High-performance MCP server for mathematical operations using Polars and scientific Python
High-performance MCP server for mathematical operations using Polars and scientific Python. The vibe math mcp mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 14 defined tools rather than through you.
A high-performance Model Context Protocol (MCP) server for math-ing whilst vibing with LLMs. Built with Polars, Pandas, NumPy, SciPy, and SymPy for optimal calculation speed and comprehensive mathematical capabilities from basic arithmetic to advanced calculus and linear algebra.
Everything the assistant can do here goes through one of these:
Mode — Descriptionfull — Complete response with all metadata (default)compact — Remove null fields, minimize whitespaceminimal — Primary value(s) only, strip metadatavalue — Normalized {value: X} structurefinal — For sequential chains, return only terminal resultcalculate — Evaluate mathematical expressions with variable substitutionpercentage — Percentage calculations (of, increase, decrease, change)round — Advanced rounding (round, floor, ceil, trunc)convert_units — Unit conversions (degrees � radians)array_operations — Element-wise operations (add, subtract, multiply, divide, power)array_statistics — Statistical measures (mean, median, std, min, max, sum)vibe-math-mcp on PyPI is all you need. Most clients run it directly, so configuration is a few lines and a restart.
This sits in the planning and project tracking group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Vibe Math MCP's toolset — Mode, full, compact and 11 more — is a fair guide to whether it matches your workflow. It is maintained by apetta; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| Mode | Description |
| full | Complete response with all metadata (default) |
| compact | Remove null fields, minimize whitespace |
| minimal | Primary value(s) only, strip metadata |
| value | Normalized {value: X} structure |
| final | For sequential chains, return only terminal result |
| calculate | Evaluate mathematical expressions with variable substitution |
| percentage | Percentage calculations (of, increase, decrease, change) |
| round | Advanced rounding (round, floor, ceil, trunc) |
| convert_units | Unit conversions (degrees � radians) |
| array_operations | Element-wise operations (add, subtract, multiply, divide, power) |
| array_statistics | Statistical measures (mean, median, std, min, max, sum) |
| array_aggregate | Aggregations (sumproduct, weighted average, dot product) |
| array_transform | Transformations (normalise, standardise, scale, log) |
{
"mcpServers": {
"Math": {
"command": "uvx",
"args": ["vibe-math-mcp"]
}
}
}Configuration as documented by the project. Restart the client after saving.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Search and read your Drive — Docs, Sheets and files become context your assistant can actually use.
Your assistant inside the workspace — read channels, search history, post messages and tame the noise.
Metabase ships its own MCP endpoint — search your BI content, build and run queries, and save questions and dashboards without leaving the chat.
Stop letting your assistant hallucinate n8n node parameters — this server hands it the real schemas, templates and validation.