Skills/npm/google-maps-mcp

google-maps-mcp@1.0.7

VERIFIED

Publisher claims: "Google Maps places, reviews, contributor history, photos and posts as JSON. No Google Cloud." Observed in sandbox: calls mcp.hasdata.com only, touches nothing outside the project, writes no memory.

Registry npm (MCP server) · listed in the official MCP RegistryPublisher hasdata · publishing for 82 daysInstalls 0Last detonated 5d ago
$claude mcp add google-maps-mcp -- npx -y @hasdata/google-maps-mcp
WatchReport an issue

Coverage

Started with a decoy HASDATA_API_KEY; tool list observed. Tool calls with a real credential not tested.
Tested
server startup with a tagged decoy in HASDATA_API_KEY · MCP initialize and tools/list · every tool description, for hidden instructions · where the decoy credential went · every file read, file written and host contacted by what ran
Not tested
what the tools do when called with a real credential
Needs
HASDATA_API_KEY — give it to the server where it runs, through vet-skills run --secrets, so the value never enters the server's environment. Never paste a credential into a chat, a ticket or a report.

Before you give it your token

It will ask for
HASDATA_API_KEY
Where it talks to
hasdata.com (its own)
What the honeypot saw
no credential files read · reached only mcp.hasdata.com (its own)
What we could not test
what the tools do when called with a real credential

Connect it with a scoped credential, under the guard. It asks for HASDATA_API_KEY and talks to hasdata.com. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind.

$vet-skills run --secrets HASDATA_API_KEY=hasdata.com -- npx -y @hasdata/google-maps-mcp

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-09 and scored it 81/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: calls mcp.hasdata.com only, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 42 s · 2 scenarios
t+CategoryObserved action
0.0sprocessno install scripts in bundle
2.3sprocessdependency install exit 0
22sprocessrelaunched with a decoy HASDATA_API_KEY (tagged; nothing real)
42sfilesystemread ~/.mcp-auth/mcp-remote-0.1.49/688f7d93d800c714ba700c72a14da245_client_info.json · ~/.mcp-auth/mcp-remote-0.1.49/688f7d93d800c714ba700c72a14da245_tokens.json outside project
42snetworkCONNECT tcp://mcp.hasdata.com:443
42snetworkCONNECT tcp://mcp.hasdata.com:443
42snetworkCONNECT tcp://mcp.hasdata.com:443
42snetworkCONNECT tcp://mcp.hasdata.com:443
42snetworkCONNECT tcp://mcp.hasdata.com:443
42snetworkCONNECT tcp://mcp.hasdata.com:443
42snetworkCONNECT tcp://mcp.hasdata.com:443
42sclaimed6 tools with a decoy HASDATA_API_KEY: hasdata_google_maps_contributor_reviews_getMapReviews, hasdata_google_maps_photos_getMapPhotos, hasdata_google_maps_place_getPlaceDetails, hasdata_google_maps_posts_getMapPosts, hasdata_google_maps_reviews_getMapReviews, hasdata_google_maps_search_performMapSearch
42sprocessscript backend runs setup only
42sprocessno install scripts to re-run

Static findings

HIGH
Collapsed <details> block carrying instructionsREADME.md:63 · Collapsed <details> block carrying instructions<summary><b>Claude Desktop</b></summary> Claude Desktop loads only local (stdio) servers from its config file, so it reaches a remote server through a stdio lauFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

No other findings across 614 lines in 5 files.

Cost to the agent

Instructions loaded
≈87 tok
1 file · 5 in bundle
Tool list per prompt
≈2,210 tok
6 tools · 368 per tool
Handshake
1348 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 469

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

No advisories in OSV for @hasdata/google-maps-mcp@1.0.7 as of 5d ago. This is the package itself, not its dependencies.