Polymath MegaBlaster MCP

Local and open-weight models (Llama, Qwen, Mistral, etc.) are consistently bad at exact math, date arithmetic, unit conversion, and a dozen other deterministic tasks. (Frontier hosted models like Claude and GPT-4 handle most of this correctly unaided already — this tool is aimed at closing the gap for smaller/local models, not replacing what those already do well.)

This is a local toolkit of 15 free tools that give AI agents a way to offload the kinds of computations reasoning models generally do not perform very well, computations are offloaded onto a calculator that uses classical deterministic methods to ascertain needed values. Fully offline, deterministic and 100% local, no network calls, no telemetry, no API keys. Fully open source and built lean.

Useful things it does:

Does exact math on huge numbers without rounding errors
Figures out dates correctly, including leap years and "the last day of the month" edge cases
Converts between units (km/miles, C/F, kg/lb) without approximating
Works out subnet math for networking
Computes distance between two coordinates (great-circle)

More technical things it does:

Arbitrary-precision arithmetic, factorials, permutations, combinations (avoids float64 overflow)
Statistics (mean, median, stdev, variance, percentiles) on a list of numbers
Base conversion (decimal, hex, binary, octal)
Levenshtein edit distance and similarity ratio (deterministic fuzzy matching)
Time zone conversion (IANA zone aware)
Token counting (GPT tokenizer) so an agent can manage its own context budget

Why local

Most AI dev tool MCP servers either charge a subscription or call out to a remote API. This one never touches the network. Every tool is pure local computation, verifiable in the source: read src/tools.js, there is no fetch or http import anywhere in it.

Setup

1. Install Node.js (v18 or newer) if you don't have it: https://nodejs.org

2. Clone this repo and install dependencies:

bash

git clone https://github.com/headlessherm-creator/polymath-megablaster-mcp.git
cd polymath-megablaster-mcp
npm install

3. Point your MCP client at the local path:

config.json

{
  "mcpServers": {
    "polymath": {
      "command": "node",
      "args": ["/absolute/path/to/polymath-megablaster-mcp/src/index.js"]
    }
  }
}

Add that to your MCP client's config and restart it. Setup docs for common clients:

Claude Desktop: https://modelcontextprotocol.io/quickstart/user
Cursor: https://docs.cursor.com/context/model-context-protocol
Claude Code: https://docs.claude.com/en/docs/claude-code/mcp

Tools (15, all free)

Deterministic math: calculate (arbitrary-precision expression evaluator), factorial, permutations, combinations (all arbitrary-precision, avoid float64 overflow), compute_statistics (mean, median, stdev, variance, percentiles)
Date and time: date_add, date_diff (leap years, month boundaries, business days handled correctly), convert_timezone
Conversion: convert_unit (length, weight, volume, temperature), convert_base (decimal, hex, binary, octal)
Networking: calc_subnet (CIDR math), check_ip_type (private/reserved range lookup)
Text: levenshtein_distance (exact edit distance and similarity ratio)
Geo: haversine_distance (exact great-circle distance between coordinates)
Agent utility: count_tokens (GPT tokenizer, for managing context budget before a large prompt)

Dependencies

@modelcontextprotocol/sdk: the MCP protocol implementation
zod: input schema validation
mathjs: arbitrary-precision math evaluation
gpt-tokenizer: GPT tokenizer for count_tokens

All installed automatically by npm install. None of them make network calls at runtime.

Development

Terminal

npm install
npm test        # unit tests on the core logic plus real MCP protocol integration tests
node src/index.js   # run the server directly (waits on stdin)

License

MIT.

Pro features

4 additional tools (hmac_text, compare_semver, aes_encrypt, aes_decrypt) are available as a paid one-time unlock: Polymath MegaBlaster Pro. [Link to be added once the storefront is live.]

Polymath Megablaster MCP README