MDN Lookup

Created By
Baby Manisha Sunkaraa year ago
Tool to fetch and summarize developer documentation from [MDN Web Docs](https://developer.mozilla.org/). ## Features - Search MDN for documentation using a query string. - Returns a summary (first paragraph) and a link to the full documentation. - Exposes an MCP-compatible tool server over stdio.
Overview

MDNlookup

A tool to fetch and summarize developer documentation from MDN Web Docs.

MDNlookup is a developer productivity tool that streamlines access to MDN Web Docs documentation directly from your development environment. Designed for seamless integration with MCP-compatible clients and editors like VS Code, mdnlookup enables developers to quickly search for and retrieve concise, relevant documentation summaries for web APIs, JavaScript methods, and other web technologies—without leaving their workflow.

By exposing an MCP-compatible tool server over stdio, mdnlookup makes it easy to automate documentation lookups and integrate them into custom toolchains or editor extensions. This helps developers save time, reduce context switching, and stay focused on coding.

Features

  • Search MDN for documentation using a query string.
  • Returns a summary (first paragraph) and a link to the full documentation.
  • Exposes an MCP-compatible tool server over stdio.

Available Tools

mdnlookup

  • Description: Fetches and summarizes developer documentation from MDN based on a search query.
  • Parameters:
    • query (string): The search term or API/method name you want documentation for.

Installation

Clone the repository and install dependencies:

git clone https://github.com/yourusername/mdn-lookup.git
cd mdn-lookup
npm install

Usage

This tool is designed to be used as an MCP tool server. You can run it directly:

node index.js

It will start an MCP server over stdio, ready to accept requests.

Example: Configure in MCP Client

{
  "mcpServers": {
    "SmartDeveloperAssistant": {
      "command": "node",
      "args": [
        "</absolute/path/to>/mdn-lookup/index.js"
      ]
    }
  }
}

VS Code (.vscode/settings.json)

"mcp": {
        "servers": {
            "mdnlookup": {
                "type": "stdio",
                "command": "node",
                "args": ["</absolute/path/to>/mdn-lookup/index.js"]
            }
        },
        "inputs": []
    },

Example: Using the Tool

You can use the mdnlookup tool by sending a request from any MCP-compatible client:

{
  "tool": "mdnlookup",
  "params": {
    "query": "Array.prototype.map"
  }
}

The response will look like:

{
  "content": [
    {
      "type": "text",
      "text": "The map() method creates a new array populated with the results of calling a provided function on every element in the calling array.\n\nMore info: https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Array/map"
    }
  ]
}

Example Results

Below are screenshots of the tool in action for various queries:

Promises

Promises Example

Async/Await

Async/Await Example

Node.js

Node.js Example

OAuth

OAuth Example

Configuration

No additional configuration is required. The tool uses the MDN public API and fetches documentation in English.

License

ISC

--

Thanks

Happy Coding!!

Baby Manisha Sunkara 👩🏻‍💻

Server Config

{
  "mcpServers": {
    "SmartDeveloperAssistant": {
      "command": "node",
      "args": [
        "</absolute/path/to>/mdn-lookup/index.js"
      ]
    }
  }
}
Project Info
Created At
a year ago
Updated At
a year ago
Author Name
Baby Manisha Sunkara
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Mnemom

14 hours ago
//beforeyouship — LLM Cost Modeling From Your Editor
@Indiegoing

Query realistic LLM cost models without leaving your editor. beforeyouship models the **true monthly cost** of an LLM app architecture — retries, prompt caching, batch discounts, infra overhead, and 3×/10× growth — across GPT-5.x, Claude, Gemini, DeepSeek, and more. Not a token calculator: a planning tool for the design phase, before you commit to a stack. **No API key needed to try it** — demo mode covers the six free-tier models. A Pro key from [beforeyouship.dev](https://beforeyouship.dev) unlocks the full 18-model catalog. ## What you can ask - "How much will a RAG chatbot cost at 10,000 requests/day?" - "Compare Claude Haiku vs Gemini Flash pricing for my workload" - "What's the cheapest model for a multi-step agent at scale?" - "Show me current per-token prices for Anthropic models" ## Tools ### `estimate_cost` Full cost model for an architecture at a given usage level. Returns Naive / Realistic / Worst Case monthly cost per model, 3×/10× growth scenarios, and an opinionated recommendation with reasoning. ### `get_model_prices` Current per-1M-token pricing — input, output, cached input, batch — with context windows and staleness metadata. ### `list_archetypes` Seven preset architecture patterns (simple chatbot, chatbot with history, RAG pipeline, multi-model router, coding assistant, document processor, multi-step agent) used as starting points for estimates. ## Setup **Claude Code:** ​```bash claude mcp add --transport http beforeyouship https://beforeyouship.dev/api/mcp ​``` **Cursor / other clients** — add a remote server: ​```json { "mcpServers": { "beforeyouship": { "type": "streamable-http", "url": "https://beforeyouship.dev/api/mcp" } } } ​``` Add an `Authorization: Bearer bys_...` header with a Pro key for the full catalog. ## Try it > Estimate the monthly cost of a RAG pipeline at 10,000 requests/day

13 hours ago
Docwand

13 hours ago