Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/HasData/google-maps-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/hasdata/google-maps-mcp/hasdata-google-maps)<a href="https://agentmods.dev/rules/hasdata/google-maps-mcp/hasdata-google-maps"><img src="https://agentmods.dev/badge/rules/hasdata/google-maps-mcp/hasdata-google-maps/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/hasdata/google-maps-mcp/hasdata-google-maps"><img src="https://agentmods.dev/badge/rules/hasdata/google-maps-mcp/hasdata-google-maps.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00018 | $0.00634 |
| Opus 5.5 | $0.00007 | $0.00254 |
| Sonnet 5.5 | $0.00004 | $0.00127 |
| Haiku 4.5 | $0.00002 | $0.00063 |
Grade A, and why
hasdata-google-maps scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Maps through HasData
Six tools, and five of them need a place you already found. Start with hasdata_google_maps_search_performMapSearch, which takes q and optionally ll for the map centre, then carry the identifiers it returns.
Which identifier
Place details take placeId. Reviews, photos and posts take placeId or dataId, and sending neither returns a 422 naming both. Contributor reviews are a different axis: they take contributorId and return everything one person wrote, which is how you check whether a reviewer is real.
The search is the map, not a directory
q behaves like the Maps search box, so coffee in Austin works and a bare category plus a separate city field does not. ll pins the centre when the query alone drifts, and gl with hl set the country and language of the answer.
Two answer shapes, and the key says which
A category query returns localResults, an array of about twenty rows carrying position, title, placeId, dataId, phone, address, website, workingHours, openState, rating, reviews, gpsCoordinates and more. That is usually enough to answer a contact or ranking question without opening a single place.
A query that Maps resolves to one entity returns placeResults instead, a single object rather than an array, and localResults is absent. Phrasing alone decides it, since coffee in Austin gave the array while coffee austin texas gave the object. Test for the key before iterating, because code that reaches straight for localResults finds nothing and reports an empty area.
There is no empty answer here. A nonsense keyword still returned one unrelated company in placeResults rather than a miss, so judge whether the result matches what was asked instead of treating any response as a hit.
Reading the payload
An empty posts array is real data: most listings post nothing. A place id that does not resolve is a clean error with requestMetadata.status set to error, so tell those two apart before you report "nothing found".
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago Changed · +6 lines db89b2316b1e
- 16d ago Changed · +8 lines 64bf8732b431
- 23d ago First seen · 23 lines · 18 tokens per session scan A 59034e6e150e
hasdata-google-maps is a cursor rule published in the GitHub repository HasData/google-maps-mcp (6 stars, last pushed 3d ago), licensed MIT. It adds 18 tokens to every session and 634 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-23.
Other cursor rules, from other repositories
hasdata-zillow
How to pull Zillow listings and property details through the HasData MCP server.
hasdata-tiktok
How to pull TikTok profiles, post feeds, keyword search and comments through the HasData MCP server.
hasdata-airbnb
How to pull Airbnb stays and listing details through the HasData MCP server.
hasdata-umbrella
How to work with the full HasData MCP server, which exposes every scraping tool behind one endpoint.
hasdata-instagram
How to pull public Instagram profiles and post feeds through the HasData MCP server.
hasdata-booking
How to pull Booking.com hotel search and property details through the HasData MCP server.