Featured

Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger
Crawl and scrape any site into clean data, 10% off logoCrawl and scrape any site into clean data, 10% off

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits, and new users get 10% off their first purchase.

Try Firecrawl free
6,000+ web scrapers for your AI agent, start free logo6,000+ web scrapers for your AI agent, start free

Apify gives your agent live web data: 6,000+ prebuilt scrapers and actors, MCP-ready. Sign up free with $5 in usage credits.

Try Apify free
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you
SEO data APIs for your agent, $1 free credit logoSEO data APIs for your agent, $1 free credit

DataForSEO gives your agent live access to SERP results, keyword data, backlinks, and on-page SEO data through one API. New accounts get a $1 credit, good for up to 20,000 keyword or backlink lookups.

Try DataForSEO free
Reach 48,000+ AI builders

A flat monthly placement in front of developers actively installing AI tools. No lock-in, cancel anytime.

Advertise here

Works with

Claude CodeClaude DesktopCursorVS CodeClineCodex CLIOpenClaw+ any MCP client

Install to Claude Code

This server doesn't publish a one-line install command. Follow the setup in the source repository.

Summary

MCP server for documentation search that automatically indexes web documentation sites and provides semantic, full-text, or hybrid search capabilities.

README.md

MCP Docs Server

MCP server for documentation search with automatic web indexing.

![npm version](https://www.npmjs.com/package/@pgupta1795/mcp-docs)

Usage via npx (Recommended)

Run the MCP server directly without installation:

# STDIO mode (for MCP client integration)
SEED_URLS="Docs|https://example.com/docs|sidebar|0" TRANSPORT=stdio npx @pgupta1795/mcp-docs

# HTTP mode
SEED_URLS="Docs|https://example.com/docs|sidebar|0" TRANSPORT=http npx @pgupta1795/mcp-docs

MCP Client Configuration (npx)

{
  "mcpServers": {
    "docs": {
      "command": "npx",
      "args": ["-y", "@pgupta1795/mcp-docs"],
      "env": {
        "TRANSPORT": "stdio",
        "SEED_URLS": "TVC Classic 2025.4.0|https://products.technia.com/app/docs/tvc-documentation-2025.4.0/tvc/install/index.html|navbar|0,TVC Helium 2025.4.0|https://products.technia.com/app/docs/tvc-helium-documentation-2025.4.0/index.html|navbar|0,TIF Classic 2025.4.0|https://products.technia.com/app/docs/tif-documentation-2025.4.0/tif-classic/2025.4.0/main/index.html|sidebar|0,TIF Cloud|https://forseven.tif.technia.cloud/docs/tif-cloud/Current/main/index.html|sidebar|0",
        "SEARCH_MODE": "SEMANTIC_ONLY",
        "DB_PATH": "C:/GBS/Search_Tool/mcp-docs/data/mcp-docs.db"
      }
    }
  }
}

---

Quick Start (Local Development)

npm install
npm run build

Running the Server

STDIO Mode

TRANSPORT=stdio npm run start
# Or for development:
npm run dev:stdio

HTTP Mode

TRANSPORT=http npm run start
# Or for development:
npm run dev:http

HTTP endpoint: http://localhost:5004/docs/mcp

---

MCP Client Configuration

STDIO Mode

{
  "mcpServers": {
    "mcp-docs": {
      "command": "node",
      "args": ["dist/index.js"],
      "cwd": "C:/path/to/mcp-docs",
      "env": {
        "TRANSPORT": "stdio",
        "SEED_URLS": "TVC Classic|https://products.technia.com/app/docs/tvc-documentation-2025.4.0/tvc/install/index.html|sidebar|0"
      }
    }
  }
}

HTTP Mode

{
  "mcpServers": {
    "mcp-docs": {
      "type": "http",
      "url": "http://localhost:5004/docs/mcp"
    }
  }
}

---

Environment Variables

| Variable | Default | Description | | ------------------- | ------------------------- | -------------------------------------------------- | | TRANSPORT | http | Transport mode: stdio or http | | PORT | 5004 | HTTP server port | | SEED_URLS | _required_ | Documentation sources (see format below) | | DB_PATH | ./data/mcp-docs.db | SQLite database path | | INIT_ON_START | true | Auto-index on startup | | CRAWL_MAX_PAGES | 1000 | Max pages per source | | CRAWL_MAX_DEPTH | 5 | Max crawl depth | | CACHE_SIZE | 100 | LRU cache size | | LOG_LEVEL | info | Log level: debug, info, warn, error | | LOG_PATH | - | Optional log file path | | SEARCH_MODE | SEMANTIC_ONLY | Search mode: FTS_ONLY, SEMANTIC_ONLY, HYBRID | | EMBEDDING_MODEL | Xenova/all-MiniLM-L6-v2 | Embedding model for semantic search | | SEMANTIC_TOP_K | 20 | Top K results for semantic search | | HYBRID_FTS_WEIGHT | 0.4 | FTS weight in hybrid mode (0-1) |

SEED_URLS Format

name|url|navigationMode|recrawlIntervalHours
  • navigationMode: sidebar, navbar, or auto
  • recrawlIntervalHours: 0 = never, 24 = daily

Example:

SEED_URLS=TVC Classic|https://products.technia.com/app/docs/tvc-documentation-2025.4.0/tvc/install/index.html|sidebar|0,TIF Cloud|https://forseven.tifdemo.technia.cloud/docs/tif-cloud/Current/main/index.html|auto|24

See related servers & alternatives →

Related MCP servers

Browse all →

Related guides

Hand-picked reading to help you choose and use Search servers.