⚡ Kael MCP Server

AI-native tools for agents — use cheap compute for web, DNS, WHOIS, screenshots, extraction, and sandboxed code execution instead of spending model tokens on guesswork.

Kael is for tasks where an agent needs fresh external data, structured output, or real execution — not another paragraph of reasoning.

Why this exists

LLMs are expensive at:

• fetching and cleaning live web content
• checking DNS / WHOIS / IP facts
• extracting structured data from messy pages
• executing code safely and reproducibly
• producing screenshots or binary artifacts

Kael turns those jobs into real tools with JSON output.

Best fit

Use Kael MCP when your agent needs:

• fresh data from the web or internet infrastructure
• structured results instead of prose
• deterministic execution instead of model simulation
• lower token burn on repetitive utility work
• small tool outputs that are easier to feed back into a model

Do not use Kael MCP when:

• the task is pure reasoning or writing
• the data is already in context
• a local tool already solves the problem cheaper/faster
• you need a full browser workflow with human-style interaction across many steps

Included tools

Web and content

• web_fetch — URL → clean readable markdown/text
• web_search — real-time search results
• html_extract — HTML/page content → structured data
• screenshot — webpage → PNG screenshot
• pdf_extract — PDF → extracted text
• url_unshorten — resolve shortened links safely

Internet and infrastructure

• dns_lookup — A, AAAA, MX, TXT, NS, CNAME, SOA, SRV records
• whois — domain registration data
• ip_geo — IP geolocation and network info

Data and utility

• code_run — execute JavaScript, Python, or Bash in a sandbox
• text_diff — compare text versions
• json_query — query/filter JSON data
• hash_text — compute common hashes

Tool selection guide

| Tool | Use when | Avoid when | |---|---|---| | web_fetch | You need readable page content for summarization or downstream extraction | You need pixel-perfect rendering or JS-heavy interaction | | web_search | You need fresh discovery across the web | You already know the exact URL | | html_extract | You need tables, lists, metadata, or page structure as data | Plain cleaned text is enough | | screenshot | You need visual verification, layout evidence, or image output | Text content alone is enough | | dns_lookup | You need factual DNS records now | Static knowledge is acceptable | | whois | You need domain ownership/registration details | DNS records alone answer the question | | ip_geo | You need IP location/ASN/ISP context | You only need DNS or hostname resolution | | code_run | You need actual execution, parsing, transformation, or calculation | The task is simple enough to do directly in-model | | pdf_extract | The source is a PDF and you need text back | The source is already HTML/text | | url_unshorten | You need to inspect where a short link resolves | You already trust and know the final URL | | text_diff | You need a concrete change set between two texts | You just need a summary | | json_query | You need to filter/reshape JSON before reasoning | The JSON is already tiny and easy to inspect | | hash_text | You need a deterministic fingerprint/checksum | Semantic comparison matters more than exact bytes |

Quick start

Server endpoints

Kael supports two MCP transports:

| Transport | URL | Best for | |---|---|---| | SSE | https://www.kael.ink/mcp/sse | Broad client compatibility | | Streamable HTTP | https://www.kael.ink/mcp/stream | Newer clients, simpler connection model |

Use SSE if your client doesn't specify a preference. Use streamable-http if your client supports the 2025-03-26+ MCP protocol version.

Health check:

https://www.kael.ink/mcp/health

Claude Desktop

Add this to claude_desktop_config.json:

{
  "mcpServers": {
    "kael-tools": {
   

... [View full README on GitHub](https://github.com/dreamingms/kael-mcp-server#readme)