DocsScraper

Provides semantic search over documentation chunks by connecting to the DocsScraper web API and returning filtered results.

javascript

GitHub Stars

javascript

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "tanevanwifferen-docsscrapermcp": {
      "command": "node",
      "args": [
        "/Users/tanevanwifferen/Documents/Cline/MCP/docs-scraper-server/build/index.js"
      ],
      "env": {
        "DOCS_SCRAPER_API_KEY": "###",
        "DOCS_SCRAPER_BASE_URL": "https://api.mcpdocsscraper.click"
      }
    }
  }
}

This MCP server lets you query documentation chunks from the DocsScraper web API using semantic search. It handles AI-driven relevance validation, automatically falls back to local scraper sources when needed, and lets you tailor results by service. You can use it with MCP-compatible clients to build powerful, searchable documentation experiences for your team.

How to use

Connect your MCP client to the DocsScraper MCP server. Use the available tool to search documentation chunks semantically by your query. You can filter results by service name, adjust how many results you receive (between 1 and 10), and rely on fallback sources if local results aren’t found. The server returns relevant chunks along with their scores and source information, so you can present trustworthy results to users.

How to install

npm install
npm run build

Configuration and usage notes

Environment variables and endpoints for the DocsScraper MCP server are defined below. Ensure you set these values in your deployment environment to enable authentication and correct API routing.

{
  "mcpServers": {
    "docs_scraper_http": {
      "type": "http",
      "url": "https://api.mcpdocsscraper.click",
      "args": [],
      "name": "docs_scraper_http",
      "env": {
        "DOCS_SCRAPER_API_KEY": "REPLACE_WITH_YOUR_API_KEY",
        "DOCS_SCRAPER_BASE_URL": "https://api.mcpdocsscraper.click"
      },
      "disabled": false,
      "timeout": 900
    },
    "docs_scraper_stdio": {
      "type": "stdio",
      "command": "node",
      "args": ["/Users/tanevanwifferen/Documents/Cline/MCP/docs-scraper-server/build/index.js"],
      "name": "docs_scraper_stdio",
      "env": {
        "DOCS_SCRAPER_API_KEY": "REPLACE_WITH_YOUR_API_KEY",
        "DOCS_SCRAPER_BASE_URL": "https://api.mcpdocsscraper.click"
      },
      "disabled": false,
      "timeout": 900
    }
  }
}

API and endpoints

The DocsScraper MCP server connects to the DocsScraper web API. It uses the search endpoint to find semantically similar documentation chunks and then applies AI validation to confirm relevance. If no local results are found, it falls back to scraper sources. The API requires an API key for authentication and accepts a query, a top limit for results, and an optional service filter.

Endpoint: GET /api/chunks/search
Headers: X-API-Key: <your_api_key>
Params: query (string), top (number, 1-10), service (string, optional, case-insensitive)

Available tools

search_docs

Search through documentation chunks using semantic search. Accepts a query string, an optional top limit (1-10), and a service filter to return relevant chunks with scores and source information.

Built by

VeilStrat

AI signals for GTM teams