Nody
@olympeio
Nody provides a powerful MCP Composer for creating and managing custom MCP servers. It enables you to personalize each tool's name and description to add context, helping agents use them with fewer tokens. It manages the configurations and secrets of MCP servers in one secure pla
概要
What is Nody?
Nody is a visual interface for composing, editing, and managing MCP server tools into collections built around specific use cases. It allows extending the tool catalog by adding servers already deployed on NPM or UV public registries.
How to use Nody?
Use the centralized UI to configure agents once, customize tool names and descriptions, and maintain tool collections. No command-line invocation is described in the README.
Key features of Nody
- Customize tool names and descriptions for AI context.
- Configure agents once; no reconfiguration needed later.
- Encrypt and store secret values securely in a personal Vault.
- Monitor execution of collections and individual tools.
- Add servers from NPM or UV public registries to the catalog.
Use cases of Nody
- Compose MCP server tools into curated collections for specific tasks.
- Optimize AI agent context by renaming and re-describing tools.
- Centrally manage and update tool configurations without touching agents.
- Track whether tool collections and their tools are running correctly.
- Expand the available tool catalog with third‑party MCP servers.
FAQ from Nody
What is the MCP Composer in Nody?
It is a powerful visual interface for composing, editing, and managing MCP server tools into collections built around specific use cases.
How are secrets (API keys, tokens) stored?
Secret values are encrypted and stored securely; the encryption key is stored in a Vault accessible only by you.
Can I add servers from public registries?
Yes, you can extend your catalog by adding servers already deployed on NPM or UV public registries, and define the required configuration parameters and secrets.
Do I need to reconfigure agents when tool collections change?
No – configure agents once and maintain tool collections and their descriptions through the centralized UI; no need to reconfigure agents later.
How can I monitor tool execution?
Track the execution of your collections and tools to know whether they are running properly.
