mcpField
N
Nody

Nody

Local
github.com/olympeioAI & Agents11Updated 74w ago

About Nody

Nody is a platform for composing and managing MCP server tools into use-case-specific collections for AI agents. It centralizes tool customization, configuration, secrets, and execution monitoring; its clients load collection tools through a runtime connected to a central orchestrator.

Key features

  1. 01Visually compose and manage tool collections
  2. 02Customize tool names and descriptions
  3. 03Centralize agent tool configuration
  4. 04Encrypt and store secret values
  5. 05Monitor collection and tool execution
  6. 06Add servers from NPM or UV registries

Use cases

  1. 01Tailor tool names and descriptions to an agent's use case
  2. 02Manage server configuration and secrets centrally
  3. 03Monitor whether tools in a collection run properly
  4. 04Add NPM or UV servers to a tool catalog

MCP support

Nody provides an MCP Composer and client runtime that exposes tools from configured collections to MCP clients. Clients retrieve collection details from a centralized orchestrator and load the customized tools.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"nody": {
"command": "npx",
"args": [
"-y",
"@olympeio/nody-vmcp"
],
"env": {
"NODY_CLIENT_ID": "<NODY_CLIENT_ID>",
"NODY_USER_KEY": "<NODY_USER_KEY>"
}
}
}
}
Run commandnpx -y @olympeio/nody-vmcp
Environment variables to set
NODY_CLIENT_ID
NODY_USER_KEYSecret

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@olympeio/nody-vmcp

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Nody

Nody
One MCP Server to TOOL them all!

Nody is a developer-first platform for managing and deploying Model Context Protocol (MCP) servers and toolsets. Nody technology maintains the tools collections in a knowledge graph. Nody clients exposing tools to your AI Agents request the knowledge graph to discover what tool should ben installed and exposed.

Overview

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 place, making it easier to deploy and scale your AI toolsets efficiently.

Features

  • MCP Composer
    A powerful visual interface for composing, editing, and managing MCP server tools into collections built around specific use cases.

  • Tool Customization
    Customize tool names and descriptions to optimize context for AI agents based on your desired use cases.

  • Configure Agents Once
    Configure agents once and maintain tool collections and their descriptions through a centralized UI. No need to reconfigure agents later.

  • Secure Configuration Storage
    Secret values (API keys, tokens, etc.) are encrypted and stored securely. The encryption key is stored in a Vault accessible only by you.

  • Monitor Execution of Collections
    Track the execution of your collections and tools to know whether they're running properly.

  • Add Servers to Catalog
    Extend your catalog by adding servers already deployed on NPM or UV public registries. Define the required configuration parameters and secrets to run them securely.

How to Use

Once your Nody client is composed at Nody, click the Run it button to get installation instructions.

Example of a Nody client configuration to add to your favorite MCP client:

{
  "mcpServers": {
    "<Nody client name>": {
      "command": "npx",
      "args": [
        "-y",
        "@olympeio/nody-vmcp@latest"
      ],
      "env": {
        "NODY_CLIENT_ID": "<Nody client id>", // REQUIRED, your Nody client ID
        "NODY_USER_KEY": "<your very own secret encryption key>" // OPTIONAL, used when authenticated, required to decrypt secret values
      }
    }
  }
}

This starts the Nody client and loads the list of tools included in the collection with the configured customizations.

Requirements

The Nody VMCP package is an NPM package that requires Node.js 18+ to work properly.

Check your installed Node.js version with:

node --version

Download the latest version from the official website.

Roadmap

Planned features and improvements:

  • Enterprise Security
    Use your enterprise vault to store encryption keys. Enterprise-grade governance for AI tooling.

  • Collection Sharing (Templates)
    Publish and share MCP configurations through public or private repositories with attribution.

  • Code Your Own Tools
    Write and test your tools directly in Nody without needing to publish them on NPM, UV, or Docker.

  • Integration of Existing APIs
    Integrate APIs from your IT landscape into AI agents by wrapping them as MCP tools and composing them into collections.

  • Add Docker and Local Servers
    Add servers not deployed on NPM or UV registries, including local or Docker-based servers, and use them in the MCP Composer.

Architecture

Nody clients are lightweight runtimes built on top of the Olympe Technology: a knowledge graph stored in a dedicated graph database describes the compositions of tools in collections, custom MCP and names and descriptions overrides. Nody Clients are distributed and connected to a centralized orchestrator providing required graph portions for the execution of the tools. Updates on tools and collections are notified in real time thanks to our event driven distributed archtitecture.

Links

License

Copyright (C) Olympe S.A. - All Rights Reserved Unauthorized copying of any of the files contained in this project, via any medium is strictly prohibited Proprietary and confidential

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.