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
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now
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 47,000+ 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

Owner-verified local business data for AI agents: profiles, hours, prices, with provenance.

README.md

Daxoom — AI-Visibility Business Data (MCP + REST)

![smithery badge](https://smithery.ai/servers/citroot/daxoom)

What schema.org is to web crawlers, Daxoom is to AI agents.

Daxoom is a hosted, owner-verified business-data layer for AI agents. Every response carries provenance (verification level, completeness score, freshness, upstream sources). One profile feeds ChatGPT, Claude, Perplexity, Gemini, and any MCP-compatible client.

This repository holds the public developer artifacts for the service — the MCP manifest, OpenAPI spec, llms.txt, the tool catalog, and copy-paste client configs. It contains no server source: Daxoom is a proprietary, hosted service (see License).

  • 🌐 Website: https://daxoom.com
  • 📚 Docs / OpenAPI: https://daxoom.com/docs · https://daxoom.com/docs/openapi.yaml
  • 🤖 LLM entry point: https://daxoom.com/llms.txt
  • 🔑 Free Developer key (3,000 queries/month): https://daxoom.com/developer

Connect (MCP — remote Streamable HTTP)

Daxoom is a remote-only MCP server at https://mcp.daxoom.com/, authenticated with an X-API-Key header (same key as the REST /pubapi). There is no local install — the server runs on Daxoom's infrastructure.

{
  "mcpServers": {
    "daxoom": {
      "url": "https://mcp.daxoom.com/",
      "transport": "http",
      "headers": { "X-API-Key": "dxm_YOUR_KEY_HERE" }
    }
  }
}

Per-client snippets (Claude Desktop, Cursor, Continue, Cline) are in examples/.

Capabilities

  • 12 tools — search, full profiles, hours, offerings (menu/services/prices),

attributes, owner Q&A, AI-grounding context, categories; a feedback loop (report_incorrect_data, submit_review); and schema explainability (list_fields, describe_field).

  • 5 browsable resourcesdaxoom://categories, daxoom://schema/business,

daxoom://schema/attributes, daxoom://schema/questions, daxoom://stats.

  • Provenance envelope — every payload is {data, _meta} with verification

level (O/E/S/C), completeness, freshness, sources, and pagination.

Full catalog: TOOLS.md · Machine manifest: mcp-server.json.

REST API

GET https://api.daxoom.com/pubapi/v1/businesses?city=irvine&category=restaurant
Header: X-API-Key: dxm_YOUR_KEY_HERE

Formats: application/json (default), application/ld+json (schema.org JSON-LD), text/plain (AI-friendly narrative). Spec: openapi.yaml.

Data model

  • Public business data (open data + public records) is public.
  • Owner-entered data stays the owner's — contributed to Daxoom for AI-agent use.
  • Daxoom-generated data (enrichment, computed signals) is Daxoom's.

All access is governed by the Daxoom API Terms.

License

The Daxoom platform and hosted service are proprietary © CITROOT LLC — the server source is not licensed for self-hosting or redistribution. The contents of this repository (docs, manifest, OpenAPI, and the example configuration snippets) may be freely used and copied to connect to the hosted service. See LICENSE.

See related servers & alternatives →

Related MCP servers

Browse all →

Related guides

Hand-picked reading to help you choose and use Files & Docs servers.