Skip to content
MCP server

Learning Model Context Protocol

Small arithmetic server for learning how MCP servers and clients work

Install
Pricing
Open source
Platforms
self-hosted, CLI
Runs
Remotely
Version
0.3.0
Listing updated
1 day ago

About Learning Model Context Protocol

Learning Model Context Protocol is an open-source MCP server for ai models and llm tooling. It runs as a hosted remote server, so there is nothing to install locally.

This is a hands-on learning project from an individual developer rather than a production service. The registry entry says it exposes basic arithmetic tools that parse and evaluate expressions written in natural language, which makes it a convenient target for trying out MCP clients.

The package, published on PyPI as mcp-learning, runs over streamable HTTP on a local address and is configured through environment variables for debug mode, runtime environment, log level, an optional log file, JSON responses and stateless HTTP. A documentation site covers installation, examples and usage, and server and client configuration.

It is licensed under AGPL-3.0-or-later. The README itself gives little detail about individual tools, so treat it as a sandbox for experimenting with MCP features.

Install

Run in a terminal

claude mcp add mcp-learning -- uvx mcp-learning

Add to claude_desktop_config.json

{
  "mcpServers": {
    "mcp-learning": {
      "command": "uvx",
      "args": [
        "mcp-learning"
      ]
    }
  }
}
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "mcp-learning": {
      "command": "uvx",
      "args": [
        "mcp-learning"
      ]
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "mcp-learning": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "mcp-learning"
      ]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "mcp-learning": {
      "command": "uvx",
      "args": [
        "mcp-learning"
      ]
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "mcp-learning": {
      "command": "uvx",
      "args": [
        "mcp-learning"
      ]
    }
  }
}

Configuration

  • DEBUGEnable additional debug logging output.
  • RUNTIME_ENVIRONMENTLogging/runtime environment.
  • LOG_LEVELLog level for server output; the server defaults to INFO.
  • LOG_FILEOptional path for a server log file.
  • JSON_RESPONSEReturn JSON payloads for HTTP responses instead of newline-delimited JSON.
  • STATELESS_HTTPDisable HTTP keep-alive to serve each request independently.

What it does

Expression evaluation
Parses and evaluates arithmetic expressions written in words.
Streamable HTTP
Runs locally over HTTP on a configurable setup.
Logging options
Debug mode, log level and optional log file.
Stateless mode
Optionally serves each request independently.
Documentation site
Guides for installation, usage and configuration.

Good for

  • Learn how an MCP server and client communicate
  • Test client configuration with a simple tool
  • Experiment with HTTP transport settings
  • Use as a reference for a small Python MCP server

Pricing

Open source

Free, AGPL-3.0-or-later licence.

Prices change. Check yarnabrina.github.io before you buy.

Learning Model Context Protocol FAQ

How do I install it?

Install the mcp-learning package from PyPI, as listed in the registry.

What licence does it use?

AGPL-3.0-or-later.

Which settings can I change?

DEBUG, RUNTIME_ENVIRONMENT, LOG_LEVEL, LOG_FILE, JSON_RESPONSE and STATELESS_HTTP.

Where is it served by default?

At http://127.0.0.1:8000/mcp over streamable HTTP.

Is Learning Model Context Protocol free?

Yes. Learning Model Context Protocol is open source, so you can use and self-host it for free.

How do I add Learning Model Context Protocol to Claude Code?

Run this command in your terminal: claude mcp add mcp-learning -- uvx mcp-learning

What are the best alternatives to Learning Model Context Protocol?

The closest alternatives to Learning Model Context Protocol are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to Learning Model Context Protocol

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools