mcp-code-execution

Scaffold the code execution pattern for MCP-based agents. Use when agents call many MCP tools, intermediate data exceeds context, you need loops, or PII must stay out of context.

Jump to install

Repository: laurigates/claude-plugins
Last source activity: July 29, 2026 at 06:22
Detected SKILL.md language: English
Stars: 49
Forks: 7

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

A direct command skips the review prompt. Inspect the source before running it.

npx skills add https://github.com/laurigates/claude-plugins --skill mcp-code-execution

The command stays on one line. Scroll horizontally to inspect it before copying.

Prefer a local copy? Download the files currently available to SkillsMP.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

File Explorer

2 files

SKILL.md

Source instructions · Read-only preview

Back to search Back to installation

mcp-management

Install, configure and troubleshoot MCP servers. Use when adding/enabling servers, editing .mcp.json, fixing OAuth, or when a server runs stale code after an upstream fix.

2026-08-08

finops-overview

FinOps snapshot — org billing, workflow stats, cache usage. Use when you want a high-level view of CI spending or workflow health before diving deeper.

2026-08-08

github-actions-finops

GitHub Actions billing, workflow efficiency, and waste analysis at org or repo level. Use when investigating CI/CD costs, wasted runs, or optimizing triggers.

2026-08-08

View all from this repository

Use code execution when...	Use direct tool calls / `mcp-management` when...
Designing agents that fan out across 10+ MCP servers or 50+ tools	Installing or configuring one or two servers in `.mcp.json`
Intermediate results are large (>10K tokens) and would blow context	Results are small and all needed by the model
Workflows need loops, retries, or conditionals across tool calls	Linear sequences of 2–3 tool calls
PII must not reach the model context	Tool responses contain no sensitive data
Tasks benefit from state persistence across runs	Stateless, one-shot operations
You want agents to accumulate reusable skills	Fixed, predefined workflows

project/
├── servers/
│   ├── google-drive/
│   │   ├── getDocument.ts
│   │   ├── getSheet.ts
│   │   └── index.ts          # Re-exports all tools
│   ├── salesforce/
│   │   └── index.ts
│   └── slack/
│       └── index.ts
├── skills/                    # Agent-accumulated reusable functions
├── workspace/                 # Persistent state between executions
├── client.ts                  # MCP client that routes calls to servers
└── sandbox.config.ts          # Execution environment configuration

Pattern	What it buys
Progressive tool discovery	Navigate `servers/` on demand — ~150K tokens → ~2K (98.7% reduction)
Context-efficient filtering	Filter large datasets in the sandbox; only a summary reaches the model
Native control flow	Loops/retries/conditionals run in the sandbox, not as chained tool calls
PII tokenization	The client tokenizes sensitive fields so PII never enters model context
State persistence	Save intermediate results to `workspace/` for cross-execution continuity
Skill accumulation	Persist reusable functions to `skills/` for future executions

Item	Status
Sandboxed execution environment	Required
Resource limits (CPU, memory, disk)	Required
Network isolation (MCP servers only)	Required
Execution timeout	Required
PII tokenization in MCP client	Recommended for sensitive data
Audit logging of all executions	Recommended
Read-only access to `servers/`	Recommended
Scoped write access to `workspace/` only	Recommended

name	mcp-code-execution
description	Scaffold the code execution pattern for MCP-based agents. Use when agents call many MCP tools, intermediate data exceeds context, you need loops, or PII must stay out of context.
user-invocable	false
allowed-tools	Bash, Read, Write, Edit, Grep, Glob, TodoWrite
created	"2026-02-08T00:00:00.000Z"
modified	"2026-07-28T00:00:00.000Z"
reviewed	"2026-06-14T00:00:00.000Z"

name	mcp-code-execution
description	Scaffold the code execution pattern for MCP-based agents. Use when agents call many MCP tools, intermediate data exceeds context, you need loops, or PII must stay out of context.
user-invocable	false
allowed-tools	Bash, Read, Write, Edit, Grep, Glob, TodoWrite
created	"2026-02-08T00:00:00.000Z"
modified	"2026-07-28T00:00:00.000Z"
reviewed	"2026-06-14T00:00:00.000Z"

Approach	Tool definitions	Intermediate data	Total
Direct tool calls	All loaded upfront	Passes through context	High
Code execution	On-demand discovery	Stays in sandbox	Low

mcp-code-execution

Install options

Review the source files