Workflow Generator MCP Server

Architecture diagram with concurrency capacity and bottleneck estimates from any codebase.

Local serverstdioPython

What is the Workflow Generator MCP server?

Workflow Generator MCP server exists for a simple reason — assistants are far more useful when they can act on Workflow Generator directly instead of describing what you should do. Architecture diagram with concurrency capacity and bottleneck estimates from any codebase.

What you get

Scan any project and generate WORKFLOW.html — a dark-mode visual system diagram showing every component, how they talk to each other, and where your throughput ceiling actually is.

What the assistant can call

Once Workflow Generator is connected, these are the calls the assistant has available:

  • generate_workflow — scans project, writes WORKFLOW.html, optionally opens in browser
  • analyze_workflow — returns structured JSON summary (no file written)
  • Section — What you get
  • Category — Examples
  • Gateways — nginx, Caddy, Traefik (with rate limits + worker_connections)
  • Databases — PostgreSQL, MySQL, MongoDB, SQLite, Redis
  • Queues — Celery, BullMQ, Kafka, RabbitMQ, RQ, AWS SQS
  • Workers — --workers N (uvicorn/gunicorn), replicas: (docker-compose), PM2 instances
  • Evaluation — TruLens, RAGAS, LangSmith

Setting it up

The server ships on PyPI as workflow-generator-mcp, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

Choosing this one

This sits in the database access group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Workflow Generator's toolset — generate_workflow, analyze_workflow, Section and 6 more — is a fair guide to whether it matches your workflow. It is maintained by askuma; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Workflow Generator's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 9 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Workflow Generator.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the workflow generator mcp server does with a few real requests.

Available tools

ToolWhat it does
generate_workflowscans project, writes WORKFLOW.html, optionally opens in browser
analyze_workflowreturns structured JSON summary (no file written)
SectionWhat you get
CategoryExamples
Gatewaysnginx, Caddy, Traefik (with rate limits + worker_connections)
DatabasesPostgreSQL, MySQL, MongoDB, SQLite, Redis
QueuesCelery, BullMQ, Kafka, RabbitMQ, RQ, AWS SQS
Workers--workers N (uvicorn/gunicorn), replicas: (docker-compose), PM2 instances
EvaluationTruLens, RAGAS, LangSmith

How to install the Workflow Generator MCP server

{
  "mcpServers": {
    "workflow-generator": {
      "command": "uvx",
      "args": ["workflow-generator-mcp"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Workflow Generator to generate workflow.
  • Use Workflow Generator to analyze workflow.
  • Use Workflow Generator to Section.

Frequently asked questions

It connects Workflow Generator to MCP-compatible AI assistants such as Claude and Cursor, exposing 9 tools (generate_workflow, analyze_workflow, Section, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Workflow Generator directly.