Summary
This is a style guide for writing Python scripts that interact with MCP servers through Claude's runtime. It enforces a clean pattern: use argparse for parameters, call tools via `call_mcp_tool("server__tool", params)`, and print to stdout. The double underscore naming convention for tools is specific and non-negotiable. The most practical bit is the hard rule against editing scripts to change parameters, which will save you from cluttering your git history with parameter tweaks. If you're building scripts that Claude will invoke to interact with MCP tools, these conventions keep things consistent and testable via the harness runner.
Install to Claude Code
npx -y skills add parcadei/continuous-claude-v3 --skill mcp-scripts --agent claude-codeInstalls into .claude/skills of the current project.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Files
SKILL.md
Select a file.
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
