Google Maps Places Scraper MCP Server

Search Google Maps places

search_google_maps_places

Read-onlyIdempotent

Search Google Maps for places or look up known place IDs and URLs, then return structured rows with contact details, address, coordinates, categories, ratings, reviews, hours, and attributes.

Instructions

Search Google Maps or look up known place IDs. Returns one row per place with name, phone, website, address, coordinates, categories, rating, review count, hours, and attributes.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_google_maps_places"
  }
}

Input Schema

Name	Required	Description
`dedupe`	No	yes or no. Default yes: a place found twice in a run is returned and charged once.
`places`	No	Optional. Look up places you already know: a ChIJ place ID, or a Google Maps place URL. Each costs one place row.
`language`	No	Language code for names and categories, such as en or de. Default en.
`locations`	No	Optional. Each search term is run once per location, as "term in location". Leave empty when your searches already name the place.
`only_country`	No	Optional 2 letter country code, such as DE. Places in other countries are dropped and not charged. A search for Berlin can otherwise return Berlin, New Jersey, on later pages.
`search_terms`	No	What to search on Google Maps, such as dentist in Austin, TX. One search per entry. Each search returns up to about 120 to 200 places, so split a large area into neighborhoods.
`max_charge_usd`	No	Optional. The run stops before a charge that would pass this amount. Summary rows are always returned.
`results_country`	No	2 letter code Google uses to tailor results. Default us. It does not limit results to that country; use only_country for that.
`max_places_per_search`	No	Whole number from 1 to 500. Default 20. Google stops most searches between 120 and 200 places.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.1Nov 9, 2026

TDQS

A3.6/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, so the safety profile is covered. The description adds genuine value by enumerating the returned fields in the absence of an output schema, but it says nothing about the paid, metered behavior or the per-search result caps that dominate this tool's operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences, front-loaded with the primary action and followed by the return shape. There is no filler or repetition, and each sentence carries information the agent needs.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description supplies a return-value summary, which matters because no output schema exists, and it names both operational modes. Given nine parameters and metered billing, it could say more about cost behavior and search-volume expectations, but the schema already carries that detail.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all nine parameters are already well documented in the schema, including defaults, country filtering, dedupe, and result caps. The description adds no syntax or format detail beyond what the schema provides, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource ("Search Google Maps") and explicitly covers a second mode, "look up known place IDs," which maps to the `places` parameter. An agent can tell what the tool does without opening the schema, though the mapping between the two modes and their parameters is left implicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There are no sibling tools to disambiguate against, and the description implies usage through the search-vs-lookup split. However, it never states when to prefer ID lookup over search terms, and it omits the cost/charging dimension that the schema treats as central (max_charge_usd, per-row billing).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools

search_google_maps_placesA