Skip to main content
Glama

CEMIS — MCP server

Read-only MCP server over the data directory of CEMIS: registered Cuban companies, business opportunities derived from Cuba's 2026 economic reforms, and the transformations/reforms themselves.

Listed in the official MCP registry as io.github.francofuji/cemis-directorio.

Connecting

Public server, no authentication (all data is already public on cemis.io):

https://mcp.cemis.io/mcp

Transport: streamable-http. Compatible with any MCP client (Claude Desktop, ChatGPT with custom connectors, etc.) — add it as a remote HTTP server.

Related MCP server: cnes-mcp-test

Tools

Tool

What it does

buscar_empresas

Filters companies by sector, province, business objective, or whether they are verified

ficha_empresa

Full company profile, with its related opportunities and transformations

oportunidades_por_sector

Business opportunities relevant to a given sector

empresas_por_oportunidad

Companies related to a specific business opportunity

impacto_de_reforma

Given an economic transformation, returns affected sectors/company types, specific companies, and opportunities that open up

listar_sectores

Taxonomy of valid sectors, derived from real data

listar_provincias

The 16 valid Cuban provinces for filtering

Local development

cd mcp_server
python3.11 -m venv venv
./venv/bin/pip install -r requirements.txt
./venv/bin/python -m pytest tests/ -v   # 25 tests, 100% local
MCP_TRANSPORT=stdio ./venv/bin/python server.py

To run in HTTP mode (the same server.py, without forking the code):

MCP_TRANSPORT=streamable-http MCP_PORT=8000 ./venv/bin/python server.py

Docker

docker build -f mcp_server/Dockerfile -t cemis_mcp .
docker run -p 8000:8000 cemis_mcp

Structure

  • cemis_core/: matching keywords and shared functions (company↔opportunity↔transformation), with no dependency on the site.

  • data.py, oportunidades_data.py, estados_transformaciones.py, empresas_data.json: the same data published at cemis.io.

  • mcp_server/: the MCP server itself.

This repo is a subset of the full cemis.io project (which also includes the static site generator) — only what is needed to run the MCP server independently lives here.

License

MIT — see LICENSE. The exposed data is the same already published publicly on cemis.io.

A
license - permissive license
Not graded
quality - not tested
C
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Related MCP Servers

  • F
    license
    Not graded
    quality
    C
    maintenance
    Read-only MCP server that serves the Archivo Epistemico (epistemic graph), enabling AI to read and query the epistemic path autonomously via tools like search, get_via, resolve, and get_necesidad.
  • F
    license
    Not graded
    quality
    C
    maintenance
    Read-only MCP server for querying Brazilian CNES health establishment data in PostgreSQL, enabling AI-assisted database exploration and analysis.
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables querying complete JUCESP company registration data by CNPJ, NIRE, or name, including status and history, via a read-only MCP server.
    MIT

View all related MCP servers

Related MCP Connectors

  • Read-only MCP server for wafergraph.com's semiconductor & AI supply-chain data: 30 tools, no auth.

  • Read-only MCP server for ClassQuill, a tutoring-business-management platform.

  • MCP server for Brazilian Federal Senate open data (legislative, administrative, e-Cidadania).

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/francofuji/cemis-directorio'

If you have feedback or need assistance with the MCP directory API, please join our Discord server