[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79ABRCZRQSD2XHPBQX7PD95":3,"skill-same:01M79ABRCZRQSD2XHPBQX7PD95":46},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":14,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M79ABRCZRQSD2XHPBQX7PD95","mcp-management",null,"Manage MCP servers - discover, analyze, execute tools\u002Fprompts\u002Fresources. Use for MCP integrations, capability discovery, tool filtering, programmatic execution, or encountering context bloat, server configuration, tool execution errors.","Elogic360\u002Fsoftware-factory","Elogic360","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F156535519?v=4","01M74NH3F0RB13PWB7JZDE2V80","elogic360","01M74NH3FPC65082MDZVMFHDM3",0,"MIT","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fmcp-management\u002Fskills\u002Fmcp-management\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: mcp-management\ndescription: Manage MCP servers - discover, analyze, execute tools\u002Fprompts\u002Fresources. Use for MCP integrations, capability discovery, tool filtering, programmatic execution, or encountering context bloat, server configuration, tool execution errors.\nmetadata:\n  keywords: \"MCP, Model Context Protocol, MCP servers, tool discovery, MCP integration, capability discovery, tool filtering, MCP tools, MCP prompts, MCP resources, progressive disclosure, multi-server management, tool catalog, mcp client, mcp execution, server configuration, context-efficient\"\nlicense: MIT\n---\n\n# MCP Management\n\nSkill for managing and interacting with Model Context Protocol (MCP) servers.\n\n## Overview\n\nMCP is an open protocol enabling AI agents to connect to external tools and data sources. This skill provides scripts and utilities to discover, analyze, and execute MCP capabilities from configured servers without polluting the main context window.\n\n**Key Benefits**:\n- Progressive disclosure of MCP capabilities (load only what's needed)\n- Intelligent tool\u002Fprompt\u002Fresource selection based on task requirements\n- Multi-server management from single config file\n- Context-efficient: subagents handle MCP discovery and execution\n- Persistent tool catalog: automatically saves discovered tools to JSON for fast reference\n\n## When to Use This Skill\n\nUse this skill when:\n1. **Discovering MCP Capabilities**: Need to list available tools\u002Fprompts\u002Fresources from configured servers\n2. **Task-Based Tool Selection**: Analyzing which MCP tools are relevant for a specific task\n3. **Executing MCP Tools**: Calling MCP tools programmatically with proper parameter handling\n4. **MCP Integration**: Building or debugging MCP client implementations\n5. **Context Management**: Avoiding context pollution by delegating MCP operations to subagents\n\n## Core Capabilities\n\n### 1. Configuration Management\n\nMCP servers configured in `.claude\u002F.mcp.json`.\n\n**Gemini CLI Integration** (recommended): Create symlink to `.gemini\u002Fsettings.json`:\n```bash\nmkdir -p .gemini && ln -sf .claude\u002F.mcp.json .gemini\u002Fsettings.json\n```\n\n### 2. Capability Discovery\n\n```bash\n# Preferred: Using bun (faster)\nbunx tsx scripts\u002Fcli.ts list-tools  # Saves to assets\u002Ftools.json\nbunx tsx scripts\u002Fcli.ts list-prompts\nbunx tsx scripts\u002Fcli.ts list-resources\n\n# Alternative: Using bunx\nbunx tsx scripts\u002Fcli.ts list-tools\nbunx tsx scripts\u002Fcli.ts list-prompts\nbunx tsx scripts\u002Fcli.ts list-resources\n```\n\nAggregates capabilities from multiple servers with server identification.\n\n### 3. Intelligent Tool Analysis\n\nLLM analyzes `assets\u002Ftools.json` directly - better than keyword matching algorithms.\n\n### 4. Tool Execution\n\n**Primary: Gemini CLI** (if available)\n```bash\ngemini -y -m gemini-2.5-flash -p \"Take a screenshot of https:\u002F\u002Fexample.com\"\n```\n\n**Secondary: Direct Scripts**\n```bash\n# Preferred: Using bun\nbunx tsx scripts\u002Fcli.ts call-tool memory create_entities '{\"entities\":[...]}'\n\n# Alternative: Using bunx\nbunx tsx scripts\u002Fcli.ts call-tool memory create_entities '{\"entities\":[...]}'\n```\n\n**Fallback: mcp-manager Subagent**\n\n## Implementation Patterns\n\n### Pattern 1: Gemini CLI Auto-Execution (Primary)\n\nUse Gemini CLI for automatic tool discovery and execution.\n\n**Quick Example**:\n```bash\ngemini -y -m gemini-2.5-flash -p \"Take a screenshot of https:\u002F\u002Fexample.com\"\n```\n\n**Benefits**: Automatic tool discovery, natural language execution, faster than subagent orchestration.\n\n### Pattern 2: Subagent-Based Execution (Fallback)\n\nUse `mcp-manager` agent when Gemini CLI unavailable. Subagent discovers tools, selects relevant ones, executes tasks, reports back.\n\n**Benefit**: Main context stays clean, only relevant tool definitions loaded when needed.\n\n### Pattern 3: LLM-Driven Tool Selection\n\nLLM reads `assets\u002Ftools.json`, intelligently selects relevant tools using context understanding, synonyms, and intent recognition.\n\n### Pattern 4: Multi-Server Orchestration\n\nCoordinate tools across multiple servers. Each tool knows its source server for proper routing.\n\n## Quick Start\n\n**Method 1: Gemini CLI** (recommended)\n```bash\nbun install -g gemini-cli  # or: bun add -g gemini-cli\nmkdir -p .gemini && ln -sf .claude\u002F.mcp.json .gemini\u002Fsettings.json\ngemini -y -m gemini-2.5-flash -p \"Take a screenshot of https:\u002F\u002Fexample.com\"\n```\n\n**Method 2: Scripts**\n```bash\ncd .claude\u002Fskills\u002Fmcp-management\u002Fscripts\nbun install  # or: bun install\nbunx tsx cli.ts list-tools  # Saves to assets\u002Ftools.json\nbunx tsx cli.ts call-tool memory create_entities '{\"entities\":[...]}'\n```\n\n**Method 3: mcp-manager Subagent**\n\nDispatch subagent to handle MCP operations, keeping main context clean.\n\n## Secure Installation\n\nWhen installing MCP server packages, follow supply chain security best practices:\n\n- **Block post-install scripts** — `npm config set ignore-scripts true` (or Bun: disabled by default)\n- **Cooldown period** — Wait 7 days for new package versions to be vetted by the community\n- **Audit before installing** — Run `socket package score npm \u003Cpkg>` or use `socket npm install \u003Cpkg>` to check packages\n\nLoad the `dependency-upgrade` skill for full security configuration including Socket CLI integration, cooldown setup, lockfile validation, and CI enforcement.\n\n## Integration Strategy\n\n### Execution Priority\n\n1. **Gemini CLI** (Primary): Fast, automatic, intelligent tool selection\n   - Check: `command -v gemini`\n   - Execute: `gemini -y -m gemini-2.5-flash -p \"\u003Ctask>\"`\n   - Best for: All tasks when available\n\n2. **Direct CLI Scripts** (Secondary): Manual tool specification\n   - Use when: Need specific tool\u002Fserver control\n   - Execute: `bunx tsx scripts\u002Fcli.ts call-tool \u003Cserver> \u003Ctool> \u003Cargs>`\n\n3. **mcp-manager Subagent** (Fallback): Context-efficient delegation\n   - Use when: Gemini unavailable or failed\n   - Keeps main context clean\n\n### Integration with Agents\n\nThe `mcp-manager` agent uses this skill to:\n- Check Gemini CLI availability first\n- Execute via `gemini` command if available\n- Fallback to direct script execution\n- Discover MCP capabilities without loading into main context\n- Report results back to main agent\n\nThis keeps main agent context clean and enables efficient MCP integration.\n","# MCP Management\n\nSkill for managing and interacting with Model Context Protocol (MCP) servers.\n\n## Overview\n\nMCP is an open protocol enabling AI agents to connect to external tools and data sources. This skill provides scripts and utilities to discover, analyze, and execute MCP capabilities from configured servers without polluting the main context window.\n\n**Key Benefits**:\n- Progressive disclosure of MCP capabilities (load only what's needed)\n- Intelligent tool\u002Fprompt\u002Fresource selection based on task requirements\n- Multi-server management from single config file\n- Context-efficient: subagents handle MCP discovery and execution\n- Persistent tool catalog: automatically saves discovered tools to JSON for fast reference\n\n## When to Use This Skill\n\nUse this skill when:\n1. **Discovering MCP Capabilities**: Need to list available tools\u002Fprompts\u002Fresources from configured servers\n2. **Task-Based Tool Selection**: Analyzing which MCP tools are relevant for a specific task\n3. **Executing MCP Tools**: Calling MCP tools programmatically with proper parameter handling\n4. **MCP Integration**: Building or debugging MCP client implementations\n5. **Context Management**: Avoiding context pollution by delegating MCP operations to subagents\n\n## Core Capabilities\n\n### 1. Configuration Management\n\nMCP servers configured in `.claude\u002F.mcp.json`.\n\n**Gemini CLI Integration** (recommended): Create symlink to `.gemini\u002Fsettings.json`:\n```bash\nmkdir -p .gemini && ln -sf .claude\u002F.mcp.json .gemini\u002Fsettings.json\n```\n\n### 2. Capability Discovery\n\n```bash\n# Preferred: Using bun (faster)\nbunx tsx scripts\u002Fcli.ts list-tools  # Saves to assets\u002Ftools.json\nbunx tsx scripts\u002Fcli.ts list-prompts\nbunx tsx scripts\u002Fcli.ts list-resources\n\n# Alternative: Using bunx\nbunx tsx scripts\u002Fcli.ts list-tools\nbunx tsx scripts\u002Fcli.ts list-prompts\nbunx tsx scripts\u002Fcli.ts list-resources\n```\n\nAggregates capabilities from multiple servers with server identification.\n\n### 3. Intelligent Tool Analysis\n\nLLM analyzes `assets\u002Ftools.json` directly - better than keyword matching algorithms.\n\n### 4. Tool Execution\n\n**Primary: Gemini CLI** (if available)\n```bash\ngemini -y -m gemini-2.5-flash -p \"Take a screenshot of https:\u002F\u002Fexample.com\"\n```\n\n**Secondary: Direct Scripts**\n```bash\n# Preferred: Using bun\nbunx tsx scripts\u002Fcli.ts call-tool memory create_entities '{\"entities\":[...]}'\n\n# Alternative: Using bunx\nbunx tsx scripts\u002Fcli.ts call-tool memory create_entities '{\"entities\":[...]}'\n```\n\n**Fallback: mcp-manager Subagent**\n\n## Implementation Patterns\n\n### Pattern 1: Gemini CLI Auto-Execution (Primary)\n\nUse Gemini CLI for automatic tool discovery and execution.\n\n**Quick Example**:\n```bash\ngemini -y -m gemini-2.5-flash -p \"Take a screenshot of https:\u002F\u002Fexample.com\"\n```\n\n**Benefits**: Automatic tool discovery, natural language execution, faster than subagent orchestration.\n\n### Pattern 2: Subagent-Based Execution (Fallback)\n\nUse `mcp-manager` agent when Gemini CLI unavailable. Subagent discovers tools, selects relevant ones, executes tasks, reports back.\n\n**Benefit**: Main context stays clean, only relevant tool definitions loaded when needed.\n\n### Pattern 3: LLM-Driven Tool Selection\n\nLLM reads `assets\u002Ftools.json`, intelligently selects relevant tools using context understanding, synonyms, and intent recognition.\n\n### Pattern 4: Multi-Server Orchestration\n\nCoordinate tools across multiple servers. Each tool knows its source server for proper routing.\n\n## Quick Start\n\n**Method 1: Gemini CLI** (recommended)\n```bash\nbun install -g gemini-cli  # or: bun add -g gemini-cli\nmkdir -p .gemini && ln -sf .claude\u002F.mcp.json .gemini\u002Fsettings.json\ngemini -y -m gemini-2.5-flash -p \"Take a screenshot of https:\u002F\u002Fexample.com\"\n```\n\n**Method 2: Scripts**\n```bash\ncd .claude\u002Fskills\u002Fmcp-management\u002Fscripts\nbun install  # or: bun install\nbunx tsx cli.ts list-tools  # Saves to assets\u002Ftools.json\nbunx tsx cli.ts call-tool memory create_entities '{\"entities\":[...]}'\n```\n\n**Method 3: mcp-manager Subagent**\n\nDispatch subagent to handle MCP operations, keeping main context clean.\n\n## Secure Installation\n\nWhen installing MCP server packages, follow supply chain security best practices:\n\n- **Block post-install scripts** — `npm config set ignore-scripts true` (or Bun: disabled by default)\n- **Cooldown period** — Wait 7 days for new package versions to be vetted by the community\n- **Audit before installing** — Run `socket package score npm \u003Cpkg>` or use `socket npm install \u003Cpkg>` to check packages\n\nLoad the `dependency-upgrade` skill for full security configuration including Socket CLI integration, cooldown setup, lockfile validation, and CI enforcement.\n\n## Integration Strategy\n\n### Execution Priority\n\n1. **Gemini CLI** (Primary): Fast, automatic, intelligent tool selection\n   - Check: `command -v gemini`\n   - Execute: `gemini -y -m gemini-2.5-flash -p \"\u003Ctask>\"`\n   - Best for: All tasks when available\n\n2. **Direct CLI Scripts** (Secondary): Manual tool specification\n   - Use when: Need specific tool\u002Fserver control\n   - Execute: `bunx tsx scripts\u002Fcli.ts call-tool \u003Cserver> \u003Ctool> \u003Cargs>`\n\n3. **mcp-manager Subagent** (Fallback): Context-efficient delegation\n   - Use when: Gemini unavailable or failed\n   - Keeps main context clean\n\n### Integration with Agents\n\nThe `mcp-manager` agent uses this skill to:\n- Check Gemini CLI availability first\n- Execute via `gemini` command if available\n- Fallback to direct script execution\n- Discover MCP capabilities without loading into main context\n- Report results back to main agent\n\nThis keeps main agent context clean and enables efficient MCP integration.\n",{"name":5,"license":15,"metadata":24,"description":7},{"keywords":25},"MCP, Model Context Protocol, MCP servers, tool discovery, MCP integration, capability discovery, tool filtering, MCP tools, MCP prompts, MCP resources, progressive disclosure, multi-server management, tool catalog, mcp client, mcp execution, server configuration, context-efficient","main","c475fc64e94e803b50d14a791dfee8853fbb2c5c","integrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fmcp-management\u002Fskills\u002Fmcp-management","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory","https:\u002F\u002Fgithub.com\u002FElogic360","2026-11-08 22:21:22",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add Elogic360\u002Fsoftware-factory --skill mcp-management",{"tool":38,"command":39},"bunx","bunx skills add Elogic360\u002Fsoftware-factory --skill mcp-management",{"tool":41,"command":42},"pnpm","pnpm dlx skills add Elogic360\u002Fsoftware-factory --skill mcp-management","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-skills-secondsky\u002Fplugins\u002Fmcp-management\u002Fskills\u002Fmcp-management\u002FSKILL.md",true,[],[47,55,62,69,76,83],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":51,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M79G206MT3J6S0GY3C45P2KV","vss-summarize-video","Use to summarize a recorded video via the LVS summarization microservice (HITL-gated) with a VLM fallback. Not for report generation or live RTSP captioning.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-summarize-video\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":51,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M79G1WN63PGRE8CKD47WEBQ5","vss-setup-video-analytics-api","Use to deploy the vss-video-analytics-api REST service standalone (config-source, data-log bind, Elasticsearch, optional Kafka). Not for full warehouse deploy.","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-setup-video-analytics-api\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":51,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M79G1S9F7VY3EF6H53PRP5AN","vss-setup-behavior-analytics","Use to deploy the vss-behavior-analytics service standalone (entrypoint, config-source, optional calibration). Not for the full warehouse deploy.","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-setup-behavior-analytics\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":51,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M79G1N1S1Y27PFZPYMNK1MTQ","vss-search-archive","Use this skill to run top-level VSS fusion search on archived video, or to ingest video files \u002F RTSP streams for search. Do NOT use for ad-hoc visual Q&A (use vss-ask-video), live captioning (use vss-deploy-dense-captioning), or video summarization and reports (use vss-summarize-video).","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-search-archive\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":51,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M79G1H6WN0Q6C0VCAXCZX6B7","vss-query-analytics","Use this skill when reading video-analytics metrics, incidents, alerts, and sensor data via the VA-MCP server (port 9901). Not for live VLM or incident-range narrative reports.","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-query-analytics\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":51,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M79G1DYPNXQS7QHZ0AAF5FX5","vss-manage-video-io-storage","Use to call the VIOS REST API (sensor list, timelines, clip extraction, snapshots, add\u002Fdelete sensors and streams). Not for VLM inference or search.","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-manage-video-io-storage\u002FSKILL.md",[],[]]