About mcp-scripts
mcp-scripts is a skill for writing scripts in a project’s `scripts/` directory. It defines CLI argument, MCP tool-call, error-handling, and output conventions for scripts intended for Claude.
Key features
- 01CLI arguments for parameters
- 02Required usage docstrings
- 03MCP tool calls via runtime pattern
- 04Graceful error reporting
- 05Results printed to stdout
Use cases
- 01Create scripts that call MCP tools
- 02Keep script parameters out of source code
- 03Check scripts with the runtime harness
MCP support
It documents the `call_mcp_tool("server__tool", params)` pattern for invoking MCP tools through `runtime.mcp_client`.
Install
Copy the command and run it in a terminal.
$
npx skills add https:/ / github.com/ parcadei/ continuous-claude-v3 --skill mcp-scriptsAfter installing, type/mcp-scriptsin Claude Code to confirm it loaded.
Details
From the project READMEMCP Script Rules
When working with files in scripts/:
DO
- Use CLI arguments for all parameters (argparse)
- Include USAGE docstring at top of file
- Use
call_mcp_tool("server__tool", params)pattern - Handle errors gracefully with informative messages
- Print results to stdout for Claude to process
DON'T
- Hardcode parameters in the script
- Edit scripts to change parameters (use CLI args instead)
- Import from servers/ directly (use runtime.mcp_client)
Tool Naming
Tool IDs use double underscore: serverName__toolName
Examples:
morph__warpgrep_codebase_searchast-grep__ast_grepperplexity__perplexity_ask
Testing
Test with: uv run python -m runtime.harness scripts/<script>.py --help
Comments
Markdown supported