AgentWeb

Created By
zerabic3 months ago
Search 11M+ businesses across 195 countries. Get phone numbers, emails, hours, addresses, and geo search. Free for personal AI agents.
Overview

AgentWeb MCP Server

MCP (Model Context Protocol) server for AgentWeb.live — a free business directory API with 11M+ businesses across 195 countries.

What It Does

This MCP server exposes AgentWeb's business directory API to AI assistants like Claude, enabling them to:

  • Search for businesses by name, category, or location
  • Get detailed business information (phone, email, hours, address, website)
  • Access data from 11M+ businesses in 195 countries

Installation

Quick Start with npx

The easiest way to use this server is with npx:

npx agentweb-mcp

Or Install Globally

npm install -g agentweb-mcp
agentweb-mcp

Getting an API Key

You need a free API key from AgentWeb:

  1. Visit https://agentweb.live/#signup
  2. Sign up with your email and name
  3. Your API key will be sent to your email (format: aw_live_...)

Configuration

Claude Desktop

Add this to your claude_desktop_config.json:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "agentweb": {
      "command": "npx",
      "args": ["-y", "agentweb-mcp"],
      "env": {
        "AGENTWEB_API_KEY": "aw_live_your_key_here"
      }
    }
  }
}

Cursor / Windsurf

Add to your MCP settings file:

{
  "mcpServers": {
    "agentweb": {
      "command": "npx",
      "args": ["-y", "agentweb-mcp"],
      "env": {
        "AGENTWEB_API_KEY": "aw_live_your_key_here"
      }
    }
  }
}

Alternative: Pass API Key as Argument

{
  "mcpServers": {
    "agentweb": {
      "command": "npx",
      "args": ["-y", "agentweb-mcp", "aw_live_your_key_here"]
    }
  }
}

Available Tools

1. search_businesses

Search for businesses in the AgentWeb directory.

Parameters:

  • q (string, optional): Text search query (business name, keywords)
  • category (string, optional): Business category (e.g., "restaurant", "hotel")
  • city (string, optional): City name for location filter
  • country (string, optional): Country code (ISO 3166-1 alpha-2, e.g., "US", "GB")
  • lat (number, optional): Latitude for geographic search
  • lng (number, optional): Longitude for geographic search
  • radius_km (number, optional): Search radius in kilometers (use with lat/lng)
  • limit (number, optional): Max results to return (default: 10, max: 50)
  • offset (number, optional): Number of results to skip for pagination

Note: At least one of q, category, or lat+lng is required.

Example queries:

  • "Find pizza restaurants in New York"
  • "Search for hotels near latitude 40.7128, longitude -74.0060 within 5km"
  • "List all cafes in London, GB"

2. get_business

Get full details for a specific business by ID.

Parameters:

  • id (string, required): The unique business ID from AgentWeb

Example:

  • "Get details for business ID abc123"

3. agentweb_health

Check the health status of the AgentWeb API.

Parameters: None

Returns: API status, total businesses count, and countries available.

Example Usage

After configuring the server, you can ask Claude:

Find Italian restaurants in San Francisco
Search for dentists near me in Chicago
Get contact information for coffee shops in Seattle

Development

Build from Source

git clone <repository>
cd agentweb-mcp
npm install
npm run build

Run in Development Mode

npm run dev

Project Structure

agentweb-mcp/
├── src/
│   └── index.ts          # Main MCP server implementation
├── dist/                 # Compiled JavaScript (generated)
├── package.json
├── tsconfig.json
└── README.md

API Documentation

For full API documentation, visit AgentWeb API Docs.

Support

License

MIT

Server Config

{
  "mcpServers": {
    "agentweb": {
      "command": "npx",
      "args": [
        "-y",
        "agentweb-mcp"
      ],
      "env": {
        "AGENTWEB_API_KEY": "aw_live_your_key"
      }
    }
  }
}
Project Info
Created At
3 months ago
Updated At
3 months ago
Author Name
zerabic
Star
-
Language
-
License
-
Category

Recommend Servers

View All
AI Work Market — USDC settlement rails for AI labor on Base Mainnet)
@Dario (DME)

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

7 hours ago
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago