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

Enables searching and retrieving Godot documentation pages using fuzzy search, with support for multiple documentation versions.

README.md

Godot Docs MCP

!demo.png

This project is hosted on Cloudflare using their Agents framework

[!WARNING] Due to the popularity of this project, a rate limit of 30 requests per 60 second has been added. If you want to avoid that, create a free Cloudflare account yourself and deploy this project.

Look up documentation in Godot using fuzz search. Supports stable, latest, 4.6, 4.5, 4.4, and 4.3 versions. The default version is "stable".

Tools

search_docs (searchTerm: string, version: "stable" | "latest" | "4.6" | "4.5" | "4.4" | "4.3" = "stable")

Search the Godot docs by term. Will return URLs to the documentation for each matching term. The resulting URLs will need to have their page content fetched to see the documentation.

get_docs_page_for_term (searchTerm: string, version: "stable" | "latest" | "4.6" | "4.5" | "4.4" | "4.3" = "stable")

Get the Godot docs content by term. Will return the full documentation page for the first matching result.

Configure the MCP server

To use the hosted HTTP server:

{
  "mcpServers": {
    "godot": {
      "type": "http",
      "url": "https://godot-docs-mcp.j2d.workers.dev/mcp"
    }
  }
}

Or, to connect to the MCP server using a stdio server:

{
  "mcpServers": {
    "godot": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://godot-docs-mcp.j2d.workers.dev/mcp"
      ]
    }
  }
}

How this works

The docs site uses a frontend search tool to handle the docs search. There is a file called searchindex.js in the docs site that contains an index of all the pages (URLs and titles, not content) on the site.

This project takes advantage of that in the following ways:

  • downloads each of those searchindex.js files for each version of the docs
  • converts the searchindex.js to a searchindex.js.json that is just json we need
  • indexes that new json using lucaong/minisearch
  • when a docs page is requested, the URL for the page is converted from HTML to markdown

Local development

MCP server

npm install
npm run dev

Then, set up your tool:

{
  "mcpServers": {
    "godot": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "http://localhost:8787/mcp"
      ]
    }
  }
}

To debug the server, you can use this browser tool:

# in another tab
npx @modelcontextprotocol/inspector

Then open http://localhost:6274/#tools.

You can also use https://www.mcpplayground.io/ to look at the tools in the live HTTP server.

Generating the docs

# create the folders
echo "stable,latest,4.6,4.5,4.4,4.3" | string split "," | xargs -I {} mkdir -p "src/indexes/{}"
# download the files
echo "stable,latest,4.6,4.5,4.4,4.3" | string split "," | xargs -I {} curl -o "src/indexes/{}/searchindex.js" "https://docs.godotengine.org/en/{}/searchindex.js"
# convert the .js to a .json
lsd src/indexes/*/searchindex.js | xargs -n1 fish -c 'cat "$argv" | sd "Search.setIndex\(" "" | sed \'$ s/.$//\' | jq \'.docnames | to_entries | map({id: .key, name: .value, category: .value | split("/") | first, url: "/\\(.value).html"})\' > "$argv.json"'

Deploy to Cloudflare

To deploy your own instance (recommended to avoid rate limits):

  1. Create a free Cloudflare account
  2. Install and authenticate Wrangler:
npm install -g wrangler
wrangler login
  1. Change the ratelimits settings in the wrangler.jsonc.
  2. Clone and deploy:
git clone https://github.com/your-repo/godot-docs-mcp.git
cd godot-docs-mcp
npm install
npm run deploy
  1. Update your server URL:

After deployment, update your MCP config with your worker URL:

{
  "mcpServers": {
    "godot": {
      "type": "http",
      "url": "https://godot-docs-mcp.YOUR-SUBDOMAIN.workers.dev/mcp"
    }
  }
}

Adjusting the Rate Limit

The default rate limit is 30 requests per 60 seconds. To increase or disable it, edit wrangler.jsonc:

Increase the limit:

"ratelimits": [
  {
    "name": "MCP_RATE_LIMITER",
    "namespace_id": "1001",
    "simple": {
      "limit": 1000,
      "period": 60
    }
  }
]

Disable rate limiting entirely: Remove the entire ratelimits array from wrangler.jsonc.

See related servers & alternatives →

Related MCP servers

Browse all →

Related guides

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