agentsclimarketplace

New mcp tool

Skill justnau1020/claude-os/skills/development/new-mcp-tool

An operating system for Claude Code. Skills, hooks (MCR), and a lean-context framework for smarter AI coding sessions.

Install
npx -y skills add justnau1020/claude-os --skill new-mcp-tool

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Add a new MCP tool to a FastMCP server. Use when adding a new tool for LLM agents or extending the MCP interface with new functionality.

SKILL.md

1.7 KB, as published. Nobody here has run it

Add a New MCP Tool

Add a tool to the project's FastMCP server.

Arguments

  • $ARGUMENTS -- Tool name in snake_case (e.g., get_user_profile)

Steps

1. Read the existing MCP server

Read the MCP server file to understand current tool patterns and the FastMCP setup.

2. Add the tool

@mcp.tool()
async def $ARGUMENTS(
    param1: str,
    param2: int = 10,
) -> str:
    """Clear description of what this tool does and when an LLM should use it.

    Include example parameter values to help LLMs understand expected input.
    Example: param1="example_value", param2=30
    """
    ...

3. Tool description conventions

The tool description is critical -- it's how LLMs decide when to call it:

  • First sentence: what the tool does
  • Second sentence: when to use it
  • Include parameter examples inline
  • Mention any constraints (rate limits, data availability)

4. Implementation conventions

  • Async only: All tool functions must be async def
  • Return strings: MCP tools return string responses for LLM consumption
  • Actionable errors: If something fails, return a helpful error string, not a generic one
  • Respect data boundaries: All data queries should respect the project's access control and data validation rules

5. Write tests

Add tests for the new tool's logic. Test:

  • Happy path with valid parameters
  • Error handling with invalid parameters
  • Data validation on returned data

6. Verify

pytest tests/ -v -k "mcp"

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.