Learning Model Context Protocol

io.github.yarnabrinaPublished by GitHub account yarnabrinav0.3.0Updated Oct 24, 2026

Basic arithmetic tools with natural-language expression parsing and evaluation.

The publisher's own server: model.tools — Zero-Auth Agent Utilities

VerifiedSTDIODesktop onlyDeveloper Tools

Overview

AI-generated overview

A small learning-oriented MCP server that gives an assistant basic arithmetic tools with natural-language expression parsing and evaluation.

What you can do
  • Parse and evaluate arithmetic expressions written in natural language
  • Perform basic arithmetic calculations through MCP tools
  • Serve as a hands-on example for experimenting with MCP servers and clients
  • Run locally over stdio, with optional HTTP-related settings such as stateless mode and JSON responses
When to use it
Useful when you want a simple, low-risk server to try out MCP tooling, test a client configuration, or let an assistant do quick arithmetic. It is a learning and experimentation project rather than a production calculator service.
Requirements
Runs as a local process on the user's machine, installed from the PyPI package mcp-learning and started with uvx, so a Python/uv environment is needed. Optional environment variables control logging and HTTP behavior: DEBUG, JSON_RESPONSE, LOG_FILE, LOG_LEVEL, RUNTIME_ENVIRONMENT and STATELESS_HTTP. No authentication is declared.
Before you install
No credentials, payments or data-writing actions are described. Optional settings such as LOG_FILE write log output to a path you choose, so point it somewhere appropriate. Treat it as a demo project and verify results before relying on its arithmetic output.

Installation

In SourceWeft

  1. Open Learning Model Context Protocol in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Learning Model Context Protocol

This project explores the features and usage of Model Context Protocol (MCP) servers and clients, providing a hands-on learning environment for experimenting with MCP-based tools and workflows.

Documentation

Contributing

Please see CONTRIBUTING.md for development and contribution guidelines.

Links

License

This project is licensed under the GNU Affero General Public License v3.0 or later (AGPL-3.0-or-later).

Copyright (C) 2025-2026 Anirban Ray

See the LICENSE file for details.

Source: README.md at commit bc9ba23

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

2
  1. v0.3.0LatestOct 17, 2026
  2. v0.2.0Sep 16, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.

Other Model integrations