data-ai MCP Server
Model Context Protocol server that enables AI agents to discover, create, and execute complex, multi-step workflows defined in simple YAML files. Allow your AI agents to better organize their tool usage and provide a more structured way to handle complex multi-step tasks.
Discovered via github-topic:mcp-server and last synced 3mo ago.
1. Install the package
bunx @cyanheads/workflows-mcp-server@latest
2. Add to claude_desktop_config.json
{
"mcpServers": {
"-cyanheads-workflows-mcp-server": {
"command": "npx",
"args": [
"@cyanheads/workflows-mcp-server"
]
}
}
}Config file location: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) / %APPDATA%\Claude\claude_desktop_config.json (Windows)
Transport: `stdio` or `http`.
Description
Port for HTTP server.
List all permanent workflows in the index, with optional category and tag filters.
Auth mode: `none`, `jwt`, or `oauth`.
Retrieve a complete workflow definition by name, with global instructions prepended.
Log level (RFC 5424).
Write a new permanent workflow YAML to the library.
Enable [OpenTelemetry instrumentation](https://github.com/cyanheads/mcp-ts-core/tree/main/docs/telemetry) (spans, metrics, completion logs).
Write a temporary one-shot workflow, indexed but excluded from list results.
Purpose
Description
Absolute or relative path to the workflows root directory.
Path to the global instructions markdown file. Derives from `WORKFLOWS_DIR` when not set.
Milliseconds to debounce filesystem change events before rebuilding the index.