
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
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.
Installation
In SourceWeft
- Open Learning Model Context Protocol in the dashboard and add it to a workspace.
- 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
- Installation Guide — How to set up your environment and install dependencies.
- Examples & Usage — Step-by-step usage and sample sessions.
- MCP Server Configuration
- MCP Client Configuration
Contributing
Please see CONTRIBUTING.md for development and contribution guidelines.
Links
- PyPI Package: mcp-learning
- MCP Registry: mcp-learning
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
0Version history
2- v0.3.0LatestOct 17, 2026
- 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

model.tools — Zero-Auth Agent Utilities
tools.modelOfficial publisher
Zero-auth remote utility server giving agents disposable email OTP reading, durable checkpoints, webhook bins, wake timers, receipts and page-to-Markdown…
NLP.COM.AI Open Model Catalog
ai.com.nlpOfficial publisher
NLP.COM.AI Open Model Catalog's hosted MCP server, published by nlp.com.ai; no sign-in required; Streamable HTTP; 3 tools.

Hologram Model Hub
foundation.uor.hubOfficial publisher
A remote MCP server that lets an assistant search an index of open models and get verified download links with SHA-256 checksums.

ModelLens
Published by GitHub account Greatbeing
Probes OpenAI-compatible model gateways, ranks models by measured latency and success, and recommends which model to use.

Bedrock Multi-Model
Published by GitHub account Sagargupta16
Local MCP server that puts AWS Bedrock's text, image, video and embedding models behind nine tools so an assistant can ask, compare and judge models.