What runtime does ynab-mcp-server require?
It requires Node.js and npm. Build commands are `npm install` and `npm run build`.
@MCP-Mirror
Basic information
Mirror of
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"ynab-mcp-server": {
"command": "npx",
"args": [
"ynab-mcp-server"
],
"env": {
"YNAP_API_TOKEN": ""
}
}
}
}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 built with mcp-framework that provides tools for interacting with your YNAB budgets. It is intended for use with AI assistants to manage YNAB data via conversation.
Set the environment variable YNAB_API_TOKEN with your YNAB personal access token. Build the project (npm install && npm run build), then add the server to your MCP client configuration (e.g., Claude Desktop) using the command and path to the built index.js, or use npx after publishing.
It requires Node.js and npm. Build commands are `npm install` and `npm run build`.
You must set the environment variable `YNAB_API_TOKEN` with your personal access token from YNAB. This token is never sent directly to the LLM; it is stored privately in the environment.
The README provides configuration examples for Claude Desktop and links to other MCP clients at https://modelcontextprotocol.io/clients.
Yes, you can extend the server by adding new tools using the CLI command `mcp add tool <tool-name>` and referencing the YNAB OpenAPI specification.
The optional `KNOWLEDGE_DIR` and `KNOWLEDGE_FILE` environment variables allow you to specify where and how server knowledge (e.g., budget selections) is stored. Defaults to `data/server-knowledge.json` in the server directory.
A curated list of references for MLOps

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi
Painless E2E Automation for Mobile and Web

Model Context Protocol Servers
A search tool helps dev to solve the naming things problem.
Comments