What runtime does the server require?
The server is launched with the `node` command, so Node.js must be installed.
@raymondlowe
Basic information
An MCP server that knows how to edit the Roo Code custom modes file
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"roo-code-custom-mode-editor-mcp-server": {
"command": "npx",
"args": [
"https://github.com/raymondlowe/roo-code-custom-mode-editor-mcp-server"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list by running this server in a temporary sandbox using the button above.
A Model Context Protocol (MCP) server that provides tools to read and modify the Roo Code custom modes file (.roomodes). It eliminates the need to overwrite the file manually or attempt unreliable JSON diffs. Designed for developers using Roo Code who want a safe, structured way to manage custom mode definitions.
Run the server with npx https://github.com/raymondlowe/roo-code-custom-mode-editor-mcp-server. To integrate with Roo Code, add a server configuration entry to the MCP settings file pointing to the built index.js (the server has a build step via npm run build). The server communicates over stdio and exposes four tools: list_custom_modes, create_custom_mode, get_custom_mode_fields, and put_custom_mode_fields.
.roomodes file..roomodes.The server is launched with the `node` command, so Node.js must be installed.
It provides dedicated MCP tools to list, create, retrieve, and update custom modes, avoiding the need to overwrite the file or attempt unreliable JSON diffs.
All data is stored in the `.roomodes` file managed by Roo Code.
The server exposes four tools: `list_custom_modes`, `create_custom_mode`, `get_custom_mode_fields`, and `put_custom_mode_fields`. Each accepts specific parameters (e.g., slug, name, roleDefinition, customInstructions, groups).
Add a JSON object under `mcpServers` in the MCP settings file, specifying `"command": "node"

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP

SSH MCP server for AI agents: remote commands, file transfer, log search and server audits through OpenSSH.

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.
AptiBuild AI — Career Intelligence MCP Server Structured career decision scaffolding for AI agents. Provides personality-conditioned business idea generation, official BLS OEWS wage data, FRED labor market signals, and
Comments