pybme-mcp
pybme-mcp
Un servidor de Model Context Protocol (MCP) que envuelve a pyBME, permitiendo a los agentes LLM realizar análisis geoestadísticos de Entropía Máxima Bayesiana mediante intención en lenguaje natural en lugar de código.
Qué hace
El servidor expone 7 herramientas, 6 recursos y 4 prompts que forman un flujo de trabajo de razonamiento de incertidumbre:
ingest_external_scenario_evidence → inspect_modeling_context
→ fit_uncertainty_model → run_uncertainty_update
→ explain_uncertainty_drivers
→ compare_operator_approaches
→ design_next_observation_or_scenarioHerramientas
Herramienta | Propósito |
| Importar observaciones duras/blandas y topología de red |
| Detectar el tipo de problema y recomendar familias de modelos |
| Ajustar modelos de covarianza espacial o de red con validación cruzada |
| Ejecutar predicción BME en objetivos de estimación |
| Identificar qué impulsa la incertidumbre en ubicaciones específicas |
| Comparar operadores euclidianos vs. de grafo vs. basados en la física |
| Clasificar ubicaciones de sensores candidatos por reducción de varianza |
Familias de modelos soportadas
spatial — Covarianza euclidiana (exponencial, gaussiana, esférica, …)
space_time — Covarianza espacio-temporal separable
graph_laplacian — Kernel de difusión de grafo en topología de red
physics_informed_network — Covarianza de red físicamente consistente
spectral_hodge — Descomposición espectral de Hodge para redes de flujo
Related MCP server: dssat-mcp
Instalación
Instale pyBME primero (aún no disponible en PyPI):
pip install git+https://github.com/wiesnerfriedman/pybme.gitLuego instale el servidor MCP:
pip install git+https://github.com/wiesnerfriedman/pybme-mcp.gitO desde un clon local:
git clone https://github.com/wiesnerfriedman/pybme-mcp.git
cd pybme-mcp
pip install -e ".[dev]"Configuración
Claude Desktop
Añada a claude_desktop_config.json:
{
"mcpServers": {
"pybme": {
"command": "pybme-mcp"
}
}
}VS Code (Copilot)
Añada a .vscode/mcp.json:
{
"servers": {
"pybme": {
"type": "stdio",
"command": "pybme-mcp"
}
}
}Uso
Una vez configurado, pregunte a su agente cosas como:
"Ajusta un modelo de incertidumbre a mis observaciones de PM2.5"
"Ejecuta una actualización BME consciente de la red en esta red de aguas pluviales"
"Compara operadores euclidianos frente a operadores de Laplaciano de grafo"
"¿Dónde debería colocar el siguiente sensor para reducir la incertidumbre al máximo?"
Consulte examples/mcp_agent_demo.ipynb para ver un tutorial paso a paso de toda la cadena de herramientas.
Desarrollo
git clone https://github.com/wiesnerfriedman/pybme-mcp.git
cd pybme-mcp
pip install -e ".[dev]"
pytestEstructura
pybme-mcp/
├── docs/
│ ├── pybme-openswmm-integration.md
│ └── v1-mcp-spec.md
├── examples/
│ └── mcp_agent_demo.ipynb
├── pyproject.toml
├── src/pybme_mcp/
│ ├── __init__.py
│ ├── __main__.py
│ ├── registry.py
│ ├── schemas.py
│ ├── serialisation.py
│ ├── server.py
│ └── services/
│ ├── catalog.py
│ ├── comparison.py
│ ├── context.py
│ ├── explanation.py
│ ├── fitting.py
│ ├── hodge.py
│ ├── ingest.py
│ ├── scenario_design.py
│ └── update.py
└── tests/
├── conftest.py
├── test_ingest.py
└── test_integration.pyLicencia
MIT
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
No tool schema history has been recorded yet.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Verifiable Earth ground truth for AI agents: water, hazard, ground stability, resource, with proof.
Deterministic reasoning stack for AI agents: simulate, decide & compute, plus cross-domain tools.
Agent-to-agent reasoning-as-a-service: chain-of-thought, analysis, and decision support.
Related MCP Servers
- AlicenseNot gradedqualityAmaintenanceEnables natural-language interaction with Ladybug Tools for building performance simulation, 3D modeling, and data visualization, allowing agents to perform complex environmental analysis tasks without CAD software.6GPL 3.0
- AlicenseNot gradedqualityDmaintenanceEnables natural language interaction with the DSSAT crop model for simulation, calibration, and sensitivity analysis through LLM agents.1MIT
- FlicenseAqualityBmaintenanceEnables AI agents to query Earth observation data, satellite imagery, active fires, and weather via natural language, returning interactive maps and briefs.12-
- FlicenseNot gradedqualityCmaintenanceEnables AI assistants to query and visualize ArcGIS Online/Enterprise geospatial data through natural language, performing spatial analysis and map generation.-
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/corinne-wf-home/pybme-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server