# COS Monitor

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

- name: io.github.internexio/cos-monitor
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 91/100
- quality: 83/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.internexio%2Fcos-monitor
- tools: https://api.protogrid.dev/v1/servers/io.github.internexio%2Fcos-monitor/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "cos-monitor": {
      "type": "http",
      "url": "https://mcp.semalytics.io/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 100
- freshness: 85
- provenance: 80
- drivers: +repository +namespace-matches-repo +reachable +uptime-99% ~updated-41d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 83/100 (good)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: analyze_content (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); analyze_framework (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_templates (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 3,600 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 13, about 3,600 tokens to load them all
- tool set hash: 14f37aae3803ac87fd7a9b7cdcbe2516
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.internexio/cos-monitor.svg)](https://protogrid.dev/servers/io.github.internexio/cos-monitor)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://mcp.semalytics.io/mcp (streamable-http, auth none, reachable true, uptime30d 0.99159664)

## Packages

_none_

## 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
- `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
- `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.
- `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
- `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
- `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?
- `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.
- `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
- `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.
- `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
- `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
- `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
- `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?"