Which integrations are available for this server?

Identifies Caddy gateway configuration, including rate limits and worker connections. Detects Celery queue usage for background job analysis. Identifies Django framework usage and its role in the API layer. Identifies Express.js framework usage and its role in the API layer. Identifies FastAPI framework usage, including worker count and concurrency. Identifies Flask framework usage and its role in the API layer. Identifies Gin framework usage and its role in the API layer. Detects GitHub as an external source integration in the project. Identifies Gunicorn worker configuration and its impact on concurrency. Detects Jira as an external source integration in the project. Detects Milvus vector store usage for storage analysis. Detects MongoDB database usage and its role in storage. Detects MySQL database usage and its role in storage. Identifies nginx gateway configuration, including rate limits and worker_connections. Detects OpenAI LLM usage and provides latency analysis as a potential bottleneck. Identifies PM2 worker configuration for concurrency analysis. Detects PostgreSQL database usage and its role in storage. Detects RabbitMQ queue usage for background job analysis. Detects Redis database usage and its role in storage. Detects Salesforce as an external source integration in the project. Detects Slack as an external source integration in the project. Detects SQLite database usage and its role in storage. Detects Stripe as an external source integration in the project. Detects Twilio as an external source integration in the project.

workflow-generator

Q: What can you do with this server?

This server scans software projects to generate visual workflow diagrams or structured JSON analyses of system architecture, concurrency, and bottlenecks. * generate_workflow: Scans a project directory and produces a WORKFLOW.html file — a dark-mode visual diagram showing components, communication paths, concurrency model, capacity estimates, and bottleneck analysis. Supports specifying output path, project directory, and auto-opening in a browser. * analyze_workflow: Scans a project and returns a structured JSON summary (no file written) covering detected framework, worker counts, capacity estimates, components (LLMs, storage, queues, external sources), concurrency primitives (semaphores, rate limits), and a ranked bottleneck analysis. * Multi-stack support: Works with Python (FastAPI, Flask, Django), Node.js (Express, Nest.js), Go, and mixed projects, while ignoring vendored/generated directories like node_modules or venv. * Wide component detection: API frameworks, gateways (nginx, Caddy, Traefik), LLM providers (OpenAI, Anthropic, etc.), vector stores, databases, queues, async primitives, worker/replica counts, and external integrations (Jira, Slack, Stripe, etc.). * Bottleneck reporting: Estimates throughput ceilings and concurrent I/O capacity, ranking bottlenecks from CRITICAL to LOW with mitigation notes.

by askuma

Overview Schema Related Servers Score Discussions

Python

Local

workflow-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.

Running workflow-generator against fastapi/full-stack-fastapi-template, from pip install to the generated diagram

(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.

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.

Related MCP server: composer-mcp

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, writes WORKFLOW.html, optionally opens in browser
analyze_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

Available Tools

2 tools

analyze_workflowA

Scan a project and return the workflow analysis as structured JSON (no file written). Returns: framework, workers, capacity estimates, detected components (LLM, storage, queues, external sources), concurrency primitives (semaphores, rate limits), and bottleneck ranking.

ParametersJSON Schema

Name	Required	Description	Default
`project_dir`	No	Absolute path to the project root.

TDQS

A4/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided. The description indicates read-only behavior ('no file written') and lists return fields, but lacks details on permissions, side effects, or other behavioral traits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

One sentence covering the main action and a bulleted list of returns. Front-loaded, efficient, no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with one simple parameter and no output schema, the description is fairly complete: it explains the return value exactly. Could be enhanced by more explicit guidance on sibling tool differentiation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% (the only parameter 'project_dir' is described in the schema as 'Absolute path to the project root.'). The description adds no additional meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Scan' and resource 'project', specifies output format 'structured JSON', and distinguishes from sibling 'generate_workflow' by noting no file is written.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implicitly suggests use for analysis vs. generation via 'no file written' and listing of analysis fields, but does not explicitly contrast with 'generate_workflow' or provide when-to-use/alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

generate_workflowA

Scan a project directory and generate WORKFLOW.html — a visual system workflow showing all components, their communication paths, concurrency model, concurrent request capacity, and bottleneck analysis. Works with Python (FastAPI, Flask, Django), Node.js (Express, Nest.js), Go, and mixed projects. Detects: API frameworks, gateways, LLM providers, vector stores, databases, queues, rate limits, async primitives, and worker counts.

ParametersJSON Schema

Name	Required	Description
`output_file`	No	Output path for WORKFLOW.html. Defaults to <project_dir>/WORKFLOW.html.
`project_dir`	No	Absolute path to the project root. Defaults to current working directory.
`open_browser`	No	Open the generated file in the default browser.

TDQS

A4.2/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. It discloses the tool scans directories, reads project files, and produces an HTML file. Could mention nondestructive nature or that it doesn't modify files, but current detail is sufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is a single paragraph that efficiently conveys purpose, supported projects, and detection capabilities. Every sentence adds value, though slightly lengthy; could be more structured but not wasteful.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, description thoroughly explains what the generated HTML contains and lists many detectable components. Provides complete understanding of tool's capabilities and output.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and parameters are well-described in schema. Description adds context that output file is a visual workflow, but doesn't enhance meaning beyond schema definitions for the three parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the tool scans a project directory and generates a visual workflow HTML file. Verb 'generate' with specific resource 'WORKFLOW.html' and explicit detection capabilities distinguish it from sibling 'analyze_workflow'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Description specifies supported project types (Python, Node.js, Go, mixed) and frameworks, giving clear context for when to use. However, lacks explicit 'when not to use' or comparison to alternatives like analyze_workflow.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

2 tool updatesJul 9, 2026
- First observedanalyze_workflow
- First observedgenerate_workflow

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.9/5.0

Disambiguation4/5

Both tools deal with workflow analysis, but they produce different outputs: analyze_workflow returns JSON, generate_workflow creates an HTML file. The descriptions make the distinction clear, though some conceptual overlap remains.

Naming Consistency5/5

Both tool names follow a consistent verb_noun pattern with snake_case, making them predictable and easy to understand.

Tool Count2/5

Only two tools for a 'workflow generator' server feels thin. The domain likely requires more operations (e.g., update, delete, validate) to be useful.

Completeness2/5

The server provides analysis and generation but lacks update, delete, or customization tools. Basic lifecycle coverage is missing, limiting agent workflows.

Maintenance

ActivitySlowing

ResponsivenessSyncing

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

Arketo
ai.arketo
Draw your app's architecture on a live canvas and flag the bottlenecks and security gaps.
Software Architecture Observability Security
1
Hokmah B
io.github.davidangularme
AI Agent with Architectural Memory. Impact analysis (free), tests and code from the graph (pro).
Knowledge & Memory Autonomous Agents AI & Machine Learning
52
ArchGraphOAuth
dev.archgraph
Code intelligence platform for AI agents. 20 tools for architecture, security & impact analysis.
Code Analysis Software Architecture Developer Tools
2
meeba-brain A
io.github.meemoprasad
Ground-truth code graph for your codebase: exact callers, callees, symbols & dependencies.
Code Analysis Developer Tools
51

Related MCP Servers

DependencyMCP Server
Code Analysis Developer Tools Code Execution
mkearl
A
license
A
quality
D
maintenance
Analyzes codebases to generate dependency graphs and architectural insights across multiple programming languages, helping developers understand code structure and validate against architectural rules.
Updated 2 years ago (2024-12-14 09:42 UTC)
6
60
20
MIT
composer-mcp
Software Architecture Developer Tools
OliverGrabner
A
license
Not graded
quality
D
maintenance
Visual architecture canvas that updates in real-time. Agents can build, read, and modify system design diagrams — services, databases, queues, APIs, entities — all linked to actual code paths in your repo.
Updated 5 months ago (2026-04-09 03:48 UTC)
94
4
MIT
Repository Architecture MCP
Code Analysis Software Architecture Developer Tools
vinit-devops
A
license
Not graded
quality
D
maintenance
Analyzes GitHub and local repositories to automatically generate visual architectural diagrams such as dependency graphs, class diagrams, and data flow diagrams.
Updated 10 months ago (2025-10-23 09:27 UTC)
2
MIT
archiet-xray
Code Analysis Software Architecture
Anioko
A
license
A
quality
C
maintenance
Extracts deterministic architecture maps from codebases for AI agents, enabling queries about blast radius, routes, security findings, and production readiness without sending code anywhere.
Updated 3 months ago (2026-06-11 14:17 UTC)
6
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/askuma/workflow-generator'

If you have feedback or need assistance with the MCP directory API, please join our Discord server

workflow-generator

What it produces

Codebase dependency graph

What it detects

Install

pip (CLI + MCP server)

Claude Code (skill)

MCP server (Claude Desktop, VS Code, Cursor, Zed, Windsurf, Continue)

Command line (standalone)

Example output (terminal)

Repo layout

License

Available Tools

TDQS

TDQS

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

DependencyMCP Server

composer-mcp

Repository Architecture MCP

archiet-xray

Latest Blog Posts

MCP directory API