{"id":"gabrielserrao-pyrestoolbox-mcp","name":"pyrestoolbox-mcp","af_score":60.5,"security_score":37.2,"reliability_score":36.2,"what_it_does":"Provides a local Model Context Protocol (MCP) server (FastMCP-based) that exposes ~108 reservoir engineering / petroleum engineering calculation tools by bridging AI agents (e.g., Claude Desktop) to the pyResToolbox library for tasks like PVT, well performance/IPR, nodal/VLP, DCA, material balance, geomechanics, brine properties, and related workflows.","best_when":"You have a local or controlled environment (e.g., Claude Desktop) and want an MCP-compatible agent to call strongly-scoped reservoir engineering functions without writing Python glue code.","avoid_when":"You need a managed, internet-hosted API with centralized access control, guaranteed rate limiting, or formal SLA/SLA-backed uptime guarantees.","last_evaluated":"2026-03-30T15:26:22.188610+00:00","has_mcp":true,"has_api":false,"auth_methods":["No documented auth for local MCP (based on README)"],"has_free_tier":false,"known_gotchas":["Tool parameter naming/method enum strings must match the provided skill/tools-reference; natural-language paraphrases may fail validation.","Unit handling (field vs metric) matters; incorrect units will lead to incorrect engineering outputs.","Because this is a local MCP server, operational issues may stem from environment setup (Python/uv paths, dependencies) rather than API usage."],"error_quality":0.0}