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

Types2docs

by CloudCorpRecordsversion 0.1.0i★ –iRuns on your computer
Registry nameio.github.CloudCorpRecords/types2docs

Install

Overview

Description from the maker (original English)

Render a markdown API reference from caller-supplied TypeScript type declarations.

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": {
    "types2docs": {
      "command": "npx",
      "args": [
        "-y",
        "@reneturcios/types2docs",
        "mcp"
      ]
    }
  }
}

Run this in your terminal

claude mcp add types2docs -- npx -y @reneturcios/types2docs mcp

Open in Cursor

Or copy the settings yourself

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

{
  "mcpServers": {
    "types2docs": {
      "command": "npx",
      "args": [
        "-y",
        "@reneturcios/types2docs",
        "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": {
    "types2docs": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@reneturcios/types2docs",
        "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 32380 servers in this category
  • Published to the registry more recently than 91% of the other 32380 servers in this category
  • Basic checks equal to or better than 100% of the other 32380 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 Types2docs 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, Dechonet MCP

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

Dechonet MCP

by node-man

30 security tools for AI agents: phishing links, exposure maps, DNS, SSL, PQC, history, pivots.

Computer or cloudUpdated 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.

types2docs

Documenting a TypeScript API usually means keeping a markdown reference in step with the types by hand, and the two drift apart. types2docs takes the other route: you supply the declaration facts you already have — each declaration's name, whether it is an interface, a type alias, an enum, or a function, its doc comment, and the kind-specific payload (the members, the alias's right-hand side, or the function signature) — and it renders the reference from those facts alone, in one pinned layout. Nothing is invented and nothing is reworded: every string in the document comes from your input, verbatim.

The layout never varies. The document opens with a # title line — "API Reference" unless you supply a title — followed by one section per declaration, in the order you supplied them. Each section is a ## heading with the declared name, the doc text as its own paragraph when one is present, a Kind: line, and then the kind body. An interface renders as a table with one row per member — member name, type text, and whether the member is required (yes when optional is absent or false, no when it is true) — followed by one line per documented member collecting its doc comment. An enum renders one line per member, with = when a value is present and the member's doc comment appended when it has one. An interface or enum with no members renders the single line (no members). A type alias and a function each render as a fenced ts block: for an alias, type = ; for a function, the signature exactly as supplied. Paragraphs and sections are separated by exactly one blank line, and the document ends with exactly one trailing newline. Alongside the markdown, the result carries counts: how many declarations were supplied, one tally per kind, and how many members the interfaces and enums hold in total.

The kind rules are structural, and breaking one is a validation error, not a rendering choice. members is required for interfaces and enums and forbidden for type aliases and functions. definition is required for a type alias and forbidden for every other kind; signature is required for a function and forbidden for every other kind. Inside members, type is required for interface members and forbidden for enum members, value belongs to enum members only, and optional is forbidden on enum members. Two declarations with the same name, or two members with the same name inside one declaration, are errors too. Every validation error names the offending path — for example types[1].members[0].type is required for interface members — and no partial document is produced. Unknown extra fields are ignored, including inside declarations and members.

CLI

npx @reneturcios/types2docs render --input args.json

npx @reneturcios/types2docs --version

args.json contains the full arguments object:

{

"title": "Widget API", "types": [ { "name": "Widget", "kind": "interface", "doc": "A widget in the catalogue.", "members": [ { "name": "id", "type": "string", "doc": "Unique identifier." }, { "name": "label", "type": "string", "optional": true } ] }, { "name": "WidgetId", "kind": "type", "definition": "string & { readonly brand: \"WidgetId\" }" }, { "name": "Colour", "kind": "enum", "members": [ { "name": "Red", "value": "\"red\"" }, { "name": "Blue", "value": "\"blue\"", "doc": "The calm one." } ] }, { "name": "makeWidget", "kind": "function", "signature": "function makeWidget(id: WidgetId): Widget" } ] }

The render is printed as JSON:

{

"markdown": "# Widget API\n\n## Widget\n\nA widget in the catalogue.\n\nKind: interface\n\n| Member | Type | Required |\n| --- | --- | --- |\n| id | string | yes |\n| label | string | no |\n\n- id — Unique identifier.\n\n## WidgetId\n\nKind: type\n\nts\ntype WidgetId = string & { readonly brand: \"WidgetId\" }\n\n\n## Colour\n\nKind: enum\n\n- Red = \"red\"\n- Blue = \"blue\" — The calm one.\n\n## makeWidget\n\nKind: function\n\nts\nfunction makeWidget(id: WidgetId): Widget\n\n", "counts": { "types": 4, "interfaces": 1, "type_aliases": 1, "enums": 1, "functions": 1, "members": 4 } }

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/types2docs mcp

MCP client config:

{

"mcpServers": { "types2docs": { "command": "npx", "args": ["-y", "@reneturcios/types2docs", "mcp"] } } }

Tools
  • render_api_reference — Render a markdown API reference from caller-supplied TypeScript type declarations: interfaces, type aliases, enums, and functions, in a pinned deterministic layout. Nothing is invented; every string comes from the input.
  • types (array, required, at least 1 item) — the type declarations to document, in document order; each item:
  • name (string, required, non-empty) — declared name
  • kind (string, required) — one of "interface", "type", "enum", or "function"
  • doc (string, optional) — doc comment text for the declaration
  • members (array) — required for interface and enum, forbidden for type and function; each item:
  • name (string, required, non-empty) — member name
  • type (string) — member type text; required for interface members, forbidden for enum members
  • value (string, optional) — enum member value text (enum members only)
  • optional (boolean, optional) — whether the member is optional (interface members only); absent means false
  • doc (string, optional) — doc comment text for the member
  • definition (string) — the alias's right-hand side, verbatim; required for kind "type", forbidden otherwise
  • signature (string) — the function signature, verbatim; required for kind "function", forbidden otherwise
  • title (string, optional) — document title; defaults to "API Reference"; an empty string is allowed and renders as #

Returns {markdown, counts}, where markdown is the rendered document and counts is {types, interfaces, type_aliases, enums, functions, members} in that key order.

Docker

docker run -i ghcr.io/cloudcorprecords/types2docs

docker run --rm -v "$PWD:/w" ghcr.io/cloudcorprecords/types2docs render --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