# Was Ihr Assistent tun kann

> Beispielfragen für den nebty-MCP-Server, welche Tools etwas ändern, und die vollständige Liste der Tools.

Sobald Sie [nebty verbunden](https://docs.nebty-id.com/de/mcp/connect/) haben, sprechen Sie mit Ihrem Assistenten in normaler Sprache. Er wählt die passenden nebty-Tools, liest die Ergebnisse und antwortet Ihnen. Er arbeitet nur mit den Brands, die Ihr nebty-Benutzer sehen kann.

## Beispielfragen

- „Liste meine Brands auf.“
- „Fasse die aktuellen Domain-Funde meiner Brand zusammen. Welche haben ein hohes Risiko?“
- „Zeige Status und Verlauf des Takedowns für `example-shop.com`.“
- „Wie viele Takedowns meiner Brand wurden erfolgreich abgeschlossen?“
- „Welche Social-Media-Profile geben sich als meine Brand aus?“
- „Gibt es Meta-Anzeigen, die meine Brand missbrauchen?“

Für vollständige Berichte bitten Sie den Assistenten, alle Seiten einer Liste zu lesen. Lange Listen kommen seitenweise, und der Assistent muss jede Seite lesen, bevor er Summen nennt.

## Tools, die etwas ändern

Die meisten Tools lesen nur. Diese 15 Tools ändern etwas, und Ihr Assistent sollte sie nur nutzen, wenn Sie darum bitten:

| Tool | Was es tut (Text, den der Assistent erhält) | Wirkung |
| - | - | - |
| `add_trusted_domain` | Add a trusted domain for an accessible brand. Adding a previously unknown domain may trigger an initial scan with DNS and HTTP requests. | Startet einen Scan oder eine Aufnahme |
| `create_social_media_takedown` | Create a social-media takedown request for an accessible brand. Requires active monitoring for non-staff users; may start enforcement workflows. | Wirkt außerhalb von nebty |
| `create_takedown` | Create a domain takedown request for an accessible brand. May start enforcement workflows; use only when the user requests a takedown. | Wirkt außerhalb von nebty |
| `dismiss_eval_result` | Dismiss a search evaluation result as a false positive for an accessible brand. | Ändert einen Eintrag |
| `dismiss_linkedin_profile` | Dismiss a LinkedIn profile from the brand's employee impersonation findings. | Ändert einen Eintrag |
| `email_sm_takedown_report` | Generate a social-media takedown PDF and SEND IT BY EMAIL to requesting\_user\_email. Use only when the user explicitly requests sending the report. Repeated calls can send repeated emails. | Wirkt außerhalb von nebty |
| `email_takedown_report` | Generate a domain takedown PDF and SEND IT BY EMAIL to requesting\_user\_email. Use only when the user explicitly requests sending the report. Repeated calls can send repeated emails. | Wirkt außerhalb von nebty |
| `inspect_domain` | Fetch a fresh screenshot for an accessible existing target. Use a domain UUID from list\_brand\_domains or list\_brand\_scans; get\_domain resolves its hostname. Target and URL must match. An upstream timeout means no screenshot was returned. | Startet einen Scan oder eine Aufnahme |
| `set_meta_ad_scan_dismissed` | Dismiss or un-dismiss a specific Meta ad for the brand. Per-ad; hidden from default view and skipped during AI relevance scoring. Independent of page trust. Countries searched describe actual historical query coverage. Meta archive coverage is limited; zero returned ads is not proof of no impersonation. Old DE scans do not cover CA/US markets. | Ändert einen Eintrag |
| `set_meta_ad_scan_trusted` | Mark a Meta page as trusted for the brand. All ads from that page\_id are annotated as is\_trusted and skipped during AI relevance scoring. Page-level; affects current and future ads. Countries searched describe actual historical query coverage. Meta archive coverage is limited; zero returned ads is not proof of no impersonation. Old DE scans do not cover CA/US markets. | Ändert einen Eintrag |
| `set_social_media_scan_dismissed` | Dismiss or un-dismiss a profile for the brand associated with this scan. | Ändert einen Eintrag |
| `set_social_media_scan_trusted` | Set or unset a profile as trusted for the brand associated with this scan. | Ändert einen Eintrag |
| `submit_scan_feedback` | Submit feedback on a domain scan result. | Ändert einen Eintrag |
| `trigger_meta_ad_scan` | Trigger a Meta Ad Library scan for a specific brand Countries searched describe actual historical query coverage. Meta archive coverage is limited; zero returned ads is not proof of no impersonation. Old DE scans do not cover CA/US markets. | Startet einen Scan oder eine Aufnahme |
| `trust_linkedin_profile` | Mark a LinkedIn profile as trusted for an accessible brand, affecting future impersonation evaluation. | Ändert einen Eintrag |

Was die Wirkungen bedeuten:

- **Ändert einen Eintrag:** ändert Daten in nebty, zum Beispiel markiert einen Fund als vertrauenswürdig oder blendet ihn aus.
- **Startet einen Scan oder eine Aufnahme:** nebty ruft eine externe Website auf oder startet einen neuen Scan, zum Beispiel einen neuen Screenshot einer Domain.
- **Wirkt außerhalb von nebty:** startet einen Takedown oder versendet eine E-Mail. Das lässt sich nicht rückgängig machen. Erlauben Sie diese Aufrufe nur, wenn Sie es wirklich wollen.

## Alle Tools

Diese Liste enthält alle 57 Tools des nebty-MCP-Servers (Version 0.2.0). Die Beschreibungen sind genau die Texte, die Ihr Assistent erhält. Deshalb sind sie auf Englisch und für den Assistenten geschrieben.

**Brands, Domains und Scans** (10)

| Tool | Was es tut (Text, den der Assistent erhält) | Wirkung |
| - | - | - |
| `add_trusted_domain` | Add a trusted domain for an accessible brand. Adding a previously unknown domain may trigger an initial scan with DNS and HTTP requests. | Startet einen Scan oder eine Aufnahme |
| `get_brand` | Retrieve one accessible brand by ID, including its monitoring configuration. | Nur lesen |
| `get_brand_risk_timeline` | Get historical risk data for a specific brand over the last N days | Nur lesen |
| `get_brand_stats` | Retrieve brand statistics. Prefer domain\_risk\_distribution for domain counts: it includes zero-risk, unscanned and unknown-risk buckets and sums to domain\_count. Legacy risk\_distribution counts historical scan rows at scores 1+ and is not the complete domain population. | Nur lesen |
| `get_domain` | Retrieve a monitored domain by brand ID and domain UUID, including detailed scan evidence. Use IDs from list\_brand\_domains or list\_brand\_scans; caller must have access to the brand. | Nur lesen |
| `inspect_domain` | Fetch a fresh screenshot for an accessible existing target. Use a domain UUID from list\_brand\_domains or list\_brand\_scans; get\_domain resolves its hostname. Target and URL must match. An upstream timeout means no screenshot was returned. | Startet einen Scan oder eine Aufnahme |
| `list_brand_domains` | List compact monitored domain summaries for one accessible brand. Includes IDs, hostnames and latest brand-specific risk/verdict. Use get\_domain for detailed evidence and history. Defaults to 20 items per page. Keep page\_size and filters unchanged while paging; follow next until null. If too large, restart at page 1 with smaller page\_size. Never report partial results as complete. | Nur lesen |
| `list_brand_scans` | List compact scan summaries for a brand, including domain UUID and domain\_name. Use get\_domain with the brand ID and domain UUID for detailed evidence. Defaults to 20 items per page. Keep page\_size and filters unchanged while paging; follow next until null. If too large, restart at page 1 with smaller page\_size. Never report partial results as complete. | Nur lesen |
| `list_brands` | List brands the authenticated user can access. Use their IDs for subsequent brand-specific lookups and get\_brand\_stats for statistics. Defaults to 20 items per page. Keep page\_size and filters unchanged while paging; follow next until null. If too large, restart at page 1 with smaller page\_size. Never report partial results as complete. | Nur lesen |
| `submit_scan_feedback` | Submit feedback on a domain scan result. | Ändert einen Eintrag |

**Suchergebnisse** (5)

| Tool | Was es tut (Text, den der Assistent erhält) | Wirkung |
| - | - | - |
| `dismiss_eval_result` | Dismiss a search evaluation result as a false positive for an accessible brand. | Ändert einen Eintrag |
| `get_eval_dismissal` | Retrieve an existing search evaluation dismissal by ID. | Nur lesen |
| `get_google_eval_scan` | Retrieve a specific Google Eval scan by ID | Nur lesen |
| `list_eval_dismissals` | List eval result dismissals (staff see all, users see only those for brands they have access to) Defaults to 20 items per page. Keep page\_size and filters unchanged while paging; follow next until null. If too large, restart at page 1 with smaller page\_size. Never report partial results as complete. | Nur lesen |
| `list_google_eval_scans` | List Google Eval scans with optional filtering Defaults to 20 items per page. Keep page\_size and filters unchanged while paging; follow next until null. If too large, restart at page 1 with smaller page\_size. Never report partial results as complete. | Nur lesen |

**Social Media** (4)

| Tool | Was es tut (Text, den der Assistent erhält) | Wirkung |
| - | - | - |
| `get_social_media_scan` | Retrieve a specific Social Media scan by ID | Nur lesen |
| `list_social_media_scans` | List Social Media scans with optional filtering Defaults to 20 items per page. Keep page\_size and filters unchanged while paging; follow next until null. If too large, restart at page 1 with smaller page\_size. Never report partial results as complete. | Nur lesen |
| `set_social_media_scan_dismissed` | Dismiss or un-dismiss a profile for the brand associated with this scan. | Ändert einen Eintrag |
| `set_social_media_scan_trusted` | Set or unset a profile as trusted for the brand associated with this scan. | Ändert einen Eintrag |

**Anzeigen (Meta Ad Library)** (9)

| Tool | Was es tut (Text, den der Assistent erhält) | Wirkung |
| - | - | - |
| `get_meta_ad_brand_aggregate` | Get aggregated Meta Ad Library scan results for a specific brand across all keywords Countries searched describe actual historical query coverage. Meta archive coverage is limited; zero returned ads is not proof of no impersonation. Old DE scans do not cover CA/US markets. | Nur lesen |
| `get_meta_ad_scan` | Retrieve one Meta Ad Library scan and its brand-abuse findings by ID. Countries searched describe actual historical query coverage. Meta archive coverage is limited; zero returned ads is not proof of no impersonation. Old DE scans do not cover CA/US markets. | Nur lesen |
| `list_latest_meta_ad_scans` | Get the latest successful Meta Ad Library scan results for a brand, falling back through history to skip failures Countries searched describe actual historical query coverage. Meta archive coverage is limited; zero returned ads is not proof of no impersonation. Old DE scans do not cover CA/US markets. Defaults to 20 items per page. Keep page\_size and filters unchanged while paging; follow next until null. If too large, restart at page 1 with smaller page\_size. Never report partial results as complete. | Nur lesen |
| `list_meta_ad_scans` | List Meta Ad Library scans with optional filtering Countries searched describe actual historical query coverage. Meta archive coverage is limited; zero returned ads is not proof of no impersonation. Old DE scans do not cover CA/US markets. Defaults to 20 items per page. Keep page\_size and filters unchanged while paging; follow next until null. If too large, restart at page 1 with smaller page\_size. Never report partial results as complete. | Nur lesen |
| `list_meta_ad_scans_by_brand` | Get Meta Ad Library scan results for a specific brand Countries searched describe actual historical query coverage. Meta archive coverage is limited; zero returned ads is not proof of no impersonation. Old DE scans do not cover CA/US markets. Defaults to 20 items per page. Keep page\_size and filters unchanged while paging; follow next until null. If too large, restart at page 1 with smaller page\_size. Never report partial results as complete. | Nur lesen |
| `list_meta_ads` | List a brand's Meta ads, one compact row per ad (newest first, deduplicated across keywords). Requires brand\_id. Prefer this over the scan tools: page\_size=1 returns one ad. Filters: exclude\_trusted, exclude\_dismissed, active\_only, search\_term. Reach, targeting and spend are omitted unless include=demographics (large). Countries searched describe actual historical query coverage. Meta archive coverage is limited; zero returned ads is not proof of no impersonation. Old DE scans do not cover CA/US markets. Defaults to 20 items per page. Keep page\_size and filters unchanged while paging; follow next until null. If too large, restart at page 1 with smaller page\_size. Never report partial results as complete. | Nur lesen |
| `set_meta_ad_scan_dismissed` | Dismiss or un-dismiss a specific Meta ad for the brand. Per-ad; hidden from default view and skipped during AI relevance scoring. Independent of page trust. Countries searched describe actual historical query coverage. Meta archive coverage is limited; zero returned ads is not proof of no impersonation. Old DE scans do not cover CA/US markets. | Ändert einen Eintrag |
| `set_meta_ad_scan_trusted` | Mark a Meta page as trusted for the brand. All ads from that page\_id are annotated as is\_trusted and skipped during AI relevance scoring. Page-level; affects current and future ads. Countries searched describe actual historical query coverage. Meta archive coverage is limited; zero returned ads is not proof of no impersonation. Old DE scans do not cover CA/US markets. | Ändert einen Eintrag |
| `trigger_meta_ad_scan` | Trigger a Meta Ad Library scan for a specific brand Countries searched describe actual historical query coverage. Meta archive coverage is limited; zero returned ads is not proof of no impersonation. Old DE scans do not cover CA/US markets. | Startet einen Scan oder eine Aufnahme |

**LinkedIn** (6)

| Tool | Was es tut (Text, den der Assistent erhält) | Wirkung |
| - | - | - |
| `dismiss_linkedin_profile` | Dismiss a LinkedIn profile from the brand's employee impersonation findings. | Ändert einen Eintrag |
| `get_linkedin_radar_profile` | Retrieve an accessible LinkedIn profile. status is its human review decision; presence and consecutive\_misses describe observation freshness. NEW does not mean recently seen, and missing observations do not prove employment ended. | Nur lesen |
| `get_linkedin_radar_scan` | Retrieve a LinkedIn employee impersonation scan by ID. | Nur lesen |
| `list_linkedin_radar_profiles` | List LinkedIn Employee Radar profiles, newest first (staff see all, users see only those for brands they have access to) status is a review decision; use presence and consecutive\_misses for freshness. Defaults to 20 items per page. Keep page\_size and filters unchanged while paging; follow next until null. If too large, restart at page 1 with smaller page\_size. Never report partial results as complete. | Nur lesen |
| `list_linkedin_radar_scans` | List LinkedIn Employee Radar scans, newest first (staff see all, users see only those for brands they have access to) Defaults to 20 items per page. Keep page\_size and filters unchanged while paging; follow next until null. If too large, restart at page 1 with smaller page\_size. Never report partial results as complete. | Nur lesen |
| `trust_linkedin_profile` | Mark a LinkedIn profile as trusted for an accessible brand, affecting future impersonation evaluation. | Ändert einen Eintrag |

**Takedowns** (19)

| Tool | Was es tut (Text, den der Assistent erhält) | Wirkung |
| - | - | - |
| `create_social_media_takedown` | Create a social-media takedown request for an accessible brand. Requires active monitoring for non-staff users; may start enforcement workflows. | Wirkt außerhalb von nebty |
| `create_takedown` | Create a domain takedown request for an accessible brand. May start enforcement workflows; use only when the user requests a takedown. | Wirkt außerhalb von nebty |
| `email_sm_takedown_report` | Generate a social-media takedown PDF and SEND IT BY EMAIL to requesting\_user\_email. Use only when the user explicitly requests sending the report. Repeated calls can send repeated emails. | Wirkt außerhalb von nebty |
| `email_takedown_report` | Generate a domain takedown PDF and SEND IT BY EMAIL to requesting\_user\_email. Use only when the user explicitly requests sending the report. Repeated calls can send repeated emails. | Wirkt außerhalb von nebty |
| `get_sm_takedown_abuse_contact` | Retrieve an abuse contact belonging to a social-media takedown. | Nur lesen |
| `get_sm_takedown_event` | Retrieve one audit event belonging to a social-media takedown. | Nur lesen |
| `get_social_media_takedown` | Retrieve a social-media takedown request and its current status by ID. | Nur lesen |
| `get_takedown` | Retrieve a specific takedown request | Nur lesen |
| `get_takedown_abuse_contact` | Retrieve one abuse contact belonging to a domain takedown. | Nur lesen |
| `get_takedown_aggregate` | Count accessible takedowns by status and resolution with brand, status, resolution and creation-time filters. Use successful\_closed\_count for successful outcomes, never CLOSED alone. UNRESOLVED, FALSE\_POSITIVE and unspecified outcomes are not successes. Creation filters do not measure closures during a period. | Nur lesen |
| `get_takedown_blacklist_submission` | Retrieve one blacklist submission belonging to a domain takedown. | Nur lesen |
| `get_takedown_event` | Retrieve one audit event belonging to a domain takedown. | Nur lesen |
| `list_sm_takedown_abuse_contacts` | List abuse contacts belonging to a social-media takedown. Defaults to 20 items per page. Keep page\_size and filters unchanged while paging; follow next until null. If too large, restart at page 1 with smaller page\_size. Never report partial results as complete. | Nur lesen |
| `list_sm_takedown_events` | List audit events belonging to a social-media takedown. Defaults to 20 items per page. Keep page\_size and filters unchanged while paging; follow next until null. If too large, restart at page 1 with smaller page\_size. Never report partial results as complete. | Nur lesen |
| `list_social_media_takedowns` | List social media takedown requests (staff see all, users see only those for brands they have access to) Defaults to 20 items per page. Keep page\_size and filters unchanged while paging; follow next until null. If too large, restart at page 1 with smaller page\_size. Never report partial results as complete. | Nur lesen |
| `list_takedown_abuse_contacts` | List abuse contacts belonging to a domain takedown. Defaults to 20 items per page. Keep page\_size and filters unchanged while paging; follow next until null. If too large, restart at page 1 with smaller page\_size. Never report partial results as complete. | Nur lesen |
| `list_takedown_blacklist_submissions` | List blacklist submissions belonging to a domain takedown. Defaults to 20 items per page. Keep page\_size and filters unchanged while paging; follow next until null. If too large, restart at page 1 with smaller page\_size. Never report partial results as complete. | Nur lesen |
| `list_takedown_events` | List audit events belonging to a domain takedown. Defaults to 20 items per page. Keep page\_size and filters unchanged while paging; follow next until null. If too large, restart at page 1 with smaller page\_size. Never report partial results as complete. | Nur lesen |
| `list_takedowns` | List accessible domain takedowns, filtered by brand, status, resolution and creation time. CLOSED does not imply success; use get\_takedown\_aggregate for outcome KPIs. Defaults to 5 cases per page. Keep page\_size and filters unchanged and follow every next page until next is null for complete reports. If a page exceeds the response limit, restart at page 1 with a smaller page\_size (minimum 1); do not report partial results as complete. created\_after is inclusive; created\_before is exclusive. These filter creation time, not closure time. | Nur lesen |

**Konto und Einstellungen** (4)

| Tool | Was es tut (Text, den der Assistent erhält) | Wirkung |
| - | - | - |
| `get_communication_settings` | Retrieve an accessible notification configuration by ID. | Nur lesen |
| `get_my_profile` | Get the authenticated user's profile information | Nur lesen |
| `list_communication_settings` | List the authenticated user's accessible notification configurations. Defaults to 20 items per page. Keep page\_size and filters unchanged while paging; follow next until null. If too large, restart at page 1 with smaller page\_size. Never report partial results as complete. | Nur lesen |
| `poll_agent_run` | Poll the status of an agent run by its key. Returns 204 while the run is pending or in progress, the result object when completed, or an error payload when failed. | Nur lesen |