Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Climbing Grade Converter MCP Server Convert 5.10a to French grade"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A specialized Model Context Protocol (MCP) server that enables LLMs (like Claude) to accurately convert climbing grades across different rating systems using a data-driven approach.
Python 3.11+
FastMCP (MCP Python SDK)
Pydantic (Data Validation)
uv (High-performance Python package & environment manager)
Related MCP server: SkillMesh
1. Prerequisites
Ensure you have uv installed in your Linux distribution:
curl -LsSf https://astral.sh/uv/install.sh | sh2. Installation
Clone the repository and sync dependencies:
git clone https://github.com/yychentw/free-climbing-grade-converter-mcp.git
cd free_climbing_grade_converter_mcp
uv sync3. Verification
Test the server logic manually in your terminal:
uv run main.pyTo use this tool in Claude Desktop (Windows) via WSL, add the following entry to your claude_desktop_config.json (Note: Replace /home/user/... with the absolute path to your project directory in WSL.):
{
"mcpServers": {
"climbing-converter": {
"command": "wsl",
"args": [
"-d", "Ubuntu",
"-e", "bash", "-l", "-c",
"cd /home/user/free_climbing_grade_converter_mcp && uv run main.py"
]
}
}
}Once connected, you can ask Claude:
"I just climbed a 6a+ in France. What is that in YDS?"
"Convert V3 to the French grading system."
"What climbing systems do you currently support?"
main.py: The core MCP server logic and tool definitions.
climbing_grades.json: The source-of-truth database for grade mappings.
pyproject.toml: Project metadata and dependency management.
| Name | Required | Description | Default |
|---|---|---|---|
| grade | Yes | ||
| to_system | Yes | ||
| from_system | Yes |
| Name | Required | Description |
|---|---|---|
| note | Yes | |
| grade | Yes | |
| system | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0convert_climbing_grade_toolScored across 1 tool
With only a single tool, there is no ambiguity between tools. The tool's purpose is clear from its name.
The tool name follows a verb_noun pattern, but the 'tool' suffix is slightly redundant. Still, it is consistent as the only tool.
One tool for a climbing grade converter is arguably well-scoped, though it feels minimal for a full-featured server.
The tool covers the core conversion operation, but with no description or additional tools, it's unclear if it supports multiple grading systems or validation, leaving potential gaps.
Extract structured data points from research papers and other documents with an LLM.
Fused LLM rankings: one IRT/Elo scale across ~5,000 public benchmark leaderboards, updated daily.
Enable language models to perform advanced AI-powered web scraping with enterprise-grade reliabili…
Sentiment, toxicity, entity extraction, PII, translation, summary, QA, fraud scoring, safety audit.
