io.github.internexio/cos-monitor

Est-ce que io.github.internexio/cos-monitor est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.internexio/cos-monitor » 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 13 outils

• analyze_content≈ 264 tokens

  Analyze content using all 4 COS frameworks in parallel. Returns comprehensive analysis with: - Overall scores (0-10) for each framework - Dimension breakdowns with weights - Specific recommendations for improvement - Cross-framework insights

  Paramètres, retour & exemple (3)

  Paramètres

  • content · string · requis
    The text content to analyze (min 50 characters)
  • platform · string · optionnel · twitter | linkedin | email | youtube | tiktok | instagram | facebook | medium
    Target platform for optimization (affects scoring weights)
  • target_audience · ? · optionnel
    Description of intended audience (improves relevance scoring)

  Exemple d'appel

  {"name": "analyze_content", "arguments": {"content": "texte"}}

  Exemple de retour

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

• analyze_framework≈ 437 tokens

  Analyze content using a single specific framework. Faster than full analysis when you only need one perspective. Frameworks: - hape: Engagement Analysis (novelty, relevance, emotional valence) - big_five: Personality Analysis using OCEAN model (openness, conscientiousness, extraversion, agreeableness, neuroticism) - strategic_clarity: Business message clarity (value prop, differentiation, CTA) - framing_strategy: Cognitive frames and power positioning

  Paramètres, retour & exemple (5)

  Paramètres

  • content · string · requis
    The text content to analyze (min 50 characters)
  • platform · string · optionnel · twitter | linkedin | email | youtube | tiktok | instagram | facebook | medium
    Target platform for optimization
  • framework · string · requis · hape | big_five | strategic_clarity | framing_strategy
    Which analysis framework to use
  • temperature · ? · optionnel
    Optional LLM sampling temperature. Pass 0.0 for deterministic scoring (validation harnesses, classification-agreement gates). Leave unset (None) for the backend default. Forwarded to the analyze endpoint, which has accepted this parameter since cos-bbf.
  • target_audience · ? · optionnel
    Description of intended audience

  Exemple d'appel

  {"name": "analyze_framework", "arguments": {"content": "texte", "framework": "hape"}}

  Exemple de retour

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

• analyze_full_comms≈ 324 tokens

  Run all 7 COS frameworks in parallel for comprehensive analysis. This is the most thorough analysis option, running: - Core 4: HAPE, Big Five, Strategic Clarity, Sovereign Mind - Extended 3: Persuasion (domain-specific), Platform, Quality Use this when you need complete analysis across all dimensions. Takes longer but provides the most comprehensive view.

  Paramètres, retour & exemple (4)

  Paramètres

  • domain · string · optionnel · business | politics | health | masculinity | comedy
    Domain for persuasion analysis
  • content · string · requis
    The text content to analyze (min 50 characters)
  • platform · string · optionnel · twitter | linkedin | email | youtube | tiktok | instagram | facebook | medium
    Target platform for optimization
  • target_audience · ? · optionnel
    Description of intended audience

  Exemple d'appel

  {"name": "analyze_full_comms", "arguments": {"content": "texte"}}

  Exemple de retour

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

• analyze_persuasion≈ 440 tokens

  Analyze content using domain-specific persuasion frameworks. Each domain has specialized scoring dimensions: - business: B2B/B2C messaging, ROI framing, objection handling - politics: Political messaging, polarization awareness, coalition building - health: Medical accuracy, safety messaging, behavior change (CRITICAL domain) - masculinity: Identity messaging, status signaling, tribe alignment - comedy: Humor mechanics, timing, callback patterns

  Paramètres, retour & exemple (5)

  Paramètres

  • domain · string · optionnel · business | politics | health | masculinity | comedy
    The domain context for persuasion analysis
  • content · string · requis
    The text content to analyze (min 50 characters)
  • platform · string · optionnel · twitter | linkedin | email | youtube | tiktok | instagram | facebook | medium
    Target platform for optimization
  • temperature · ? · optionnel
    Optional LLM sampling temperature. Pass 0.0 for deterministic scoring (validation harnesses, classification-agreement gates). Leave unset (None) for the backend default. Forwarded to the persuasion endpoint, which has accepted this parameter since cos-bbf.
  • target_audience · ? · optionnel
    Description of intended audience

  Exemple d'appel

  {"name": "analyze_persuasion", "arguments": {"content": "texte"}}

  Exemple de retour

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

• analyze_platform≈ 295 tokens

  Analyze content for platform-specific optimization. Evaluates content against platform constraints and algorithm preferences: - Character limits and formatting rules - Algorithm optimization signals - Engagement pattern recommendations - Platform-specific best practices Supported platforms: twitter, linkedin, email, youtube, tiktok, instagram, facebook, medium, substack, podcast, newsletter, slack, discord

  Paramètres, retour & exemple (3)

  Paramètres

  • content · string · requis
    The text content to analyze (min 50 characters)
  • platform · string · optionnel · twitter | linkedin | email | youtube | tiktok | instagram | facebook | medium
    The target platform for optimization
  • target_audience · ? · optionnel
    Description of intended audience

  Exemple d'appel

  {"name": "analyze_platform", "arguments": {"content": "texte"}}

  Exemple de retour

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

• analyze_quality≈ 268 tokens

  Analyze content quality across 5 dimensions. Quality dimensions evaluated: - Clarity: Is the message easy to understand? - Coherence: Does the content flow logically? - Correctness: Grammar, spelling, factual accuracy - Completeness: Are all necessary elements present? - Conciseness: Is the content appropriately tight?

  Paramètres, retour & exemple (3)

  Paramètres

  • content · string · requis
    The text content to analyze (min 50 characters)
  • platform · string · optionnel · twitter | linkedin | email | youtube | tiktok | instagram | facebook | medium
    Target platform context
  • target_audience · ? · optionnel
    Description of intended audience

  Exemple d'appel

  {"name": "analyze_quality", "arguments": {"content": "texte"}}

  Exemple de retour

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

• audience_profile≈ 409 tokens

  Infer OCEAN personality profile from an audience description. Maps a free-text target audience description into a structured psychological profile suitable for personalized outreach (cold email, ads, sales messaging). Returns: - OCEAN scores (openness, conscientiousness, extraversion, agreeableness, neuroticism) - ocean_confidence (0.0-1.0) — low when signals are weak - elm_route ("central" | "peripheral" | "mixed") — how the audience processes persuasion - dominant_traits + trait_rationale - dominant_moral_foundations (Moral Foundations Theory) - vulnerability_flags — audiences requiring careful ethics review - recommended_persuasion_principle (Cialdini) + persuasion_rationale Common use: feed a CRM Person/Account description (title, industry, recent signals) to get a psychology-grounded targeting profile for that prospect.

  Paramètres, retour & exemple (3)

  Paramètres

  • domain · string · optionnel
    Campaign domain context (e.g. "B2B", "ecommerce", "health", "financial").
  • campaign_objective · string · optionnel
    Campaign goal (e.g. "awareness", "conversion", "retention", "cold_outreach").
  • audience_description · string · requis
    Free-text description of the target audience (10-2000 chars). Include role, industry, behaviors, pain points, recent signals.

  Exemple d'appel

  {"name": "audience_profile", "arguments": {"audience_description": "texte"}}

  Exemple de retour

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

• chat≈ 167 tokens

  Have a conversation with the COS analysis agent. The agent can help you: - Analyze content interactively - Get recommendations for improvement - Understand framework scores - Configure analysis settings

  Paramètres, retour & exemple (2)

  Paramètres

  • message · string · requis
    Your message to the COS agent
  • conversation_id · ? · optionnel
    Optional ID to continue an existing conversation

  Exemple d'appel

  {"name": "chat", "arguments": {"message": "texte"}}

  Exemple de retour

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

• execute_template≈ 248 tokens

  Execute a specific template with provided variables. Templates guide the analysis with pre-defined prompts and variable placeholders. First use get_templates to find available templates and their required variables.

  Paramètres, retour & exemple (3)

  Paramètres

  • platform · string · optionnel · twitter | linkedin | email | youtube | tiktok | instagram | facebook | medium
    Target platform for optimization
  • variables · object · requis
    Dictionary of variable values required by the template
  • template_id · string · requis
    The template ID to execute (from get_templates)

  Exemple d'appel

  {"name": "execute_template", "arguments": {"variables": {}, "template_id": "texte"}}

  Exemple de retour

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

• get_template_details≈ 138 tokens

  Get detailed information about a specific template. Returns the template's: - Name and description - Required and optional variables with types - Categories and tags - Scoring dimensions and weights

  Paramètres, retour & exemple (1)

  Paramètres

  • template_id · string · requis
    The template ID to get details for

  Exemple d'appel

  {"name": "get_template_details", "arguments": {"template_id": "texte"}}

  Exemple de retour

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

• get_templates≈ 185 tokens

  List available analysis templates. Templates are pre-configured analysis scenarios for common use cases: - Email outreach optimization - LinkedIn post analysis - Sales pitch review - Content marketing assessment

  Paramètres, retour & exemple (2)

  Paramètres

  • search · ? · optionnel
    Search templates by name or description
  • category · ? · optionnel
    Filter by template category (e.g., "email", "social", "sales")

  Exemple d'appel

  {"name": "get_templates", "arguments": {"search": "texte", "category": "texte"}}

  Exemple de retour

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

• optimize_email_for_prospect≈ 824 tokens

  Generate or refine a personalized cold email for a CRM prospect. Composite tool: combines audience profiling (OCEAN + Cialdini), optional agent profiling from writing samples, draft generation (if no draft is supplied), and persuasion + platform scoring in a single call. Designed for CRM integrations like Clarify, HubSpot, Salesforce — pass a Person/Account context, get back a draft + scoring. Returns: - audience_profile: OCEAN scores, ELM route, Cialdini principle - agent_profile: prospect's writing style (if samples provided) - draft: generated or echoed email body - draft_was_generated: bool — whether COS generated the draft - persuasion + platform: full scoring breakdowns - rewrites: prioritized rewrite suggestions - one_thing: the single most important next step - cialdini_principle: recommended influence principle

  Paramètres, retour & exemple (12)

  Paramètres

  • name · ? · optionnel
  • draft · ? · optionnel
    Existing draft to score + refine. If None, a draft is generated.
  • title · ? · optionnel
  • domain · string · optionnel
    Persuasion domain (default "business").
  • intent · string · optionnel · cold_outreach | follow_up | reactivation | warm_intro | demo_request | discovery_call | proposal_recap
    Email intent ("cold_outreach", "follow_up", "reactivation", "warm_intro", "demo_request", "discovery_call", "proposal_recap").
  • company · ? · optionnel
  • industry · ? · optionnel
  • recent_signals · ? · optionnel
    List of recent activity/triggers from the CRM (e.g. ["downloaded ROI calculator", "viewed pricing 3x"]).
  • sender_context · ? · optionnel
    Who the sender is and what they're pitching.
  • include_scoring · ? · optionnel
    Run persuasion + platform scoring on the draft. Default (None): scoring runs ONLY when a draft was supplied (refine path). On the generate path scoring is skipped by default (cuts latency from ~45s to ~10s). Set True to force scoring on a generated draft, or False to suppress scoring even when refining.
  • writing_samples · ? · optionnel
    0-5 prospect writing samples (emails, posts). Each ≥50 chars. Profiled if provided.
  • audience_description · string · requis
    REQUIRED. Free-text describing the prospect (role, industry, behaviors, pain points, recent signals). 10-2000 chars. This seeds the audience profile.

  Exemple d'appel

  {"name": "optimize_email_for_prospect", "arguments": {"audience_description": "texte"}}

  Exemple de retour

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

• profile_agent≈ 226 tokens

  Profile an agent's personality from their writing samples. Analyzes 1-10 writing samples (3-5 recommended) to infer the author's Big Five (OCEAN) personality traits, communication style, strengths, blind spots, and persuasion profile. This is the inverse of content analysis — instead of "is this content effective?", it answers "who is this writer based on how they communicate?"

  Paramètres, retour & exemple (2)

  Paramètres

  • samples · array · requis
    List of writing samples from the agent (min 50 chars each, 3-5 recommended)
  • agent_name · string · optionnel
    Name of the agent being profiled

  Exemple d'appel

  {"name": "profile_agent", "arguments": {"samples": []}}

  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://mcp.semalytics.io/mcp