UniverCity MCP v0.2.1
Expert business diagnosis engine by CIA — Consultoría de Inteligencia Aplicada.
Analyzes any company across 8 dimensions and returns a Revenue Leak Score with prioritized, triple-option recommendations. Works from Claude, GPT, Gemini, DeepSeek, Cursor — any LLM that speaks MCP.
Architecture
"LLM has EYES, MCP has BRAIN."
The LLM gathers data from the user (the eyes). UniverCity MCP applies CIA consulting expertise (the brain) — ICP detection, dimension scoring, revenue leak estimation, and triple-option recommendations. No scraping. No fixed questionnaire. Each diagnosis is unique.
Tools
| Tool | Description |
|---|---|
univercity_diagnose |
Full 8-dimension diagnosis. Send company context, get Revenue Leak Score + actions. |
univercity_list_industries |
Returns available industry benchmarks (construction, healthcare, agency, ecommerce, startup, enterprise, generic). |
8 Dimensions
digital, operations, supply_chain, talent, financial, leadership, market, regulatory
Triple Option
Every recommendation shows three paths: the best paid tool, the best open source alternative, and the CIA professional service — with prices. Radical transparency.
Quick Start
Install
pip install univercity-mcp
Run (stdio — local)
univercity-mcp
Run (HTTP — remote)
UNIVERCITY_TRANSPORT=streamable-http univercity-mcp --transport streamable-http --port 3792
Claude Desktop config
{
"mcpServers": {
"univercity": {
"command": "uvx",
"args": ["univercity-mcp"]
}
}
}
Remote (Streamable HTTP)
{
"mcpServers": {
"univercity": {
"url": "https://audit.univercityaiconsult.tech/mcp"
}
}
}
Environment Variables
| Variable | Default | Description |
|---|---|---|
UNIVERCITY_TRANSPORT |
stdio |
Transport: stdio, sse, streamable-http |
UNIVERCITY_HTTP_PORT |
3792 |
HTTP port for remote mode |
UNIVERCITY_DB_PATH |
~/.univercity-mcp/sessions.db |
SQLite database path |
UNIVERCITY_N8N_WEBHOOK |
(empty) | n8n webhook for lead capture |
UNIVERCITY_RATE_FREE |
5 |
Free diagnoses per IP per day |
UNIVERCITY_LANG |
es |
Default language (es/en) |
Industry Benchmarks (YAML-driven)
Add an industry = add a YAML file in src/univercity_mcp/domain/diagnosis/benchmarks/. No code changes needed.
Current benchmarks: construction, healthcare, agency, ecommerce, startup, enterprise, generic.
Value Ladder
Free diagnosis → Paid diagnostic ($1K-$5K) → Core implementation ($4K-$25K) → Retainer ($500-$3K/mo) → Bespoke ($30K+)
100% Credit Bridge: audit cost credited if client proceeds within 30 days.
License
Proprietary — CIA (Consultoría de Inteligencia Aplicada). All rights reserved.
Release files for univercity-mcp 1.0.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| univercity_mcp-1.0.0.tar.gz | 231.8 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| univercity_mcp-1.0.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 300.6 kB
Release files / univercity_mcp-1.0.0.tar.gz
| Download URL | univercity_mcp-1.0.0.tar.gz |
|---|---|
| Size | 231.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
943924b64b2950ba2253c25478071f51930872953416ab72488c41cce3afeb2c
|
|
BLAKE2b-256 checksum How to use checksums |
b484674fa3569ef7374106c8802b18f61226fe07cc848c178f4aeca6f008086d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on May 10, 2026.
Transparency logRelease files / univercity_mcp-1.0.0-py3-none-any.whl
| Download URL | univercity_mcp-1.0.0-py3-none-any.whl |
|---|---|
| Size | 68.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
557fa95777509cc76c5a5cae7a24a6edd71bf57f8abbe48659679334285cb315
|
|
BLAKE2b-256 checksum How to use checksums |
afafc0cc19c714179b7952f21e29598a77fae11278f6ca66c38d1a9c747943f5
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on May 10, 2026.
Transparency log