Install, validate, and manage MCP servers for OMK using the curated catalog and parallel processing.
Install, validate, and manage MCP servers for OMK using the curated catalog and parallel processing.
npx skills add https://github.com/dmae97/oh-my-kimi --skill mcp-install复制此命令并粘贴到 Claude Code 中以安装该技能
| name | mcp-install |
| description | Install, validate, and manage MCP servers for OMK using the curated catalog and parallel processing. |
Guide for adding MCP servers to an OMK project using the built-in catalog and parallel orchestration.
# List configured MCP servers
omk mcp list
# Diagnose all MCP servers
omk mcp doctor
# Diagnose a specific server
omk mcp doctor <server-name>
# Install a single MCP server
omk mcp install <name> <command> [args...]
# Remove a server from project-local config
omk mcp remove <name>
# Sync global MCP servers into project
omk mcp sync-global
OMK ships with a verified catalog in src/mcp/server-catalog.ts (or accessible via the runtime).
Recommended categories:
sequential-thinking — structured problem solvingmemory — persistent knowledge graphpdf — PDF text extractionpuppeteer — browser automationfilesystem, sqlite — file and database accessrailway — remote Railway MCP; supabase — database management and edge functionsWhen installing multiple servers (e.g., during omk init), OMK uses Promise.all for parallel setup.
Agents and hooks can also trigger bulk installs:
omk mcp doctor to verify each serverpost-init-mcp.sh runs non-blocking validation after initnpx -y <package> so no global install is required.${PROJECT_ROOT} and ${DB_PATH} placeholders in catalog entries; they are resolved at install time.mcp.json env values.omk mcp doctor after adding servers to confirm they start.startup_timeout_sec and network access.omk init when selecting additional MCP servers.omk mcp doctor --json for structured evidence.Launch nexu-io Open Design on localhost so OMK/Kimi can generate prototypes, decks, and design artifacts in a local web UI.
Slash command for safe OMK provider routing, doctor checks, and OAuth/login guidance without exposing secrets.
Review AdaptOrch, OMK, and similar DAG multi-agent orchestration frameworks. Use when assessing DAG node responsibility, dependency edges, worker write authority, fallback/retry/timeout/evidence gates, review/merge boundaries, or reproducible decision traces.
Diagnose agent, runtime, tool, hook, context, provider-routing, DAG, retry, fallback, and evidence-gate failures using an industrial automation feedback-control loop. Use when workflows oscillate, stall, lose context, misroute tools, or need setpoint/sensor/controller/actuator/disturbance/correction analysis.
Generate task-specific evidence contracts before a done/completed claim. Use for feature, bugfix, refactor, research, release, security, docs, or orchestration tasks that need changed files, non-empty diffs, test/build/typecheck results, citations, uncertainty, conflicting evidence, and final risk notes.
Persistent memory, recall, session replay, and memory-governance workflow adapted from rohitg00/agentmemory for OMK. Use when setting up agent memory, deciding what to remember, importing/replaying sessions, reducing repeated context, or auditing memory safety.