AI-native tool server: web fetch, screenshot, search, PDF, DNS, WHOIS, IP geo, code exec & more
Kael MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. AI-native tool server: web fetch, screenshot, search, PDF, DNS, WHOIS, IP geo, code exec & more.
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
Once Kael is connected, these are the calls the assistant has available:
dns_lookup — Useful when you want: - machine-checkable infrastructure facts - small outputs that a model can quote directly - an easy first connectivity testweb_fetch — Useful when you want: - readable page content instead of raw HTML - a compact artifact for summarization - a lower-token input for downstreamhtml_extract — Useful when you want: - page structure as data before reasoning - table/list extraction without custom scraping glue - cleaner agent pipelinescode_run — Useful when you want: - deterministic transforms or calculations - reproducible parser behavior - concrete execution evidence instead of simulatedInstallation goes through your MCP client rather than a global install: point it at @modelcontextprotocol/inspector on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Kael's toolset — dns_lookup, web_fetch, html_extract and 1 more — is a fair guide to whether it matches your workflow. It is maintained by dreamingms; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Kael's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| dns_lookup | Useful when you want: - machine-checkable infrastructure facts - small outputs that a model can quote directly - an easy first connectivity test after listTools |
| web_fetch | Useful when you want: - readable page content instead of raw HTML - a compact artifact for summarization - a lower-token input for downstream reasoning |
| html_extract | Useful when you want: - page structure as data before reasoning - table/list extraction without custom scraping glue - cleaner agent pipelines: fetch/extract first, summarize second |
| code_run | Useful when you want: - deterministic transforms or calculations - reproducible parser behavior - concrete execution evidence instead of simulated code reasoning |
Or add to `.claude/settings.json`:
```json
{
"mcpServers": {
"kael-tools": {
"type": "sse",
"url": "https://www.kael.ink/mcp/sse"
}
}
}Configuration as documented by the project. Restart the client after saving.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.