google-maps

A set of geographic query capabilities for an AI agent, using Google Maps data to work with places, addresses, coordinates, routes, distances, travel times, and elevation.

In plain words
What is it for?
Finding nearby places, converting addresses to coordinates, comparing locations, planning routes, calculating distance or duration, and checking elevation.
Why use it?
It replaces guesses about physical locations and travel with structured map results. It also provides patterns for combining several map queries when one question needs multiple steps.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/cablate/mcp-google-map/google-maps
Any agent
npx skills add cablate/mcp-google-map --skill google-maps
Clone the repo
git clone --depth 1 https://github.com/cablate/mcp-google-map

Made for: Claude Code, Codex.

Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,542 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00080 $0.01542
Opus 5 $0.00040 $0.00771
Sonnet 5 $0.00016 $0.00308
Haiku 4.5 $0.00008 $0.00154

Measured yesterday against content hash 6c0ab3bdb768, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 yesterday.

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.

skills/google-maps/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Google Maps - Geospatial Query Capabilities

Overview

Gives an AI Agent the ability to reason about physical space — understand locations, distances, routes, and elevation, and naturally weave that information into conversation.

Without this Skill, the agent can only guess or refuse when asked "how do I get from Taipei 101 to the National Palace Museum?". With it, the agent returns exact coordinates, step-by-step routes, and travel times.


Core Principles

Principle Explanation
Chain over single-shot Most geo questions require 2-5 tool calls chained together. See Scenario Recipes in references/tools-api.md for the full patterns.
Match recipe to intent Map the user's question to a recipe (Trip Planning, Local Discovery, Route Comparison, Neighborhood Analysis, Multi-Stop, Place Comparison, Along the Route) before calling any tool.
Precise input saves trouble Use coordinates over address strings when available. Use place_id over name search. More precise input = more reliable output.
Output is structured Every tool returns JSON. Use it directly for downstream computation or comparison — no extra parsing needed.
Present as tables Users prefer comparison tables and scorecards over raw JSON. Format results for readability.

Tool Map

17 tools in five categories — pick by scenario:

Place Discovery

Tool When to use Example
maps_geocode Have an address/landmark, need coordinates "What are the coordinates of Tokyo Tower?"
maps_reverse_geocode Have coordinates, need an address "What's at 35.65, 139.74?"
maps_search_nearby Know a location, find nearby places by type "Coffee shops near my hotel"
maps_search_places Natural language place search "Best ramen in Tokyo"
maps_place_details Have a place_id, need full info (+ optional photo URLs via maxPhotos) "Opening hours and reviews for this restaurant?"
maps_batch_geocode Geocode multiple addresses at once (max 50) "Get coordinates for all these offices"

Read the full file on GitHub · 124 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. yesterday First seen · 124 lines · 80 tokens per session scan A 6c0ab3bdb768

Subscribe to this mod's changes

google-maps is a skill published in the GitHub repository cablate/mcp-google-map (438 stars, last pushed 16d ago), licensed MIT. It adds 80 tokens to every session and 1,542 once invoked, about $0.0004 per session on Opus 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 2026-08-30.

Related

Other skills, from other repositories

baocut

BaoCut-only operator for the installed bcut CLI and .bcut projects. Implicitly trigger only when the request explicitly names BaoCut or bcut, targets a .bcut project or BaoCut Subtitle Studio, or continues a BaoCut workflow already established in the conversation. Do not trigger solely for generic audio or video…

JimLiu/baocut · 160 tokens

karpathy-llm-wiki

Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.

Astro-Han/karpathy-llm-wiki · 67 tokens

proxies

Oxylabs proxy networks: Residential, Mobile, shared Datacenter/ISP, and Dedicated Datacenter/ISP proxies with geo-targeting, IP rotation, session persistence, and port-based sticky IPs. Use when routing traffic through proxies, building scrapers with proxy auth, rotating or sticky sessions, whitelisting IPs, or…

oxylabs/agent-skills · 76 tokens

agentsop-llamaindex

Operating-system distillation of LlamaIndex — the leading RAG / document-agent framework. Activate when the calling agent must build, debug, harden, or evaluate a Retrieval-Augmented Generation pipeline over unstructured/private data, decide between RAG primitives (Index types, retrievers, query engines, routers…

agentsope/SkillAlchemy · 178 tokens

agentsop-prompt-compilation

The compile-readiness gate for prompt auto-optimization. Decide whether you have earned the right to run an optimizer (DSPy MIPROv2 / GEPA / BootstrapFewShot) before spending compute. Two preconditions only — a real metric, and enough examples for the optimizer you picked. Garbage metric in, garbage prompt out. Pick…

agentsope/SkillAlchemy · 96 tokens

agentsop-signature-design

Decision rubric for promoting a prose prompt into a typed DSPy Signature. This is an ENHANCE overlay on top of the [[dspy]] library skill: it does NOT teach DSPy syntax — it answers the coder-agent decision "when do I stop hand-writing a prompt string and declare it as a dspy.Signature, and how do I name/describe its…

agentsope/SkillAlchemy · 226 tokens