mcpField
C
CloudArch Codeflow

CloudArch Codeflow

Local
web.cloud-arch.ruDeveloper Tools

About CloudArch Codeflow

Turn a TypeScript codebase into a live animated call-flow diagram on CloudArch

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"ru-cloud-arch-cloudarch-codeflow": {
"command": "npx",
"args": [
"-y",
"@cloud-arch/mcp-codeflow"
],
"env": {
"CLOUDARCH_API_KEY": "<CLOUDARCH_API_KEY>",
"CLOUDARCH_API_URL": "<CLOUDARCH_API_URL>"
}
}
}
}
Run commandnpx -y @cloud-arch/mcp-codeflow
Environment variables to set
CLOUDARCH_API_KEYSecretCloudArch API key (create one at https://web.cloud-arch.ru/workspace/api)
CLOUDARCH_API_URLAPI base URL override for self-hosted instances (default https://api.cloud-arch.ru)

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@cloud-arch/mcp-codeflow0.1.1

Tools

2

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
namestringNoName for the published diagram. Auto-generated from entry if omitted.
slugstringNoURL slug for the diagram. Auto-generated if omitted.
entrystringYesEntry point. Accepts: 'ClassName.methodName' (single class method), 'ClassName.*' (all public methods of class as scenarios), 'moduleName:funcName' (single function), 'moduleName:*' (all functions of module as scenarios). Multi-entry mode (globs or `additionalEntries`) renders one diagram with multiple scenarios you flip between in the player.
isPublicbooleanNoWhether the diagram is publicly visible. Defaults to false (your own code is usually private).
projectPathstringYesAbsolute path to a directory containing tsconfig.json (the root of the TS project to analyse).
additionalEntriesarrayNoExtra entries (same syntax as `entry`) rendered as additional scenarios on the same diagram. Use this when you want to compare or co-visualise several flows that share infrastructure.

Details

The maintainer has not added details yet. Check the README in the repository.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.