Prototype · Preview: every server in the official registry, synced every 30 minutes. Reviews and accounts come in a later step.
PopNx MCPMCP servers for people who use AI · explained in plain words

Onboardmap

by CloudCorpRecordsversion 0.1.0i★ –iRuns on your computer
Registry nameio.github.CloudCorpRecords/onboardmap

Install

Overview

Description from the maker (original English)

Build a newcomer map from supplied repo facts: areas, entry points, tests, and owners.

PopNx MCP’s three pillars

These three are never merged into one score: opinions, measurements and popularity are different things.

What you can do with it

We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.

  • Connection: Runs on your computer
  • Transport: stdio
  • Category: Other

Install

Pick the AI app you use, then copy the settings.

Before you install

  • Basic checks: 1 of 1 passed
  • Runs on your computer with your user’s permissions (files, network, apps).
  • The registry lists no key to fill in.

You need

  • npmNode.js installed (for the npx command)

Which app do you use?

Pick your app above. We remember it, so next time the button says “Install in …”.

Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json

{
  "mcpServers": {
    "onboardmap": {
      "command": "npx",
      "args": [
        "-y",
        "@reneturcios/onboardmap",
        "mcp"
      ]
    }
  }
}

Run this in your terminal

claude mcp add onboardmap -- npx -y @reneturcios/onboardmap mcp

Open in Cursor

Or copy the settings yourself

Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "onboardmap": {
      "command": "npx",
      "args": [
        "-y",
        "@reneturcios/onboardmap",
        "mcp"
      ]
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

Open in VS Code

Or copy the settings yourself

Paste into .vscode/mcp.json in your project

{
  "servers": {
    "onboardmap": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@reneturcios/onboardmap",
        "mcp"
      ]
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.

Your choice stays on this device in a cookie; no account needed.

These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.

What it can do

Runs on your computer; the tool list appears in your AI app after you install it.

Basic checksi

We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 6, 2026

  • ✓ Pass

    Maker matches the repo

    The registry name was verified with the GitHub account CloudCorpRecords, which owns the repo

  • … Not checked yet

    Still maintained

    We have not read this repo from GitHub yet

  • … Not checked yet

    Has a licence

    We have not read this repo from GitHub yet

  • – Not applicable

    Endpoint responds

    This one runs on your computer; there is no internet endpoint

  • – Not applicable

    Sign-in with OAuth

    Runs on your computer and uses local settings instead

  • … Not checked yet

    No hidden instructions in tool descriptions

    Runs on your computer; we can only read tool lists from internet endpoints

Compared with others in Otheri

  • More stars than 0% of the other 32415 servers in this category
  • Published to the registry more recently than 91% of the other 32415 servers in this category
  • Basic checks equal to or better than 100% of the other 32415 servers in this category

Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.

Common questions

Is Onboardmap safe?

It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.

What keys or codes does it need?

The registry does not list a required key, though some servers ask you to sign in on first use.

Does it run on my computer or in the cloud?

It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).

Is it still maintained?

The GitHub repo last changed –, and the latest version (0.1.0) reached the registry 3 days ago.

Which apps can use it?

Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js, Docker on your computer.

What can I use instead?

In the same category: Spec Driven Development, Remote Desktop Commander, Safe Fetch

Alternatives

Servers in the same category from other makers, sorted by stars.

Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi

Spec Driven Development

by formulahendry

MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.

Runs on your computer★ 440MITUpdated 14 months ago
Install

Remote Desktop Commander

by desktop-commander

Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.

Runs in the cloud★ 211Updated yesterday
Install

Safe Fetch

by Sanoy24

MCP server for fetching URLs, safe against SSRF, DNS rebinding, and redirect-to-internal attacks.

Runs on your computerUpdated today
Install

README from the maker

Open the README

Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.

onboardmap

Joining a codebase is mostly a geography problem: where does the program start, where do the tests live, how do you run just one of them, and who do you ask about a given corner? onboardmap draws that map from facts you already have. You supply the repository's file paths, the paths you consider entry points, the command that runs the tests if you want it recorded, and a set of path prefixes with the person or team that owns each one. onboardmap hands back the map: the files grouped into areas, the entry points that actually exist, the ones you named that are missing, every test file, every file nobody owns, and the tallies. It never opens the repository; the map comes from the supplied facts only.

A file's area is the first segment of its path, so everything under src/ belongs to the src area and a file sitting at the top level, with no slash in its path, belongs to an area literally called (root). Areas come back sorted ascending, and each one reports how many files it holds, how many of those are tests, which entry points live inside it in the order you named them, and the distinct owners of its files, also sorted.

A file counts as a test file in two ways. Its basename — the part after the last slash — may contain .test. or .spec., as in parser.test.ts. Or one of its directory segments may be exactly test, tests, __tests__, or spec, as in tests/helpers/setup.ts. A name that merely starts with the letters t-e-s-t, like testfoo.ts or a folder called testing, matches neither rule and is not a test file.

Ownership is prefix matching with a longest-match rule. A prefix owns a file when the file equals the prefix, when the prefix ends with a slash and the file starts with it, or when the file starts with the prefix plus a slash — so src owns src/app.ts but not srcfoo/app.ts. When two prefixes both match, the longer one wins, which lets a broad owner cover a whole tree while a narrower prefix carves out one subtree for someone else. Files no prefix matches are listed as unowned.

An entry point you name that is not in the file list is not an error — building a map for a newcomer is exactly when you want to learn that the documented starting point does not exist. Found entry points are echoed in your order, missing ones are reported separately in your order, and the entry-point count in the tallies counts only the found ones. The test command is echoed word for word, an empty string included, or reported as null when you leave it out.

Malformed input — a missing, empty, or non-array file list, a non-string or empty file path, a bad entry-point list, a non-string test command, or an owners map with an empty key or an empty or non-string value — is a validation error naming the offending path, with no partial result. Two files with the same path are an error naming the duplicated path. Unknown extra fields are ignored.

CLI

npx @reneturcios/onboardmap map --input args.json

npx @reneturcios/onboardmap --version

args.json contains the full arguments object:

{

"files": [ "README.md", "src/index.ts", "src/parser.ts", "src/parser.test.ts", "tests/helpers/setup.ts", "docs/guide.md" ], "entry_points": ["src/index.ts", "src/main.ts"], "test_command": "npm test", "owners": { "src": "alice", "docs": "bob" } }

The map is printed as JSON:

{

"areas": [ { "area": "(root)", "files": 1, "tests": 0, "entry_points": [], "owners": [] }, { "area": "docs", "files": 1, "tests": 0, "entry_points": [], "owners": ["bob"] }, { "area": "src", "files": 3, "tests": 1, "entry_points": ["src/index.ts"], "owners": ["alice"] }, { "area": "tests", "files": 1, "tests": 1, "entry_points": [], "owners": [] } ], "entry_points": ["src/index.ts"], "missing_entry_points": ["src/main.ts"], "test_files": ["src/parser.test.ts", "tests/helpers/setup.ts"], "unowned_files": ["README.md", "tests/helpers/setup.ts"], "test_command": "npm test", "counts": { "files": 6, "test_files": 2, "areas": 4, "entry_points": 1, "unowned": 2 } }

Exit codes: 0 on success, 1 on a runtime error (including an unreadable or invalid input file, or invalid input), 2 on a usage error.

MCP server

npx -y @reneturcios/onboardmap mcp

MCP client config:

{

"mcpServers": { "onboardmap": { "command": "npx", "args": ["-y", "@reneturcios/onboardmap", "mcp"] } } }

Tools
  • build_onboard_map — Build a newcomer map from caller-supplied repository facts: files grouped into areas, entry points, where the tests live, and who owns what.
  • files (array of strings, required, at least 1 item) — repository file paths, repo-relative, in the caller's order
  • entry_points (array of strings, optional) — paths the caller names as entry points; absent means none
  • test_command (string, optional) — command that runs the test suite, echoed into the map
  • owners (object, optional) — map from path prefix to owner name; absent means no owners

Returns {areas, entry_points, missing_entry_points, test_files, unowned_files, test_command, counts}, where areas holds one {area, files, tests, entry_points, owners} per area, and counts is {files, test_files, areas, entry_points, unowned}.

Docker

docker run -i ghcr.io/cloudcorprecords/onboardmap

docker run --rm -v "$PWD:/w" ghcr.io/cloudcorprecords/onboardmap map --input /w/args.json

Development

npm install

npm run build # tsc -> dist/ npm test # tsx --test test/*.test.ts (pure local, no network) npm run dev # run the CLI from source

License

MIT — Copyright (c) 2026 Rene Turcios

Ask PopNx