mcpField
A

AgentWeb

Local
github.com/zerabicBusiness & Marketing0
Repository

About AgentWeb

Search 11M+ businesses across 195 countries. Get phone numbers, emails, hours, addresses, and geo search. Free for personal AI agents.

#business#directory#search#geolocation#api#data

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "zerabic-agentweb": {
      "command": "npx",
      "args": [
        "-y",
        "agentweb-mcp"
      ],
      "env": {
        "AGENTWEB_API_KEY": "<AGENTWEB_API_KEY>"
      }
    }
  }
}
Run commandnpx -y agentweb-mcp
Environment variables to set
AGENTWEB_API_KEYSecretYour free AgentWeb API key (get one at https://agentweb.live/#signup)

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmagentweb-mcp1.5.0

Tools

23

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
qstringNoText search query, e.g. 'noma', 'thai restaurant', 'dentist near me'
categorystringNoBusiness category filter (e.g., 'restaurant', 'hotel', 'pharmacy')
citystringNoCity name for location filter
countrystringNoCountry code (ISO 3166-1 alpha-2, e.g., 'US', 'GB', 'DK')
latnumberNoLatitude for geographic search (requires lng and radius_km)
lngnumberNoLongitude for geographic search (requires lat and radius_km)
radius_kmnumberNoSearch radius in kilometers (used with lat/lng)
limitnumberNoMaximum number of results to return (default: 10, max: 100)
offsetnumberNoNumber of results to skip for pagination
formatenumNoResponse format. 'text' (default) returns markdown prose — recommended for LLM consumption. 'json' returns structured JSON.text | json

Details

The maintainer has not added details yet. Check the README in the repository.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.