co.proofsource/proofsource

Est-ce que co.proofsource/proofsource est sûr ?

Au dernier audit MCP Hub, le serveur MCP « co.proofsource/proofsource » 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

• add_brand≈ 291 tokens

  Start measuring a brand: does ChatGPT, Perplexity, Claude or Google AI mention it, and who does AI recommend instead? Give the brand's website (or its app store, Google Maps, YouTube or Instagram link). It reads the site, picks the buyer questions, and starts the first scan across the AI engines. Reading the site takes 1-2 minutes; if it is still running, call again with the same link and it picks up the same run, never a second one. Returns the brand_id; then use get_scan_status.

  Paramètres, retour & exemple (2)

  Paramètres

  • link · string · requis
    The brand's website, like acme.com, or its app store, Google Maps, YouTube or Instagram link.
  • description · string · optionnel
    Optional: what the brand sells, in a sentence. Only needed when add_brand says it couldn't read the website.

  Exemple d'appel

  {"name": "add_brand", "arguments": {"link": "texte"}}

  Exemple de retour

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

• create_prompt≈ 265 tokens

  Adds a buyer question to a topic so it is asked on every engine in the plan from the next run. Counts toward the plan's question limit. Calling again with the same text returns the existing question, never a duplicate.

  Paramètres, retour & exemple (4)

  Paramètres

  • text · string · requis
    The question, phrased the way a buyer would ask an AI assistant.
  • topic_id · string · requis
    Topic id from list_topics.
  • target_engines · array · optionnel
    Optional: limit to these engines. Omit for the plan's engines.
  • confirm_new_engines · boolean · optionnel
    Set true to confirm using an engine this workspace has never used before.

  Exemple d'appel

  {"name": "create_prompt", "arguments": {"text": "texte", "topic_id": "texte"}}

  Exemple de retour

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

• get_changes≈ 194 tokens

  What moved over the window: the daily mention-rate trend, how much the engines' answers changed, notable changes on competitors' websites, and new pages about the category.

  Paramètres, retour & exemple (2)

  Paramètres

  • brand_id · string · optionnel
    Brand id from list_brands. May be omitted when the workspace tracks a single brand.
  • window_days · integer · optionnel
    Trailing window in whole UTC days ending today. Default 30.

  Exemple d'appel

  {"name": "get_changes", "arguments": {"brand_id": "texte", "window_days": 1}}

  Exemple de retour

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

• get_citations≈ 302 tokens

  The websites AI answers cite for the brand's buyer questions, ranked by share of citations and by how many answers cite them, and where the brand's own site ranks.

  Paramètres, retour & exemple (4)

  Paramètres

  • limit · integer · optionnel
    Max sites per ranking. Default 25.
  • engines · array · optionnel
    Optional: only these engines (e.g. openai, perplexity, anthropic, google_aio). Default: the engines the dashboard headline counts (ChatGPT, Perplexity, Claude, Google AI Overviews, plus any the plan adds); the reply's counted_engines names them.
  • brand_id · string · optionnel
    Brand id from list_brands. May be omitted when the workspace tracks a single brand.
  • window_days · integer · optionnel
    Trailing window in whole UTC days ending today. Default 30.

  Exemple d'appel

  {"name": "get_citations", "arguments": {"limit": 1, "engines": [], "brand_id": "texte", "window_days": 1}}

  Exemple de retour

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

• get_competitors≈ 275 tokens

  The competitors AI answers name for the brand's buyer questions, per engine, with each one's share of voice against the brand and how it changed over the window.

  Paramètres, retour & exemple (3)

  Paramètres

  • engines · array · optionnel
    Optional: only these engines (e.g. openai, perplexity, anthropic, google_aio). Default: the engines the dashboard headline counts (ChatGPT, Perplexity, Claude, Google AI Overviews, plus any the plan adds); the reply's counted_engines names them.
  • brand_id · string · optionnel
    Brand id from list_brands. May be omitted when the workspace tracks a single brand.
  • window_days · integer · optionnel
    Trailing window in whole UTC days ending today. Default 30.

  Exemple d'appel

  {"name": "get_competitors", "arguments": {"engines": [], "brand_id": "texte", "window_days": 1}}

  Exemple de retour

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

• get_fix_verification≈ 223 tokens

  Each fix marked shipped for the brand with its mention rate before and after and a verdict: moved (beyond normal answer churn), within_noise, or awaiting_samples. Fixes marked "Not a fix" are left out; auto-detected page changes carry source auto_detected.

  Paramètres, retour & exemple (3)

  Paramètres

  • limit · integer · optionnel
    Most recent fixes to return. Default 20.
  • brand_id · string · optionnel
    Brand id from list_brands. May be omitted when the workspace tracks a single brand.
  • fix_event_id · string · optionnel
    Optional: just this fix.

  Exemple d'appel

  {"name": "get_fix_verification", "arguments": {"limit": 1, "brand_id": "texte", "fix_event_id": "texte"}}

  Exemple de retour

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

• get_report_link≈ 196 tokens

  A link to the brand's AI visibility report to share with a team or client: how often AI answers mention the brand, which competitors they name instead, and which sources they cite. Returns the newest finished report's own unlisted link. Reports are built automatically after a brand's first scan.

  Paramètres, retour & exemple (1)

  Paramètres

  • brand_id · string · optionnel
    Brand id from list_brands or add_brand. May be omitted when the workspace tracks a single brand.

  Exemple d'appel

  {"name": "get_report_link", "arguments": {"brand_id": "texte"}}

  Exemple de retour

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

• get_scan_status≈ 166 tokens

  Progress of a brand's first scan after add_brand: the stage, how many AI answers are in out of how many expected, per engine, and when it should finish. Once complete, use get_visibility for the results.

  Paramètres, retour & exemple (1)

  Paramètres

  • brand_id · string · optionnel
    Brand id from list_brands or add_brand. May be omitted when the workspace tracks a single brand.

  Exemple d'appel

  {"name": "get_scan_status", "arguments": {"brand_id": "texte"}}

  Exemple de retour

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

• get_visibility≈ 340 tokens

  How often ChatGPT, Perplexity, Claude and Google AI mention the brand when buyers ask about its category. by=engine (default): mention rate, share of voice, average position, citation share and sentiment per engine, with the change from the previous period. by=question: each buyer question's mention rate and rank.

  Paramètres, retour & exemple (4)

  Paramètres

  • by · string · optionnel · engine | question
    engine (default) or question.
  • engines · array · optionnel
    Optional: only these engines (e.g. openai, perplexity, anthropic, google_aio). Default: the engines the dashboard headline counts (ChatGPT, Perplexity, Claude, Google AI Overviews, plus any the plan adds); the reply's counted_engines names them.
  • brand_id · string · optionnel
    Brand id from list_brands. May be omitted when the workspace tracks a single brand.
  • window_days · integer · optionnel
    Trailing window in whole UTC days ending today. Default 30.

  Exemple d'appel

  {"name": "get_visibility", "arguments": {"by": "engine", "engines": [], "brand_id": "texte", "window_days": 1}}

  Exemple de retour

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

• list_brands≈ 106 tokens

  The brands this workspace tracks in AI answers, with ids and websites. Call first; every other tool takes a brand_id.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_brands", "arguments": {}}

  Exemple de retour

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

• list_fix_opportunities≈ 194 tokens

  The gaps that keep AI engines from citing or recommending the brand, each with its evidence and the suggested fix. Gives the gap_id mark_fix_shipped needs.

  Paramètres, retour & exemple (2)

  Paramètres

  • brand_id · string · optionnel
    Brand id from list_brands. May be omitted when the workspace tracks a single brand.
  • include_closed · boolean · optionnel
    Also return gaps that were checked and no longer apply. Default false.

  Exemple d'appel

  {"name": "list_fix_opportunities", "arguments": {"brand_id": "texte", "include_closed": true}}

  Exemple de retour

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

• list_topics≈ 152 tokens

  The topics and buyer questions this workspace asks ChatGPT, Perplexity, Claude and Google AI for a brand. Gives the topic_id create_prompt needs.

  Paramètres, retour & exemple (1)

  Paramètres

  • brand_id · string · optionnel
    Brand id from list_brands. May be omitted when the workspace tracks a single brand.

  Exemple d'appel

  {"name": "list_topics", "arguments": {"brand_id": "texte"}}

  Exemple de retour

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

• mark_fix_shipped≈ 353 tokens

  Records that a fix shipped, against a gap_id from list_fix_opportunities or a published content_draft_id, so get_fix_verification can measure whether it moved the brand's mention rate. Calling again with the same fix and description returns the existing record.

  Paramètres, retour & exemple (6)

  Paramètres

  • gap_id · string · optionnel
    The gap finding the fix addresses (one of gap_id or content_draft_id).
  • brand_id · string · optionnel
    Brand id from list_brands. May be omitted when the workspace tracks a single brand.
  • shipped_at · string · optionnel
    When it shipped: RFC 3339 timestamp or YYYY-MM-DD. Default now.
  • description · string · requis
    What shipped, in one or two sentences.
  • content_draft_id · string · optionnel
    A published content draft (one of gap_id or content_draft_id).
  • acknowledge_unfilled_gaps · boolean · optionnel
    A content draft that still has [INSERT ...] gaps is refused and the gaps listed. Set true only after the user confirms the shipped page has them filled.

  Exemple d'appel

  {"name": "mark_fix_shipped", "arguments": {"description": "texte"}}

  Exemple de retour

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

• see_example≈ 248 tokens

  Shows what Proofsource measures, without signing in: a real visibility card for one example brand (Tesla), from answers collected from ChatGPT, Perplexity, Claude and Google AI Overviews. It shows how often AI answers mention the brand, per engine, which competitors they name instead, and sample answers. Use it when someone asks whether their brand shows up in AI answers and has not signed in. It always shows the example brand; to check their own brand they sign in.

  Paramètres, retour & exemple (1)

  Paramètres

  • brand · string · optionnel
    Optional: the brand the person asked about. The example card is shown either way, with a note to sign in to check that brand.

  Exemple d'appel

  {"name": "see_example", "arguments": {"brand": "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://app.proofsource.co/v1/mcp