一键导入
commander-mcp
Access commander-mcp for ALL infrastructure data, skills, and methodology
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Access commander-mcp for ALL infrastructure data, skills, and methodology
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Load CI/CD pipeline configuration and deployment information when working with automation or deployments
Load database relationships, shared resources, and schema information when working with data models or database configuration
Load development environment information including folder structure, OrbStack setup, and system configuration
Load port mappings for all projects when working with networking, docker-compose, or service configuration
Load GitHub/GitLab repository information when working with git, CI/CD, or repository management
Load server information, infrastructure details, and access patterns when working with deployment or server configuration
| name | commander-mcp |
| description | Access commander-mcp for ALL infrastructure data, skills, and methodology |
| disable-model-invocation | false |
ALL infrastructure data, methodology, and project context lives in commander-mcp (dev-02:30040). Do NOT hardcode IPs, ports, credentials, or service info. Query at runtime.
get_skill(name) — get full skill content by namelist_skills() — list all available skillssearch_skills(query) — search skills by contentget_context_servers — server landscape (IPs, specs, status)get_context_ports — port allocationsget_context_databases — database configs and credentialsget_context_services — service catalog with healthget_context_repos — git repository listget_context_cicd — CI/CD pipeline configget_context_environment — env vars for all serviceslist_servers, get_server(key) — server details from ArangoDBlist_services, get_service(key) — service detailslist_ports, get_port(key) — port mappingsquery_dependencies(key, direction) — dependency graph traversal (upstream/downstream/both)get_topology() — full infrastructure topologysearch_infra(query) — search across all infrastructureget_stage_instructions(stage) — what to do at each pipeline stagelist_pipeline_runs, create_pipeline_run — manage runslist_work_items, create_work_item — work itemslist_scenarios, get_scenario — test scenariostransition_work_item(id, status) — move items through statuseslist_credentials — list available credentialsget_credential(name) — get credential value securelyagent_heartbeat — report agent statuslog_agent_event — log events for auditlog_cost_event — track API costsWhen MCP tools aren't available (e.g., on a remote server via SSH):
curl -s 'http://localhost:30040/skill/<name>'
curl -s 'http://localhost:30040/context/<type>'
curl -s 'http://localhost:30040/skill-catalog'
curl -s 'http://localhost:30040/health'
Never hardcode infrastructure data. Always query commander-mcp at runtime. When you need server IPs, port numbers, credentials, or service configs — use the tools above.