · optionnel
    Only return sites that expose an MCP server
  • category · string · optionnel · ai-tools | developer | data | finance | ecommerce | jobs | security | health
    Filter by public category (ai-tools, developer, data, finance, ecommerce, jobs, security, health, education, communication, productivity, news). Audit-only buckets may appear in /api/v1/categories as other or spam, but are not promoted as discovery inventory.
  • min_score · integer · optionnel
    Minimum agentic readiness score 0-100 (higher = more agent-ready)
  • has_openapi · boolean · optionnel
    Only return sites with a published OpenAPI / Swagger spec
  • has_llms_txt · boolean · optionnel
    Only return sites that publish an llms.txt file (LLM-first site summary)

  Exemple d'appel

  {"name": "search_agents", "arguments": {"limit": 1, "query": "texte", "has_api": true, "has_mcp": true, "category": "ai-tools", "min_score": 1}}

  Exemple de retour

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

• submit_site≈ 192 tokens

  Submit a URL for NHS to crawl and score. Use when you discover an agent-first tool, API, or service that isn't in the index yet. NHS will fetch the site, check its 7 agentic signals (llms.txt, ai-plugin.json, OpenAPI, structured API, MCP server, robots.txt AI rules, Schema.org), compute a score, and add it to the index. The site becomes searchable within a few seconds if the crawl succeeds.

  Paramètres, retour & exemple (1)

  Paramètres

  • url · string · requis
    Full URL to submit (include scheme, e.g. 'https://example.com'). Homepage is best — NHS will check /.well-known/ paths, /robots.txt, /llms.txt, etc. relative to the site root.

  Exemple d'appel

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

  Exemple de retour

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

• verify_mcp≈ 151 tokens

  Actively probe any URL to check if it is a live, spec-compliant MCP server. Sends a JSON-RPC tools/list request and verifies a valid response. Use this before depending on a third-party MCP endpoint — manifests and documentation can claim MCP support without actually serving it. Returns {verified: true/false, endpoint, note}.

  Paramètres, retour & exemple (1)

  Paramètres

  • url · string · requis
    Full URL of the MCP endpoint to probe (include scheme, e.g. 'https://example.com/mcp').

  Exemple d'appel

  {"name": "verify_mcp", "arguments": {"url": "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://nothumansearch.ai/mcp