A location-data connection for researching US places and properties. It returns records and citations about terrain, hazards, land use, utilities, parcels, and site suitability.

Use it to screen sites, check property and parcel information, assess environmental risks, and answer questions about utilities or physical conditions at a US location.

It avoids relying on generic maps or unsupported guesses when a question depends on a specific location. The returned sources and calculations make the answer traceable.

use-mireye — Skill for Claude Code and Codex by Mireye-Labs

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.

Any agent

npx skills add Mireye-Labs/mireye-earth-mcp --skill use-mireye

Clone the repo

git clone --depth 1 https://github.com/Mireye-Labs/mireye-earth-mcp

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/mireye-labs/mireye-earth-mcp/use-mireye/github.svg)](https://agentmods.dev/skills/mireye-labs/mireye-earth-mcp/use-mireye)

Your own site

<a href="https://agentmods.dev/skills/mireye-labs/mireye-earth-mcp/use-mireye"><img src="https://agentmods.dev/badge/skills/mireye-labs/mireye-earth-mcp/use-mireye/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/mireye-labs/mireye-earth-mcp/use-mireye"><img src="https://agentmods.dev/badge/skills/mireye-labs/mireye-earth-mcp/use-mireye.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,775 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00065	$0.01775
Opus 5.5	$0.00026	$0.00710
Sonnet 5.5	$0.00013	$0.00355
Haiku 4.5	$0.00006	$0.00178

Measured 16d ago against content hash 3872be91d63c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

use-mireye 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 16d 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.

mireye_earth_mcp/skills/use-mireye/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Use Mireye

Answer questions about real places using Mireye's returned records, location quality, and citations. Preserve the user's chosen data sources and task scope.

Choose a connection

Prefer an already connected Mireye MCP server. Inspect its advertised tools and input schemas before calling: only the hosted service serves MCP tools. The hosted endpoint is https://api.mireye.com/mcp.

If a required operation is unavailable through MCP, use the documented HTTP API when an API bearer token is already configured. Production base URL: https://api.mireye.com. Read the relevant endpoint in the documentation index; do not infer routes or schemas from tool names.

Authentication paths are distinct:

Hosted MCP uses client-managed OAuth. Its access tokens are scoped to MCP and do not authenticate general /v1/* requests.
HTTP requests use Authorization: Bearer <API token>. The quickstart names the environment variable MIREYE_API_TOKEN.
The mireye-mcp package is an installation/diagnostic helper only. Its saved scoped API key at ~/.config/mireye-mcp/credentials.json is private and bound to the API origin and account. It does not run a local MCP server or create an OAuth grant.

If authentication is missing, identify the needed connection and use the documented sign-in path. Keep credentials out of skill files, project instructions, and displayed output. For setup diagnostics, run uvx --from mireye-mcp==0.7.3 mireye-mcp doctor. doctor --proof makes one free REST elevation Fetch and validates its provenance. This does not verify or authorize hosted MCP OAuth; complete the client’s sign-in separately. Reconnect with mireye-mcp connect --client <client> when configuration is missing. This skill does not change client configuration on its own.

Route the request

Use the following tools only when the connected server advertises them; follow that server's schema.

User need	Tool
A natural-language question about a location	`mireye_ask`
Named data fields or a known preset at a location	`mireye_fetch`
Resolve a street address to a coordinate and inspect match quality	`mireye_geocode`
Driving relationships, nearest candidates, or a labor shed	`mireye_proximity`
Find parcels satisfying requirements	`mireye_search`
Investigate one identified parcel	`mireye_enrich`

Read the full file on GitHub · 85 lines

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.

16d ago Changed · +16 lines 3872be91d63c
18d ago First seen · 69 lines · 65 tokens per session scan A fb9dbbfcb65b

Subscribe to this mod's changes

use-mireye is a skill published in the GitHub repository Mireye-Labs/mireye-earth-mcp (1 stars, last pushed 16d ago), licensed MIT. It adds 65 tokens to every session and 1,775 once invoked, about $0.0003 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 2026-10-21.

Research geospatial mcp model-context-protocol

use-mireye next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
use-mireyeMireye-Labs/mireye-earth-mcp	Skill	1	16d ago	MIT	A	65	Claude Code, Codex
opik-diagnosecomet-ml/opik-mcp	Skill	226	2d ago	Apache-2.0	A	187	Claude Code
dcc-blender-assembly-pitfallsdcc-mcp/dcc-mcp-blender	Skill	62	2d ago	MIT	A	153	Claude Code
color-theorymtarcure/claude-vibe-squad	Skill	228	11d ago	MIT	A	62	Claude Code, Codex
client-scriptsserac-labs/serac	Skill	77	19d ago	Apache-2.0	A	45	Claude Code
linkdingjmagar/claude-homelab	Skill	87	1mo ago	MIT	A	69	Claude Code
blender-texture-bakedcc-mcp/dcc-mcp-blender	Skill	62	2d ago	MIT	A	23	Claude Code