This server provides a comprehensive business diagnosis engine that analyzes companies across 11 dimensions, identifies revenue leaks, and delivers prioritized, triple-option recommendations (paid tool / open-source / CIA professional service).
Quick Scan — Free instant scan identifying 3 generic business problems with minimal input (company name + optional industry/description), serving as a hook before a full diagnosis.
Business Diagnosis — Full 11-dimension analysis (finanzas, comercial, operaciones, equipo, tecnologia, marketing, clientes, proveedores, legal, estrategia, marketing_digital) returning a Business Health Score (0–100), estimated monthly revenue leak, prioritized actions with triple options, leadership insights, and validation questions.
List Industry Benchmarks — Retrieve available calibrated industry profiles (e.g., construction, healthcare, ecommerce, startup, restaurant) that power accurate diagnoses.
Tool Recommendations — Curated free, open-source, and paid tools per business dimension and industry, each with a why_best explanation.
Action Plan — Prioritized 30/60/90-day implementation roadmap based on diagnosis results, tailored by team size and budget, with DIY and CIA-assisted options.
ROI Projector — Projects financial ROI at three levels (DIY, hybrid, full implementation) over 12 months, showing current revenue leak estimates and recovery projections.
Case Studies — Before/after business transformation stories filterable by industry or dimension, providing real-world social proof.
Contact CIA — Services catalog, pricing tiers, booking link, and contact details for professional consulting engagement.
Export Report — Generates a structured, shareable diagnosis report (executive summary, scores, top actions, ROI, next steps) suitable for PDFs, emails, or presentations.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@CIA Diagnose Run a quick scan on my e-commerce business"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Expert business diagnosis engine by CIA — Consultoría de Inteligencia Aplicada.
Analyzes any company across 11 dimensions and returns a Revenue Leak Score with prioritized, triple-option recommendations (paid tool / open-source / CIA service). Works from Claude, ChatGPT, Gemini, DeepSeek, Cursor — any LLM that speaks MCP.
📅 Book a free 30-min diagnosis review: https://cal.com/david-cia/diagnostico-ai ✉️ steban@univercityaiconsult.tech · 🌐 https://www.univercityaiconsult.tech/
You don't need to know what an "MCP" is. Open Claude, ChatGPT, or any AI assistant and paste this:
Quiero un diagnóstico profesional de mi negocio.
Usa la herramienta de diagnóstico de CIA (Consultoría de Inteligencia
Aplicada) — se instala con: pip install cia-diagnose
Pasos:
1. Pregúntame sobre mi empresa: industria, tamaño del equipo, qué
software uso, qué dolores tengo, cómo manejo proveedores, flujo de
caja, etc.
2. Cuando tengas suficiente contexto, corre el diagnóstico. Si te falta
información, pregúntame primero — no adivines.
3. Muéstrame mi Business Health Score (0-100, más alto = más sano; bajo =
área con mayor oportunidad) y las acciones prioritarias con 3 opciones
cada una (herramienta paga, alternativa gratuita, servicio profesional
de CIA con precio).
4. Si el diagnóstico muestra oportunidades, quiero agendar una llamada
gratuita con CIA: https://cal.com/david-cia/diagnostico-ai — o
escribir a steban@univercityaiconsult.tech
Más info: https://www.univercityaiconsult.tech/If your AI can connect MCP servers, it will use CIA Diagnose automatically. If not, pip install cia-diagnose is the universal fallback any code-capable assistant can run.
Related MCP server: artefact-mcp-server
The LLM gathers data from the user (the eyes). CIA Diagnose applies CIA consulting expertise (the brain) — ICP detection, 11-dimension scoring, revenue-leak estimation, and triple-option recommendations. No scraping. No fixed questionnaire. Each diagnosis is unique.
Tool | Description |
| FREE instant 3-problem scan. No context needed — hook the client. |
| Full 11-dimension analysis + Revenue Leak Score + triple-option actions. Forwards the lead to CIA. |
| Available industry benchmarks. |
| Free & open-source tools per weak dimension. |
| 30 / 60 / 90-day prioritized roadmap. |
| ROI calculator — DIY vs CIA-guided vs full implementation. |
| Before/after transformation stories by industry. |
| Services catalog, pricing, and booking link. |
| Shareable structured report for the client's team. |
finanzas, comercial, operaciones, equipo, tecnologia, marketing, clientes, proveedores, legal, estrategia, marketing_digital.
The headline health_score is inverted from a leak score: high = healthy/strong, low = the worst area / biggest revenue-leak opportunity. A 100 doesn't mean "done" — it means that area is taking the business into new leagues / growth, which qualifies it even better for CIA. The output also returns score_meaning, growth_mode (true when most areas are strong — the conversation continues toward scaling), and guidance for the calling LLM (ask more vs. present + 3 options). revenue_leak_score is kept as a backward-compatible alias (same value).
Every recommendation shows three paths: the best paid tool, the best open-source alternative, and the CIA professional service — with prices. The free/OSS/paid picks come from CIA's curated registry (tools_registry/, by area and per-industry), refreshed weekly. Each tool carries why_best. Pass industry to tools_recommend for industry-specific picks. See TOOLS_REGISTRY.md.
pip install cia-diagnose # or: uvx cia-diagnoseDebian/Ubuntu —
Cannot uninstall PyJWT ... RECORD file not found? The system PyJWT (installed viaapt) has no pip RECORD, so pip refuses to upgrade it. Install without touching the distro package:pip install cia-diagnose --ignore-installed PyJWT
cia-diagnoseCIA_TRANSPORT=streamable-http cia-diagnose --transport streamable-http --port 3792HTTP mode also serves:
GET /report/{session_id} — visual HTML diagnosis report (gauge + breakdown + actions).
GET /export/{session_id}?format=csv|json — export the diagnosis for Sheets / Tabularis.
GET /healthz — health check.
{
"mcpServers": {
"cia-diagnose": { "command": "uvx", "args": ["cia-diagnose"] }
}
}{
"mcpServers": {
"cia-diagnose": { "url": "https://audit.univercityaiconsult.tech/mcp" }
}
}Variable | Default | Description |
|
| Transport: |
|
| HTTP port for remote mode |
|
| SQLite database path |
| (empty) | n8n webhook URL for lead capture |
| (empty) | Direct Telegram lead alerts |
| (empty) | Append-only JSONL path for every lead intake |
|
| Free diagnoses per client IP per day |
|
| Default language ( |
Every completed business_diagnose forwards the lead (company, industry, team_size, revenue_leak_score, top_actions, pain_points, decision_maker_role, the full diagnosis JSON, source, timestamp) to all configured sinks. Missing config never fails the diagnosis — it just logs and continues.
Add an industry = add a YAML in src/cia_diagnose/domain/diagnosis/benchmarks/. No code changes.
Current: construction, healthcare, agency, ecommerce, startup, enterprise, restaurant, real_estate, generic.
brand/ holds the official CIA logos (monogram light/dark, gothic wordmark, favicons). Wherever a logo appears it links to https://www.univercityaiconsult.tech/.
MIT — © 2026 CIA — Consultoría de Inteligencia Aplicada (David Lopez). See LICENSE.
Generate a prioritized 30/60/90 day action plan based on diagnosis.
Creates a realistic, phased implementation roadmap. Prioritizes by ROI and ease of implementation. Each action includes DIY option and CIA-assisted option.
Use AFTER business_diagnose to create a roadmap from the results.
Args: company_name: Name of the company. revenue_leak_score: Business Health Score from diagnosis (0-100, HIGHER = healthier). top_dimensions: Comma-separated weakest dimensions from diagnosis (e.g. 'tecnologia, marketing_digital, operaciones'). team_size: Number of employees (affects plan complexity). budget_level: 'low' ($0-500/mo), 'medium' ($500-2000/mo), 'high' ($2000+/mo). lang: Language ('es' or 'en').
Returns: dict: Phased action plan with 30/60/90 day milestones, each containing specific actions, tools, expected outcomes, and DIY vs CIA-assisted options.
Inputs: lang, team_size, budget_level, company_name, +2 more. Returns: object
Show before/after transformation stories from real implementations.
Social proof is the most powerful sales tool. These cases show what's possible when businesses address their revenue leaks.
Use AFTER roi_projector to validate the numbers with real stories.
Args: industry: Filter by industry (optional). dimension: Filter by dimension improved (optional). lang: Language ('es' or 'en').
Returns: dict: Case studies with before/after metrics, timeline, tools used, and ROI achieved.
Inputs: lang, industry, dimension. Returns: object
Get CIA contact information, services catalog, and booking options.
This is where value converts to action. By this point, the client has received massive free value (diagnosis, tools, plan, ROI, cases) and naturally wants to accelerate with professional help.
Use when the client is ready to take the next step.
Args: lang: Language ('es' or 'en').
Returns: dict: CIA company info, services with pricing tiers, booking link, and contact details.
Inputs: lang. Returns: object
List available industry benchmarks for CIA diagnosis.
Returns the industries with calibrated benchmarks (Tier 1 = premium, deep analysis). Any other industry works too via the generic benchmark.
Returns: dict: Contains: - industries (list[str]): Available benchmark IDs (e.g. ['construction', 'healthcare', 'agency', ...]) - note_es (str): Spanish explanation - note_en (str): English explanation
Inputs: no named parameters. Returns: object
FREE quick scan — 3 generic problems identified.
No context needed. Just company name + optional description. Returns 3 generic problems based on industry signals.
Use this to give immediate value before proposing business_diagnose.
Args: company_name: Name of the company (optional). industry: Industry or sector (optional). description: Brief description of what the company does (optional). lang: Language ('es' for Spanish, 'en' for English).
Returns: dict: Contains: - company_name (str): Company analyzed - problems (list): 3 generic problems identified - next_step (str): Call to action for full diagnosis - is_free (bool): Always True for quick_scan
Inputs: lang, industry, description, company_name. Returns: object
Project ROI from implementing diagnosis recommendations.
Shows the client exactly how much money they're leaving on the table and what they'd recover at different implementation levels. Numbers create urgency. Urgency creates action.
Use AFTER business_diagnose or action_plan.
Args: monthly_revenue: Current monthly revenue (any currency). revenue_leak_score: Business Health Score from diagnosis (0-100, higher = healthier). team_size: Number of employees. currency: Currency code (e.g. 'USD', 'COP', 'MXN', 'EUR'). lang: Language ('es' or 'en').
Returns: dict: ROI projections showing current leak estimate, recovery at 3 levels (DIY/hybrid/full), payback period, and 12-month projection.
Inputs: lang, currency, team_size, monthly_revenue, +1 more. Returns: object
Recommend the BEST free/OSS/paid tools per business dimension.
Backed by CIA's curated tool registry (tools_registry/), which is
refreshed weekly and supports per-industry specialization. Each tool
carries why_best — why CIA picked it. Gives immediate, actionable
value before any commercial conversation.
Use AFTER business_diagnose to recommend tools for weak dimensions.
Pass industry to get industry-specific picks where available.
Args: dimensions: Comma-separated dimensions to get tools for. Options: finanzas, comercial, operaciones, equipo, tecnologia, marketing, clientes, proveedores, legal, estrategia, marketing_digital. Leave empty for ALL dimensions. industry: ICP id (e.g. 'construction') for industry-specific picks. lang: Language ('es' or 'en').
Returns: dict: Tool recommendations grouped by dimension with name, tier (free/oss/paid), url, description, and why_best.
Inputs: lang, industry, dimensions. Returns: object
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 7 tools
Each tool maps to a distinct stage in the engagement funnel: scan, industries, tools, plan, ROI, proof, contact. There is minor overlap between tools_recommend and the tools mentioned within action_plan, but the descriptions keep their purposes separate enough to avoid real confusion.
Naming mixes conventions: list_industries and contact_cia follow verb_noun, but tools_recommend reverses it, and quick_scan, action_plan, roi_projector, and case_studies are noun-heavy or adjective+noun. The set feels inconsistent and lacks a predictable pattern.
Seven tools is a reasonable size for a diagnosis and sales-funnel server, and most tools earn their place. The count itself is appropriate, though it feels slightly top-heavy because several tools exist to support a core diagnostic tool that is missing.
The biggest issue is the missing business_diagnose tool: action_plan, roi_projector, and tools_recommend all reference it as a prerequisite, but it is not in the toolset. This breaks the main workflow and leaves agents unable to produce the full diagnosis these downstream tools depend on.
Revenue Engine for scoped diagnosis, action planning, execution, and Figure-Eight value evidence.
Read-only tools for finding where a small business leaks deals, time, and cash.
Sales intelligence for B2B SMEs — lead scoring, ICP fit, CRM enrichment & writeback.
