pyrestoolbox-mcp

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.

Evaluated Mar 30, 2026 (21d ago)
Repo ↗ Ai Ml mcp fastmcp python reservoir-engineering pvt well-performance petroleum ai-tooling tool-calling
⚙ Agent Friendliness
60
/ 100
Can an agent use this?
🔒 Security
37
/ 100
Is it safe for agents?
⚡ Reliability
36
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
78
Documentation
70
Error Messages
0
Auth Simplicity
95
Rate Limits
5

🔒 Security

TLS Enforcement
0
Auth Strength
30
Scope Granularity
20
Dep. Hygiene
65
Secret Handling
80

No network auth/TLS details are provided because the MCP server is intended to run locally via Claude Desktop launch configuration. This can be acceptable for a single-user workstation but may be risky if exposed beyond localhost. No explicit secret management guidance is shown; ensure you do not place credentials in command args/logs if you extend the server.

⚡ Reliability

Uptime/SLA
0
Version Stability
70
Breaking Changes
40
Error Recovery
35
AF Security Reliability

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.

Use Cases

  • AI-assisted reservoir engineering calculations (PVT properties, bubble point, black-oil tables)
  • Generating IPR curves and well performance outputs from natural-language prompts
  • Preparing inputs for reservoir simulators (e.g., relative permeability tables, black oil tables, aquifer influence functions)
  • Nodal/VLP calculations for deviated and horizontal completions
  • Geomechanics/wellbore stability calculations via MCP tool calls
  • Education/research workflows combining reservoir engineering computations with LLM-driven analysis

Not For

  • Production web applications requiring authenticated multi-tenant access over HTTP from a centralized service (based on provided info)
  • Environments that require guaranteed compliance certifications or auditable security posture beyond basic OSS usage guidance
  • Use as a high-assurance engineering component without independent validation/testing (calculations depend on models/correlations and user inputs)

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: No documented auth for local MCP (based on README)
OAuth: No Scopes: No

README describes connecting via Claude Desktop by launching the MCP server locally; no authentication mechanism, tokens, or scopes are documented in the provided content.

Pricing

Free tier: No
Requires CC: No

Open-source; no hosted pricing described in provided content.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

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.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for pyrestoolbox-mcp.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered