Local MCP server for agent skill files that can detect IDE layouts, list/read/write skills, lint and validate formats, convert between IDE skill formats, and diff local skills against cloud versions. It also provides optional cloud sync and search via ModelBound.
From the registry: Local-first MCP server for agent skills. Validate, lint, diff, and convert across IDEs.
Please install the `modelbound-mcp` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Node.js and npm** — Install Node.js and npm so you can run the server with npx or install it globally. (https://nodejs.org/)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","modelbound-mcp"]
- optional environment variables:
- `MODELBOUND_API_KEY`: Optional API key for ModelBound cloud features such as cloud.pullSkill, cloud.pushSkill, cloud.search, cloud.listSkills, cloud.resourceTree, cloud.installMarketplaceSkill, and optimization.health. Without it, local-only tools still work. (example: `<your-modelbound-api-key>`)
Note: The server runs locally over stdio. The simplest portable setup is `npx -y modelbound-mcp`. Global install (`npm i -g modelbound-mcp`) is available but not necessary.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.MODELBOUND_API_KEYrequiredAPI key used to enable cloud tools and access ModelBound cloud services.Real-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection.
Persistent codebase knowledge graph. Survives session restarts and context compaction.
Validate oh-my-posh configurations and segment snippets against the official schema.