MCP Code Flow Analyzer
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP Code Flow Analyzer trace the checkout flow from 'Add to Cart' button to database"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Code Flow Analyzer
An MCP (Model Context Protocol) server for analyzing and tracing business code flows across your codebase. Helps developers quickly understand the complete execution path of features from frontend to backend to database.
Features
Business Flow Tracing: Follow function calls from entry points through the entire codebase
Multi-Language Support: TypeScript, JavaScript
Smart Symbol Extraction: Automatically identifies functions, classes, variables, and imports
Call Graph Analysis: Builds and traverses function call relationships
Clickable Links: Generate VSCode and GitHub links for quick navigation
Flexible Configuration: YAML-based project configuration
Related MCP server: trazabilidad-mcp
Installation
npm install
npm run buildUsage
1. Configure Your Project
Create a .flowanalysis.yaml file:
version: '1.0'
project:
name: "my-project"
languages: [typescript]
rootPath: "."
sourceConfig:
include: ["src/**/*.ts"]
exclude: ["**/*.test.ts", "node_modules/**"]
analysisConfig:
maxCallDepth: 10
crossFileAnalysis: true
linkConfig:
vscode: { enabled: true }
github:
enabled: true
repository: "https://github.com/owner/repo"2. Configure in VSCode
{
"modelContextProtocol": {
"servers": {
"code-flow-analyzer": {
"command": "node",
"args": ["/path/to/mcp-server/dist/index.js"],
"env": { "PROJECT_ROOT": "${workspaceFolder}" }
}
}
}
}MCP Tools
traceBusinessFlow— Trace the complete execution path from an entry pointfindCallers— Find all functions that call a given functiongetProjectInfo— Get metadata about the project and analysis resultsgenerateFlowDiagram— Generate a Mermaid call graph diagram
Architecture
MCP Server (index.ts)
├── Project Config Manager
├── Code Analysis Manager
│ ├── Parser Factory
│ │ ├── TypeScript Parser
│ └── Symbol Table
├── Call Graph Analyzer
└── Link Generators
├── VSCode Link Generator
└── GitHub Link GeneratorDevelopment
npm run build # Build
npm run typecheck # Type check
npm run start # Run server
npm run dev # Build + runLicense
MIT
Available Tools
7 toolsfindCallersA
Find all functions that call a given function (reverse call graph)
Inputs: functionName (required).
generateFlowDiagramB
Generate a Mermaid call graph diagram for a function. Output renders in any markdown viewer (GitHub, VSCode, etc.).
Inputs: entryPoint (required), mode.
getCriticalPointsA
Get all critical operations (database reads/writes, HTTP requests, file I/O, exec calls) reachable from a function. This is the unique value of MCP vs raw search — it semantically classifies what each function actually DOES.
Inputs: entryPoint.
getProjectInfoB
Get project statistics: file count, symbol count, critical point count, languages detected
Inputs: no named parameters.
searchSymbolsA
Fuzzy search for symbols. Supports partial names, Chinese keywords ("登录", "支付"), and CamelCase prefixes.
Inputs: query (required).
traceBusinessFlowA
Trace the complete business flow chain from an entry point. Returns real call graph (parsed from function bodies), critical operations (DB/HTTP/file I/O), and a Mermaid diagram. Supports fuzzy matching and Chinese keywords like "登录"/"支付".
Inputs: entryPoint (required).
whoTriggersA
Reverse trace: find all entry points (controllers/public methods) that eventually call a given function. Answers questions like "what endpoints write to the order table?" by reverse-BFS from a critical operation.
Inputs: functionName (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 7 tools
Most tools have distinct purposes, but there is some overlap between findCallers and whoTriggers, and between generateFlowDiagram and traceBusinessFlow. Descriptions help differentiate, but agents might occasionally confuse them.
All tool names follow a consistent verb_noun pattern in camelCase (e.g., findCallers, generateFlowDiagram), making them predictable and easy to understand. 'whoTriggers' is slightly different but still verb-like.
With 7 tools, the server is well-scoped, covering essential code flow analysis functions without being overwhelming. Each tool serves a clear role.
The tool set covers search, call graph analysis, critical point detection, and visualization. Minor gaps exist, such as lacking a tool for comparing flows or detailed function metadata, but it sufficiently handles core analysis tasks.
Maintenance
Related MCP Connectors
Repository knowledge graph MCP server for codebase understanding and debugging.
The Cortex MCP server provides read-only access to real-time engineering context from the Cortex developer portal, allowing AI coding assistants to answer natural language questions about your organization's catalog (microservices, libraries, domains, teams, infrastructure), scorecards (engineering standards and best practices), initiatives (goals and deadlines), and Engineering Intelligence metrics. It includes tools for querying documentation, tracking personal entities, and accessing AI-assisted insights across the entire Cortex ecosystem.
2,000+ MCP servers read at source level. Know what one does before you connect. Free, no key.
A MCP server built for developers enabling Git based project management with project and personal…
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceAn MCP server that transforms codebases into intelligent, queryable knowledge bases, enabling AI assistants to perform semantic search, explore architecture, and analyze code relationships.166-
- FlicenseNot gradedqualityBmaintenanceMCP server that exposes code tracing capabilities including journey flows, HTTP seams, and findings from indexed projects, allowing AI assistants to query software architecture.-
- AlicenseAqualityDmaintenanceAn MCP server that extracts complete knowledge from any codebase — architecture, patterns, dependencies, API surface. Combines static analysis with AI-powered deep interpretation.8MIT
- FlicenseNot gradedqualityDmaintenanceMCP server for AI coding agents that builds a complete code structure graph and semantic vector index, enabling fast querying of code entities, relationships, and impact analysis.20 npm11-