
Mcp Scripts
- 475 installs
- 3.9k repo stars
- Updated January 26, 2026
- parcadei/continuous-claude-v3
mcp-scripts is a Continuous Claude v3 skill that enforces MCP wrapper script conventions with argparse CLI args and call_mcp_tool patterns for developers who automate MCP tool calls from Python scripts.
About
mcp-scripts is a parcadei/continuous-claude-v3 agent skill with 458 skills.sh installs that defines rules for Python files under scripts/. Scripts must accept all parameters via argparse CLI arguments, include a USAGE docstring at the top, call tools through call_mcp_tool("server__tool", params), handle errors with informative messages, and print results to stdout for Claude to parse. Hardcoding parameters or importing directly from servers/ is forbidden—scripts must use runtime.mcp_client instead. Tool IDs follow a double-underscore convention such as morph__warpgrep_codebase_search or perplexity__perplexity_ask. Testing uses uv run python -m runtime.harness scripts/<file>.py --help. Developers reach for mcp-scripts when adding or editing automation scripts that wrap MCP servers inside the Continuous Claude v3 harness.
- mcp-scripts
Mcp Scripts by the numbers
- 475 all-time installs (skills.sh)
- +2 installs in the week ending Aug 4, 2026 (Skillselion tracking)
- Ranked #859 of 4,347 Backend & APIs skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/parcadei/continuous-claude-v3 --skill mcp-scriptsAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 475 |
|---|---|
| repo stars | ★ 3.9k |
| Last updated | January 26, 2026 |
| Repository | parcadei/continuous-claude-v3 ↗ |
How do you write MCP wrapper scripts in Python?
Use mcp-scripts for development tasks
Who is it for?
Developers extending Continuous Claude v3 who add scripts/ utilities that invoke MCP tools through the project's runtime harness.
Skip if: Direct MCP server implementation inside servers/ or ad-hoc scripts that hardcode parameters without CLI arguments.
When should I use this skill?
Files under scripts/ are created or edited and must call MCP tools via call_mcp_tool with correct naming and harness testing.
What you get
Argparse-driven Python scripts with USAGE docstrings, call_mcp_tool invocations, stdout results, and harness-testable CLI interfaces.
- Argparse CLI Python MCP wrapper script
- stdout-printed tool results for agent parsing
- Harness-verified --help interface
By the numbers
- 458 skills.sh installs for parcadei/continuous-claude-v3 mcp-scripts
- Documents serverName__toolName double-underscore MCP tool ID convention
- Example tool IDs include morph__warpgrep_codebase_search and perplexity__perplexity_ask
Files
MCP 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
Related skills
How it compares
Use mcp-scripts when authoring Continuous Claude v3 Python MCP wrappers; use MCP server docs when implementing the server itself.
FAQ
What import pattern does mcp-scripts require for MCP calls?
mcp-scripts forbids importing from servers/ directly. Scripts in continuous-claude-v3 must use runtime.mcp_client and invoke tools through call_mcp_tool with serverName__toolName identifiers.
How should parameters be passed in mcp-scripts Python files?
mcp-scripts requires all parameters as argparse CLI arguments with a USAGE docstring at the file top. Editing scripts to change parameters is disallowed; callers pass flags at runtime instead.
How do you test mcp-scripts-compliant files?
mcp-scripts specifies testing with uv run python -m runtime.harness scripts/<script>.py --help to verify CLI wiring before Claude processes stdout output from live MCP calls.