COS Monitor

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Scores website pages for communication quality, tracks regressions, surfaces a fix queue.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "COS Monitor": {
      "url": "https://mcp.semalytics.io/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (13)

• analyze_content

  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

  Parameters:

  • content (required) — string — The text content to analyze (min 50 characters)
  • platform — string — Target platform for optimization (affects scoring weights)
  • target_audience — Description of intended audience (improves relevance scoring)

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• analyze_framework

  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

  Parameters:

  • content (required) — string — The text content to analyze (min 50 characters)
  • framework (required) — string — Which analysis framework to use
  • platform — string — Target platform for optimization
  • temperature — 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 — Description of intended audience

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_templates

  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

  Parameters:

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

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• execute_template

  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.

  Parameters:

  • template_id (required) — string — The template ID to execute (from get_templates)
  • variables (required) — object — Dictionary of variable values required by the template
  • platform — string — Target platform for optimization

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• chat

  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

  Parameters:

  • message (required) — string — Your message to the COS agent
  • conversation_id — Optional ID to continue an existing conversation

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_template_details

  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

  Parameters:

  • template_id (required) — string — The template ID to get details for

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• analyze_persuasion

  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

  Parameters:

  • content (required) — string — The text content to analyze (min 50 characters)
  • domain — string — The domain context for persuasion analysis
  • platform — string — Target platform for optimization
  • temperature — 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 — Description of intended audience

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• analyze_platform

  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

  Parameters:

  • content (required) — string — The text content to analyze (min 50 characters)
  • platform — string — The target platform for optimization
  • target_audience — Description of intended audience

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• analyze_quality

  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?

  Parameters:

  • content (required) — string — The text content to analyze (min 50 characters)
  • platform — string — Target platform context
  • target_audience — Description of intended audience

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• analyze_full_comms

  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.

  Parameters:

  • content (required) — string — The text content to analyze (min 50 characters)
  • domain — string — Domain for persuasion analysis
  • platform — string — Target platform for optimization
  • target_audience — Description of intended audience

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• profile_agent

  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?"

  Parameters:

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

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• audience_profile

  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.

  Parameters:

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

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• optimize_email_for_prospect

  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

  Parameters:

  • audience_description (required) — string — REQUIRED. Free-text describing the prospect (role, industry, behaviors, pain points, recent signals). 10-2000 chars. This seeds the audience profile.
  • name
  • draft — Existing draft to score + refine. If None, a draft is generated.
  • title
  • domain — string — Persuasion domain (default "business").
  • intent — string — Email intent ("cold_outreach", "follow_up", "reactivation", "warm_intro", "demo_request", "discovery_call", "proposal_recap").
  • company
  • industry
  • recent_signals — List of recent activity/triggers from the CRM (e.g. ["downloaded ROI calculator", "viewed pricing 3x"]).
  • sender_context — Who the sender is and what they're pitching.
  • include_scoring — 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 — 0-5 prospect writing samples (emails, posts). Each ≥50 chars. Profiled if provided.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.