Erstellt visuelle Architekturdiagramme und Schätzungen zu Concurrency-Bottlenecks aus jedem Codebase mittels statischer Analyse.
Auch bekannt als askuma/workflow-generator, workflow-generator, workflow-generator-mcp
- Stars
- 0
- Tools
- —
- Downloads, 30 Tage
- 365
- Neueste Version
- 0.5.0
- Letzter Commit
- 26. Okt. 2026
- Lizenz
- MIT
Was ist Workflow Generator MCP?
Erstellt visuelle Architekturdiagramme und Schätzungen zu Concurrency-Bottlenecks aus jedem Codebase mittels statischer Analyse.
Zusammenfassung generiert aus dem README des Projekts
Über Workflow Generator MCP server
Die Visualisierung der Systemarchitektur und das Identifizieren von Performance-Bottlenecks direkt aus einem Codebase ist das, was der Workflow Generator für Entwickler ermöglicht. Durch die Durchführung statischer Analysen an Projekten in Python, Node.js, Go, Java, Rust oder Ruby erstellt er einen umfassenden WORKFLOW.html Report. Dieser Report enthält ein visuelles Diagramm im Dark Mode, einen Dependency Graph sowie Schätzungen für Concurrency-Limits und den praktischen Durchsatz.
Nutzer können das Tool als eigenständiges CLI-Tool ausführen oder mit MCP-kompatiblen Clients wie Claude Desktop, Cursor, VS Code oder Zed verbinden. Der Server bietet zwei primäre Tools: generate_workflow zum Erstellen des vollständigen HTML-Reports und analyze_workflow zum Abrufen einer strukturierten JSON-Zusammenfassung. Um die Genauigkeit zu gewährleisten, werden Vendored-Verzeichnisse wie node_modules oder venv automatisch ignoriert. Für tiefere Einblicke kannst du ein Access Log bereitstellen, um reale Request-Zahlen über den Dependency Graph zu legen. Das Tool generiert sogar ein k6 Load-Test-Script, um die Schätzungen der statischen Analyse mit realen Messwerten zu verifizieren.
Was du damit machen kannst
- 1Visuelle Systemdiagramme erstellenLass die KI eine visuelle Darstellung davon erstellen, wie alle Komponenten in deinem Projekt interagieren.
- 2Concurrency-Limits schätzenErmittle die maximale Anzahl an gleichzeitigen Requests, die deine aktuelle Architektur verarbeiten kann.
- 3Performance-Bottlenecks identifizierenFinde die spezifischen Layer in deinem Stack, die den Durchsatz deines Systems limitieren.
- 4Codebase-Dependencies mappenVisualisiere die Beziehungen zwischen Source-Files und externen Services wie Datenbanken oder LLM-Providern.
Geschrieben aus dem README des Projekts. Jeder Use Case wurde gegen ein Zitat daraus geprüft.
So installierst du Workflow Generator MCP
Formate geprüft am 10. Nov. 2026Zu Cursor hinzufügenZu Goose hinzufügenWorkflow Generator MCP in Claude Code installieren
$ claude mcp add workflow-generator -- uvx workflow-generator-mcpWorkflow Generator MCP in Cursor installieren
~/.cursor/mcp.json
{
"mcpServers": {
"workflow-generator": {
"command": "uvx",
"args": [
"workflow-generator-mcp"
]
}
}
}Workflow Generator MCP in VS Code installieren
.vscode/mcp.json
{
"servers": {
"workflow-generator": {
"type": "stdio",
"command": "uvx",
"args": [
"workflow-generator-mcp"
]
}
}
}Workflow Generator MCP in VS Code CLI installieren
$ code --add-mcp '{"name":"workflow-generator","type":"stdio","command":"uvx","args":["workflow-generator-mcp"]}'Workflow Generator MCP in Claude Desktop installieren
claude_desktop_config.json
{
"mcpServers": {
"workflow-generator": {
"command": "uvx",
"args": [
"workflow-generator-mcp"
]
}
}
}Workflow Generator MCP in Codex installieren
$ codex mcp add workflow-generator -- uvx workflow-generator-mcpWorkflow Generator MCP in Codex config.toml installieren
~/.codex/config.toml
[mcp_servers.workflow-generator] command = "uvx" args = ["workflow-generator-mcp"]
Workflow Generator MCP in Gemini CLI installieren
$ gemini mcp add -s user workflow-generator uvx -- workflow-generator-mcpWorkflow Generator MCP in Gemini settings.json installieren
~/.gemini/settings.json
{
"mcpServers": {
"workflow-generator": {
"command": "uvx",
"args": [
"workflow-generator-mcp"
]
}
}
}Automatisierte Checks
Geluften am 14. Nov. 2026Vollständiger Bericht →Unsere automatisierten Checks bestanden. Das ist kein Security-Audit: Lies den Code und gib dem Server nur den minimal notwendigen Zugriff. Wie die Checks funktionieren
- Source Repository verknüpft und erreichbaraskuma/workflow-generator is public and reachablegithub.com/askuma/workflow-generator ↗Bestanden
- Paket nennt dieses Repository als Quelleworkflow-generator-mcp names askuma/workflow-generator as sourcepypi.org/project/workflow-generator-mcp/ ↗Bestanden
- Build-Provenienz (Sigstore-Attestierung)Sigstore attestation for workflow-generator-mcppypi.org/project/workflow-generator-mcp/ ↗Bestanden
- Open Source Lizenz (OSI)MITspdx.org/licenses/MIT.html ↗Bestanden
- Commit oder Release im letzten JahrLast commit or release 2026-10-26github.com/askuma/workflow-generator ↗Bestanden
- OpenSSF ScorecardNicht geprüft
- Package-Name ähnelt keinem populären PackageNo popular package one edit away from workflow-generator-mcpBestanden
- Keine kritischen Advisories im Paket oder seinen Abhängigkeiten29 resolved dependencies checked; no critical advisoryosv.dev ↗Bestanden
- Keine versteckten Anweisungen an das Modell0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersBestanden
- Destruktive Tools sind markiertNicht geprüft
- Remote-Endpoint beantwortet den MCP-HandshakeNicht geprüft
README
Auf GitHub ansehenworkflow-generator
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.
Works with Python, Node.js, Go, Java, Rust, Ruby, and mixed projects. No external dependencies for the core scanner.
Vendored and generated directories (node_modules, venv, site-packages, dist, …) are never scanned,
and capacity figures are clearly labeled as static-analysis estimates.
Live demo → — generated from fastapi/full-stack-fastapi-template, unmodified.

(real CLI output, unscripted — static screenshot if you'd rather not autoplay)
What it produces
Every generated page contains:
| Section | What you get |
|---|---|
| Stat row | Workers · Concurrent I/O ceiling · Semaphore limit · Rate limit · Practical throughput |
| Architecture diagram | Layered flow: external sources → gateway → API → queues → AI → storage |
| Data flow cards | Write path, read/query path, background jobs — inferred from what's detected |
| Concurrency table | Every layer: model · ceiling · limiting factor |
| Bottleneck analysis | Ranked CRITICAL → LOW with mitigation notes |
| Codebase dependency graph | Force-directed module/import graph — click a node to isolate its neighbors, hover for file details. Import-direction edges are clearly distinguished from real observed traffic (see below) |
| Guided tour | Spotlight walkthrough of every section, shown automatically the first time a report is opened; replay anytime with the ? button |
Codebase dependency graph
Every source file (Python, JS/TS, Go, Java, Rust, Ruby) becomes a node; every real import becomes
an edge — resolved with a language-appropriate parser (Python's ast module, regex for JS/TS/Go/
Java/Rust/Ruby), not guessed. Files that match an already-detected component (an LLM call, a
database client, a queue) get an edge to that component too, so you can see exactly which files
talk to Redis, OpenAI, etc. Large repos (350+ files) are automatically aggregated into
directory-level nodes so the graph stays readable; override with --graph-detail files or
--graph-detail dirs.
Test files (tests/, test_*.py, conftest.py, *.spec.ts, *_test.go, …) get their own
Test Graph section below the main one, showing which modules and services each test reaches.
Fixtures and test doubles name every service they exercise, so keeping them in the main graph
buries the real dependency structure under service edges.
Both sections have a Flow | Graph toggle over the same nodes and edges. Flow (the default up to 80 nodes) is a left-to-right layered diagram: columns are dependency depth from the sources (HTTP entry and files nothing imports), every detected service is its own node in the last column, and import cycles are drawn dashed. Graph is the force-directed view. Moving dots show data going both ways: a filled dot is the call/request, a hollow dot the return/response. On graphs with more than 60 edges, only the paths of the clicked or hovered node animate. Search, "hide isolated" and the selected node are shared between the two views.
The older layered Full System Architecture diagram is collapsed by default, since the Architecture Map covers the same ground.
By default the graph only shows what the code says (import direction, static "this file calls
Redis"), which is honest but not the same as real traffic. Pass --access-log /path/to/access.log
(any combined/common log format) to overlay real observed request counts onto the HTTP-entry
edges — and the generated report includes a ready-to-run k6 load-test script
covering up to 5 detected routes, so the "Practical throughput" number can be checked against a
real measurement instead of only a static-analysis estimate.
What it detects
| Category | Examples |
|---|---|
| API frameworks | FastAPI, Flask, Django, Express, Nest.js, Gin |
| Gateways | nginx, Caddy, Traefik (with rate limits + worker_connections) |
| LLM providers | OpenAI, Anthropic Claude, Cohere, AWS Bedrock |
| Vector stores | Qdrant, Pinecone, Weaviate, ChromaDB, pgvector, FAISS, Milvus |
| Databases | PostgreSQL, MySQL, MongoDB, SQLite, Redis |
| Queues | Celery, BullMQ, Kafka, RabbitMQ, RQ, AWS SQS |
| Async primitives | asyncio.Semaphore, run_in_executor, asyncio.gather, asyncio.Lock |
| Workers | --workers N (uvicorn/gunicorn), replicas: (docker-compose), PM2 instances |
| External sources | Jira, Azure DevOps, Slack, GitHub, Stripe, Salesforce, Twilio |
| Evaluation | TruLens, RAGAS, LangSmith |
Install
pip (CLI + MCP server)
pip install workflow-generator-mcp
workflow-generator . WORKFLOW.html # CLI: scan and write the report
workflow-generator-mcp # stdio MCP server
With pip installed, any MCP host config reduces to:
{
"mcpServers": {
"workflow-generator": { "command": "workflow-generator-mcp" }
}
}
Claude Code (skill)
mkdir -p ~/.claude/skills
git clone https://github.com/askuma/workflow-generator.git ~/.claude/skills/workflow-generator
Then in any Claude Code session:
/workflow-generator
/workflow-generator /path/to/project
MCP server (Claude Desktop, VS Code, Cursor, Zed, Windsurf, Continue)
1. Install the dependency:
pip install mcp
2. Add to your MCP host config (replace ~ with your actual home path):
~/Library/Application Support/Claude/claude_desktop_config.json (Mac)
%APPDATA%\Claude\claude_desktop_config.json (Windows)
{
"mcpServers": {
"workflow-generator": {
"command": "python3",
"args": ["~/.claude/skills/workflow-generator/mcp/server.py"]
}
}
}
.vscode/mcp.json
{
"servers": {
"workflow-generator": {
"type": "stdio",
"command": "python3",
"args": ["~/.claude/skills/workflow-generator/mcp/server.py"]
}
}
}
~/.cursor/mcp.json
{
"mcpServers": {
"workflow-generator": {
"command": "python3",
"args": ["~/.claude/skills/workflow-generator/mcp/server.py"]
}
}
}
.zed/settings.json
{
"context_servers": {
"workflow-generator": {
"command": {
"path": "python3",
"args": ["~/.claude/skills/workflow-generator/mcp/server.py"]
}
}
}
}
~/.windsurf/mcp_config.json
{
"mcpServers": {
"workflow-generator": {
"command": "python3",
"args": ["~/.claude/skills/workflow-generator/mcp/server.py"]
}
}
}
3. Restart your tool, then ask:
generate a workflow diagram for this project
how many concurrent requests can this handle?
show me the system architecture
MCP tools exposed:
generate_workflow— scans project, writesWORKFLOW.html, optionally opens in browseranalyze_workflow— returns structured JSON summary (no file written)
Command line (standalone)
No install needed beyond Python 3.8+:
python3 ~/.claude/skills/workflow-generator/scripts/analyze.py . ~/WORKFLOW.html
# then open ~/WORKFLOW.html
Optional flags:
--access-log /path/to/access.log # overlay real request counts onto the dependency graph
--graph-detail auto|files|dirs # force file-level or directory-level graph nodes (default: auto)
Example output (terminal)
Written: /your/project/WORKFLOW.html
Framework: FastAPI · Workers: 8 · Concurrent I/O: ~800
Practical throughput: ~50–200 req/min
Bottleneck: OpenAI (LLM latency 3–30s per call)
Gateway: nginx · 2 rate limit zone(s)
LLM: OpenAI · eval: TruLens RAG Triad
Storage: Qdrant, Redis
External sources: Jira, Azure DevOps, Slack
Repo layout
workflow-generator/
├── SKILL.md ← Claude Code skill definition
├── INSTALL.md ← detailed per-platform install guide
├── workflow_generator_mcp/
│ ├── analyze.py ← core scanner + HTML renderer (stdlib only)
│ └── server.py ← MCP stdio server (package form)
├── scripts/
│ └── analyze.py ← thin compatibility shim -> workflow_generator_mcp/analyze.py
├── tests/ ← pytest suite for the scanner
├── mcp/
│ ├── server.py ← MCP stdio server
│ └── requirements.txt ← pip install mcp
└── copilot/
├── index.js ← GitHub Copilot Extension (Express)
├── package.json
└── openai_function.json
License
MIT
Workflow Generator MCP Fragen
Wie füge ich Workflow Generator MCP zu Claude Code hinzu?
Führe claude mcp add workflow-generator -- uvx workflow-generator-mcp in deinem Terminal aus. Füge --scope user hinzu, damit der Server in jedem Projekt verfügbar ist.
Wie füge ich Workflow Generator MCP zu Cursor hinzu?
Öffne ~/.cursor/mcp.json und füge den Server unter mcpServers hinzu, mit der Cursor-Config aus dem Installationsabschnitt oben.
Welche Programmiersprachen werden unterstützt?
Der Scanner funktioniert mit Python, Node.js, Go, Java, Rust, Ruby und gemischten Projekten.
Werden node_modules oder virtuelle Umgebungen gescannt?
Nein, Vendored- und generierte Verzeichnisse wie node_modules, venv und site-packages werden vom Scan ausgeschlossen.
Wie genau sind die Kapazitätsangaben?
Die Kapazitätsangaben werden als Schätzungen basierend auf der statischen Analyse bereitgestellt.
Kann ich echte Traffic-Daten über den Graphen legen?
Ja, du kannst einen Pfad zu einem Access Log übergeben, um die tatsächlich beobachteten Request-Zahlen über die HTTP-Entry-Edges zu legen.