COS Monitor
Scores website pages for communication quality, tracks regressions, surfaces a fix queue.
¿Debería usar esto?
Calidad y seguridad
Hallazgos (3)
- HIGHTool poisoning patterns detected
- MEDIUMTool 'execute_template' description contains placeholder texten execute_template
- INFOTool description contains placeholder or incomplete texten execute_template
Basado en el análisis automatizado de las definiciones de herramientas y el cumplimiento del protocolo.
Costo de contexto
Este es el número aproximado de tokens que se consumen cada vez que las herramientas del servidor se cargan en el contexto de un modelo. Los recuentos más altos reducen la atención disponible para otras tareas.
Instalar
Instalación con un clic
Agrega esto a tu archivo `claude_desktop_config.json`:
{
"mcpServers": {
"cos-monitor": {
"url": "https://mcp.semalytics.io/mcp"
}
}
}Puntos de conexión remotos
https://mcp.semalytics.io/mcpstreamable-httpQué puede hacer
Inventario de herramientas
Herramientas (13)
🟢analyze_content(content, platform, target_audience)
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
Esquema de entrada
{
"type": "object",
"properties": {
"content": {
"type": "string",
"description": "The text content to analyze (min 50 characters)"
},
"platform": {
"default": "general",
"enum": [
"twitter",
"linkedin",
"email",
"youtube",
"tiktok",
"instagram",
"facebook",
"medium",
"substack",
"podcast",
"newsletter",
"slack",
"discord",
"general"
],
"type": "string",
"description": "Target platform for optimization (affects scoring weights)"
},
"target_audience": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Description of intended audience (improves relevance scoring)"
}
},
"required": [
"content"
],
"additionalProperties": false
}Esquema de salida
{
"type": "object",
"additionalProperties": true
}🟢analyze_framework(content, framework, platform, target_audience, temperature)
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
Esquema de entrada
{
"type": "object",
"properties": {
"content": {
"type": "string",
"description": "The text content to analyze (min 50 characters)"
},
"framework": {
"enum": [
"hape",
"big_five",
"strategic_clarity",
"framing_strategy"
],
"type": "string",
"description": "Which analysis framework to use"
},
"platform": {
"default": "general",
"enum": [
"twitter",
"linkedin",
"email",
"youtube",
"tiktok",
"instagram",
"facebook",
"medium",
"substack",
"podcast",
"newsletter",
"slack",
"discord",
"general"
],
"type": "string",
"description": "Target platform for optimization"
},
"target_audience": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Description of intended audience"
},
"temperature": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional LLM sampling temperature. Pass 0.0 for deterministic\nscoring (validation harnesses, classification-agreement gates). Leave\nunset (None) for the backend default. Forwarded to the analyze\nendpoint, which has accepted this parameter since cos-bbf."
}
},
"required": [
"content",
"framework"
],
"additionalProperties": false
}Esquema de salida
{
"type": "object",
"additionalProperties": true
}🟡get_templates(category, search)
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
Esquema de entrada
{
"type": "object",
"properties": {
"category": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Filter by template category (e.g., \"email\", \"social\", \"sales\")"
},
"search": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Search templates by name or description"
}
},
"additionalProperties": false
}Esquema de salida
{
"type": "object",
"additionalProperties": true
}🟢execute_template(template_id, variables, platform)
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.
Esquema de entrada
{
"type": "object",
"properties": {
"template_id": {
"type": "string",
"description": "The template ID to execute (from get_templates)"
},
"variables": {
"additionalProperties": true,
"type": "object",
"description": "Dictionary of variable values required by the template"
},
"platform": {
"default": "general",
"enum": [
"twitter",
"linkedin",
"email",
"youtube",
"tiktok",
"instagram",
"facebook",
"medium",
"substack",
"podcast",
"newsletter",
"slack",
"discord",
"general"
],
"type": "string",
"description": "Target platform for optimization"
}
},
"required": [
"template_id",
"variables"
],
"additionalProperties": false
}Esquema de salida
{
"type": "object",
"additionalProperties": true
}🟢chat(message, conversation_id)
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
Esquema de entrada
{
"type": "object",
"properties": {
"message": {
"type": "string",
"description": "Your message to the COS agent"
},
"conversation_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional ID to continue an existing conversation"
}
},
"required": [
"message"
],
"additionalProperties": false
}Esquema de salida
{
"type": "object",
"additionalProperties": true
}🟢get_template_details(template_id)
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
Esquema de entrada
{
"type": "object",
"properties": {
"template_id": {
"type": "string",
"description": "The template ID to get details for"
}
},
"required": [
"template_id"
],
"additionalProperties": false
}Esquema de salida
{
"type": "object",
"additionalProperties": true
}🟡analyze_persuasion(content, domain, platform, target_audience, temperature)
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
Esquema de entrada
{
"type": "object",
"properties": {
"content": {
"type": "string",
"description": "The text content to analyze (min 50 characters)"
},
"domain": {
"default": "business",
"enum": [
"business",
"politics",
"health",
"masculinity",
"comedy"
],
"type": "string",
"description": "The domain context for persuasion analysis"
},
"platform": {
"default": "general",
"enum": [
"twitter",
"linkedin",
"email",
"youtube",
"tiktok",
"instagram",
"facebook",
"medium",
"substack",
"podcast",
"newsletter",
"slack",
"discord",
"general"
],
"type": "string",
"description": "Target platform for optimization"
},
"target_audience": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Description of intended audience"
},
"temperature": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional LLM sampling temperature. Pass 0.0 for deterministic\nscoring (validation harnesses, classification-agreement gates). Leave\nunset (None) for the backend default. Forwarded to the persuasion\nendpoint, which has accepted this parameter since cos-bbf."
}
},
"required": [
"content"
],
"additionalProperties": false
}Esquema de salida
{
"type": "object",
"additionalProperties": true
}🟢analyze_platform(content, platform, target_audience)
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
Esquema de entrada
{
"type": "object",
"properties": {
"content": {
"type": "string",
"description": "The text content to analyze (min 50 characters)"
},
"platform": {
"default": "linkedin",
"enum": [
"twitter",
"linkedin",
"email",
"youtube",
"tiktok",
"instagram",
"facebook",
"medium",
"substack",
"podcast",
"newsletter",
"slack",
"discord",
"general"
],
"type": "string",
"description": "The target platform for optimization"
},
"target_audience": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Description of intended audience"
}
},
"required": [
"content"
],
"additionalProperties": false
}Esquema de salida
{
"type": "object",
"additionalProperties": true
}🟢analyze_quality(content, platform, target_audience)
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?
Esquema de entrada
{
"type": "object",
"properties": {
"content": {
"type": "string",
"description": "The text content to analyze (min 50 characters)"
},
"platform": {
"default": "general",
"enum": [
"twitter",
"linkedin",
"email",
"youtube",
"tiktok",
"instagram",
"facebook",
"medium",
"substack",
"podcast",
"newsletter",
"slack",
"discord",
"general"
],
"type": "string",
"description": "Target platform context"
},
"target_audience": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Description of intended audience"
}
},
"required": [
"content"
],
"additionalProperties": false
}Esquema de salida
{
"type": "object",
"additionalProperties": true
}🟢analyze_full_comms(content, domain, platform, target_audience)
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.
Esquema de entrada
{
"type": "object",
"properties": {
"content": {
"type": "string",
"description": "The text content to analyze (min 50 characters)"
},
"domain": {
"default": "business",
"enum": [
"business",
"politics",
"health",
"masculinity",
"comedy"
],
"type": "string",
"description": "Domain for persuasion analysis"
},
"platform": {
"default": "linkedin",
"enum": [
"twitter",
"linkedin",
"email",
"youtube",
"tiktok",
"instagram",
"facebook",
"medium",
"substack",
"podcast",
"newsletter",
"slack",
"discord",
"general"
],
"type": "string",
"description": "Target platform for optimization"
},
"target_audience": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Description of intended audience"
}
},
"required": [
"content"
],
"additionalProperties": false
}Esquema de salida
{
"type": "object",
"additionalProperties": true
}⚪profile_agent(samples, agent_name)
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?"
Esquema de entrada
{
"type": "object",
"properties": {
"samples": {
"items": {
"type": "string"
},
"type": "array",
"description": "List of writing samples from the agent (min 50 chars each, 3-5 recommended)"
},
"agent_name": {
"default": "Unknown Agent",
"type": "string",
"description": "Name of the agent being profiled"
}
},
"required": [
"samples"
],
"additionalProperties": false
}Esquema de salida
{
"type": "object",
"additionalProperties": true
}🟢audience_profile(audience_description, domain, campaign_objective)
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.
Esquema de entrada
{
"type": "object",
"properties": {
"audience_description": {
"type": "string",
"description": "Free-text description of the target audience (10-2000 chars).\nInclude role, industry, behaviors, pain points, recent signals."
},
"domain": {
"default": "business",
"type": "string",
"description": "Campaign domain context (e.g. \"B2B\", \"ecommerce\", \"health\", \"financial\")."
},
"campaign_objective": {
"default": "conversion",
"type": "string",
"description": "Campaign goal (e.g. \"awareness\", \"conversion\", \"retention\",\n\"cold_outreach\")."
}
},
"required": [
"audience_description"
],
"additionalProperties": false
}Esquema de salida
{
"type": "object",
"additionalProperties": true
}🟢optimize_email_for_prospect(audience_description, intent, name, title, company, ...)
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
Esquema de entrada
{
"type": "object",
"properties": {
"audience_description": {
"type": "string",
"description": "REQUIRED. Free-text describing the prospect\n(role, industry, behaviors, pain points, recent signals).\n10-2000 chars. This seeds the audience profile."
},
"intent": {
"default": "cold_outreach",
"enum": [
"cold_outreach",
"follow_up",
"reactivation",
"warm_intro",
"demo_request",
"discovery_call",
"proposal_recap"
],
"type": "string",
"description": "Email intent (\"cold_outreach\", \"follow_up\", \"reactivation\",\n\"warm_intro\", \"demo_request\", \"discovery_call\", \"proposal_recap\")."
},
"name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null
},
"title": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null
},
"company": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null
},
"industry": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null
},
"recent_signals": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "List of recent activity/triggers from the CRM\n(e.g. [\"downloaded ROI calculator\", \"viewed pricing 3x\"])."
},
"writing_samples": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "0-5 prospect writing samples (emails, posts).\nEach ≥50 chars. Profiled if provided."
},
"sender_context": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Who the sender is and what they're pitching."
},
"draft": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Existing draft to score + refine. If None, a draft is generated."
},
"include_scoring": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"default": null,
"description": "Run persuasion + platform scoring on the draft.\nDefault (None): scoring runs ONLY when a draft was supplied (refine path).\nOn the generate path scoring is skipped by default (cuts latency from\n~45s to ~10s). Set True to force scoring on a generated draft, or\nFalse to suppress scoring even when refining."
},
"domain": {
"default": "business",
"type": "string",
"description": "Persuasion domain (default \"business\")."
}
},
"required": [
"audience_description"
],
"additionalProperties": false
}Esquema de salida
{
"type": "object",
"additionalProperties": true
}Comunidad
Evidencia