accueil / serveurs / Recherche & Web / tech.botclaw/agent-observer
tech.botclaw/agent-observer
serveur MCP (Model Context Protocol) · botclaw 1.2.0
Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur.
Est-ce que tech.botclaw/agent-observer est sûr ?
Au dernier audit MCP Hub, le serveur MCP « tech.botclaw/agent-observer » 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 11 outils
- botclaw_choose≈ 749 tokens
Apply deterministic task, hosting, platform, budget and access gates to published dossiers. Each candidate has sourced reasons, explicit unknowns and hosting conflicts. No performance scores, account-access guarantee, inference, purchase or setup action. no-new-subscription does not establish free inference.
Paramètres, retour & exemple (6)
Paramètrestask· string · optionnel · collect | memory | office | personalaccess· string · optionnel · any | generalbudget· string · optionnel · flexible | no-new-subscriptionhosting· string · optionnel · any | self-managed | hostedlanguage· string · optionnel · en | zhplatform· string · optionnel · any | windows | macos | linux | web | mobile
Exemple d'appel{"name": "botclaw_choose", "arguments": {"task": "collect", "access": "any", "budget": "flexible", "hosting": "any", "language": "en", "platform": "any"}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"_trust": {}, "inputs": {}, "choices": [], "language": "en", "limitations": [], "rulesVersion": "texte"}} - botclaw_compare≈ 606 tokens
Compare source-backed capabilities and explicit unknowns for the seven products. Filters can shortlist documented self-managed options. This is official documentation, not a tested product ranking or current account-access guarantee.
Paramètres, retour & exemple (3)
Paramètreslanguage· string · optionnel · en | zhproducts· array · optionnelselfHosted· boolean · optionnel
Exemple d'appel{"name": "botclaw_compare", "arguments": {"language": "en", "products": [], "selfHosted": true}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"_trust": {}, "evidence": "texte", "language": "en", "profiles": [], "reviewedAt": "texte", "limitations": []}} - botclaw_get_catalog≈ 556 tokens
List the seven tracked products, category and content-type IDs, and the public MCP's paging and language options. Use these IDs in other tools.
Paramètres, retour & exemple (1)
Paramètreslanguage· string · optionnel · en | zh
Exemple d'appel{"name": "botclaw_get_catalog", "arguments": {"language": "en"}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"_trust": {}, "maxPage": 1, "language": "en", "pageSize": 1, "products": [], "timeZone": "texte", "languages": [], "categories": [], "contentTypes": [], "defaultLanguage": "texte"}} - botclaw_get_changes≈ 1503 tokens
Read a sequence-ordered change stream after a decimal cursor. Start at 0, persist nextCursor only after applying the page, and continue while hasMore. Upserts contain the current published projection; withdrawn events contain only ID/revision/date, item=null. Remove withdrawn records locally. Replaying a page is safe. This is not a historical full-text archive.
Paramètres, retour & exemple (3)
Paramètreslimit· integer · optionnelcursor· string · optionnellanguage· string · optionnel · en | zh
Exemple d'appel{"name": "botclaw_get_changes", "arguments": {"limit": 1, "cursor": "texte", "language": "en"}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"_trust": {}, "cursor": "texte", "changes": [], "hasMore": true, "nextCursor": "texte", "highWatermark": "texte"}} - botclaw_get_daily≈ 806 tokens
Read public items dated on a real YYYY-MM-DD calendar day in Asia/Shanghai. Omit date for today. This is a date index, not an AI-generated daily report. reviewedAt is a source-review date, not a publication date. Returns 20 items per page.
Paramètres, retour & exemple (4)
Paramètresdate· string · optionnelpage· integer · optionnelproduct· string · optionnel · openclaw | hermes | muse | cue | grok-bot | instinct | dotlanguage· string · optionnel · en | zh
Exemple d'appel{"name": "botclaw_get_daily", "arguments": {"date": "texte", "page": 1, "product": "openclaw", "language": "en"}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"date": "texte", "kind": "texte", "page": 1, "items": [], "query": {}, "total": 1, "_trust": {}, "hasMore": true, "language": "en", "pageSize": 1, "timeZone": "texte"}} - botclaw_get_item≈ 1289 tokens
Read one published record by stable ID, with body, applicable conditions, evidence type, revision and canonical citation URL. Missing or withdrawn records return item=null. Original-source excerpts are not independent execution evidence.
Paramètres, retour & exemple (2)
Paramètresid· string · requislanguage· string · optionnel · en | zh
Exemple d'appel{"name": "botclaw_get_item", "arguments": {"id": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"item": "texte", "_trust": {}}} - botclaw_get_latest≈ 856 tokens
Read the latest dated agent news, newest first. Defaults to news; choose content_type guide, experience or review for other reading. Filters are listed by botclaw_get_catalog. Results have 20 items per page; use hasMore and page to continue.
Paramètres, retour & exemple (6)
Paramètrespage· integer · optionnelproduct· string · optionnel · openclaw | hermes | muse | cue | grok-bot | instinct | dotcategory· string · optionnel · release | workflow | integration | deployment | securitylanguage· string · optionnel · en | zhselected· boolean · optionnelcontent_type· string · optionnel · news | guide | experience | review
Exemple d'appel{"name": "botclaw_get_latest", "arguments": {"page": 1, "product": "openclaw", "category": "release", "language": "en", "selected": true, "content_type": "news"}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"date": "texte", "kind": "texte", "page": 1, "items": [], "query": {}, "total": 1, "_trust": {}, "hasMore": true, "language": "en", "pageSize": 1, "timeZone": "texte"}} - botclaw_get_observations≈ 1453 tokens
Read published bilingual version radar, weekly editions, question guides or product dossiers. Includes full bodies, source dates, review dates and weekly coverage cutoff. Editorial interpretation is not product execution. Use product to include records discussing that product, including multi-product guides.
Paramètres, retour & exemple (5)
Paramètresq· string · optionnelpage· integer · optionnelproduct· string · optionnel · openclaw | hermes | muse | cue | grok-bot | instinct | dotsection· string · optionnel · radar | weekly | topic | profilelanguage· string · optionnel · en | zh
Exemple d'appel{"name": "botclaw_get_observations", "arguments": {"q": "texte", "page": 1, "product": "openclaw", "section": "radar", "language": "en"}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"page": 1, "items": [], "total": 1, "_trust": {}, "hasMore": true, "section": "radar", "language": "en", "pageSize": 1}} - botclaw_get_sources≈ 543 tokens
List public source URLs, source origin (official or independent), collection state, last successful collection, and item counts. Manual sources are editorially reviewed; they are not automatic collectors.
Paramètres, retour & exemple (2)
Paramètresproduct· string · optionnel · openclaw | hermes | muse | cue | grok-bot | instinct | dotlanguage· string · optionnel · en | zh
Exemple d'appel{"name": "botclaw_get_sources", "arguments": {"product": "openclaw", "language": "en"}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"_trust": {}, "counts": [], "sources": [], "language": "en", "automaticSummaries": true, "automaticCollection": true}} - botclaw_get_workflows≈ 802 tokens
Find owned, reproducible workflow procedures. Each list entry has a stable ID; call get_item for the steps and actual verification boundary. Only the Node RSS example currently has execution evidence. Does not run workflows.
Paramètres, retour & exemple (4)
Paramètresq· string · optionnelpage· integer · optionnelproduct· string · optionnel · openclaw | hermes | muse | cue | grok-bot | instinct | dotlanguage· string · optionnel · en | zh
Exemple d'appel{"name": "botclaw_get_workflows", "arguments": {"q": "texte", "page": 1, "product": "openclaw", "language": "en"}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"date": "texte", "kind": "texte", "page": 1, "items": [], "query": {}, "total": 1, "_trust": {}, "hasMore": true, "language": "en", "pageSize": 1, "timeZone": "texte"}} - botclaw_search≈ 888 tokens
Search published titles, summaries and owned workflow text using bounded bilingual keyword aliases (1–80 characters). Product, content type and category filters apply. Returns up to 20 records per page, not a generated answer or live-internet search. Use get_item to inspect conditions, evidence and citation URLs.
Paramètres, retour & exemple (7)
Paramètresq· string · requispage· integer · optionnelproduct· string · optionnel · openclaw | hermes | muse | cue | grok-bot | instinct | dotcategory· string · optionnel · release | workflow | integration | deployment | securitylanguage· string · optionnel · en | zhselected· boolean · optionnelcontent_type· string · optionnel · news | guide | experience | review
Exemple d'appel{"name": "botclaw_search", "arguments": {"q": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"date": "texte", "kind": "texte", "page": 1, "items": [], "query": {}, "total": 1, "_trust": {}, "hasMore": true, "language": "en", "pageSize": 1, "timeZone": "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 ».