Skill456 repo starsupdated 2d ago

mcp-operations

mcp-operations manages the local Model Context Protocol server infrastructure for the Claude Code Agent Monitor project. Use this skill when configuring the MCP host, diagnosing tool connectivity issues, modifying tool domain settings, or adjusting safety policy flags like mutation and destructive operation modes. The skill enforces read-only defaults and requires explicit confirmation for sensitive operations.

View source Repository: Claude-Code-Agent-Monitor

Install in Claude Code

Copy

git clone --depth 1 https://github.com/hoangsonww/Claude-Code-Agent-Monitor /tmp/mcp-operations && cp -r /tmp/mcp-operations/.claude/skills/mcp-operations ~/.claude/skills/mcp-operations

Then start a new Claude Code session; the skill loads automatically.

Definition

SKILL.md

# MCP Operations

Use this skill whenever work touches `mcp/` behavior or MCP host integration.

## Core workflow
- Confirm dashboard API is running (`/api/health`).
- Confirm MCP server build status.
- Validate env flags for mutation/destructive modes.
- Verify host configuration path and command.

## Safe operations policy
- Default to read-only mode (`MCP_DASHBOARD_ALLOW_MUTATIONS=false`).
- Enable mutations only for explicit admin tasks.
- Enable destructive mode only transiently and require explicit confirmation token.

## Required verification for code changes
- `npm run mcp:typecheck`
- `npm run mcp:build`

## References
- Host config examples: `references/host-config.md`
- Operations runbook: `references/runbook.md`