Mrugankpednekar Mcp Optimizer
Built on top of CrewAI and SciPy's HiGHS solver, this server wraps linear and mixed-integer program solvers behind five MCP tools: solve_linear_program, solve_mixed_integer_program, parse_natural_language, diagnose_infeasibility, and solve_word_problem_with_data. The last one reads CSV, JSON, or Excel files and automatically extracts values to feed into optimization models. You supply LP models as JSON structures with variables, constraints, and objective terms, or describe problems in plain English and let the parser convert them. The MILP solver uses lightweight branch-and-bound or falls back to OR-Tools. Reach for this when you need to schedule shifts, allocate resources, or solve routing problems directly from Claude without coding up optimization logic yourself.
- tools
- 5
- auth
- Required
- transport
- HTTP
- last updated
- Oct 7, 2025
Tools
5 toolsPublic tool metadata for what this MCP can expose to an agent.
solve_linear_programSolves linear programs via SciPy's HiGHS backend.
Solves linear programs via SciPy's HiGHS backend.
No parameter schema in public metadata yet.
solve_mixed_integer_programExplores mixed-integer models with a lightweight branch-and-bound search (or OR-Tools fallback).
Explores mixed-integer models with a lightweight branch-and-bound search (or OR-Tools fallback).
No parameter schema in public metadata yet.
parse_natural_languageTranslates natural language prompts into LP JSON.
Translates natural language prompts into LP JSON.
No parameter schema in public metadata yet.
diagnose_infeasibilityDiagnoses infeasibility.
Diagnoses infeasibility.
No parameter schema in public metadata yet.
solve_word_problem_with_dataSolve optimization problems using data from files
Solve optimization problems using data from files
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
Crew Optimizer
Crew Optimizer rebuilds the original optimisation project around the CrewAI ecosystem. It provides reusable CrewAI tools and agents capable of solving linear programs via SciPy's HiGHS backend, exploring mixed-integer models with a lightweight branch-and-bound search (or OR-Tools fallback), translating natural language prompts into LP JSON, and diagnosing infeasibility. You can embed the tools inside your own crews or call them programmatically through the OptimizerCrew convenience wrapper, or serve them over the MCP protocol for clients such as Smithery.
Installation
python -m venv .venv
source .venv/bin/activate
pip install -e .[mip]
This installs Crew Optimizer together with optional OR-Tools support for MILP solving. Add pytest, ruff, or other dev tools as needed (pip install pytest).
Quick Usage
from crew_optimizer import OptimizerCrew
crew = OptimizerCrew(verbose=False)
Details
- Repository
- github.com/mrugankpednekar/mcp-optimizer
- Category
- Developer Tools
- Transport
- HTTP
- Auth
- Required
- Registry
- MCP registry, active
Related Developer Tools MCP servers
View all
Fake Star Auditarmada735/fake-star-auditTransparent rule-based GitHub fake-star detector — LOW/MEDIUM/HIGH with per-rule evidence.0stars
DevInsight MCPazalhoseinian/devinsight-mcpRead-only MCP server to inspect Git repos: code stats, TODOs, commits, health score, tech stack0stars
Vectorabrunosrz/vectoraAI assistant with RAG, web search, filesystem and memory. MCP sub-agent for Claude Code.0stars
Developer Tools Mcp Servercom.thenextgennexus/developer-tools-mcp-serverGitHub, npm, PyPI, Stack Overflow, arXiv and OpenAlex paper search as agent tools.0stars
Compuute MCP Security Scannercompuute/compuute-scan-apiScan any public GitHub MCP-server repo for security issues. 37 MCP-specific L1 rules, 8 languages.0stars
Deltaprobedeepthi-04/deltaprobeReview GitHub pull requests: diffs, summaries, risk checks and inline review comments.0stars