Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

com.mireye/earth

PYPI · MIREYE-MCP · 2 COMPONENTS · SCANNED SEP 20

MCP server for Mireye Earth — federal-source-cited geospatial data for any MCP-aware agent.

0 this week 82 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
  • 0 of 29 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency45
Schema Quality & AI Usability80
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1736 tokens (~192/item across 9 items; 6 tools + 3 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management90
  • Stability observed for 27 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage75
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 13% of tool parameters carry a description.Partial
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the com.mireye/earth MCP server?

com.mireye/earth runs locally as a PyPI package, launched with uvx mireye-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · mireye-mcp

# add to Claude Code
claude mcp add com-mireye-earth -- uvx mireye-mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "com-mireye-earth": {
      "command": "uvx",
      "args": [
        "mireye-mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "com-mireye-earth": {
      "command": "uvx",
      "args": [
        "mireye-mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add com-mireye-earth -- uvx mireye-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-mireye-earth": {
      "type": "local",
      "command": [
        "uvx",
        "mireye-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add com-mireye-earth --command uvx --arg mireye-mcp
# ~/.hermes/config.yaml
mcp_servers:
  com-mireye-earth:
    command: "uvx"
    args: ["mireye-mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "com-mireye-earth": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "mireye-mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add com-mireye-earth -t stdio -c uvx -a mireye-mcp
// mcp.json
{
  "mcpServers": {
    "com-mireye-earth": {
      "command": "uvx",
      "args": [
        "mireye-mcp"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 19 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 −2
    • Stability: pass → 0.83 functional
  • 17 Sept 26 0
    • Stability: 0.97 → pass security
  • 16 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 15 Sept 26 +15
    • Malware scan: unverified → pass security
  • 14 Sept 26 −15
    • Malware scan: pass → unverified security
  • 13 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 11 Sept 26 −2
    • Stability: pass → 0.80 functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Analysed pypi/mireye-mcp@0.5.0

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend allowlisted hatchling.build

Background: Why install scripts are a supply-chain risk →

Dependencies 29 packages
Packages resolved 29
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 6 exposed · ~1,626 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
mireye_ask ~169

Answer a natural-language question about a US location, with citations to authoritative federal data sources. Give EITHER lat+lng OR address, never both. Returns the answer plus per-citation provenance (source, source URL, fetched_at, confidence). Use this when the caller has a specific question about a place (e.g. 'is this in a flood zone?', 'what's the wildfire risk here?'). When you pass an address, the response carries a `geocode` block: if `parcel_grade` is false the location was estimated from the street and can be ~2.9 km out in rural areas, and the answer says so.

NameTypeReqDescription
address
lat
lng
questionstringyesNatural-language question about the coordinate.

Structured output declared, but exposes no named fields.

No examples provided.

mireye_fetch ~161

Fetch specific data fields at a US location with full provenance per field. Give EITHER lat+lng OR address, never both. Use this when the caller knows exactly which fields they need (e.g. 'elevation and slope at this point') or wants to power a custom workflow. Each field includes its value, source, source URL, fetched_at timestamp, and confidence. When you pass an address, the response carries a `geocode` block: check `parcel_grade` before trusting parcel-specific fields — a false value means the coordinate was estimated from the street and can be ~2.9 km out in rural areas.

NameTypeReqDescription
address
fields
lat
lng
preset

Structured output declared, but exposes no named fields.

No examples provided.

mireye_field_request_status ~279

Poll the status of a field request filed with mireye_request_field: status, queue position, the promised estimated_ready_at (fixed at acceptance, never recomputed on poll), and -- once status is 'live' -- the resume call (a ready-to-send /v1/fetch request) that answers the original ask. Store request_id in durable task state, not conversation context: builds run on a scale of hours and the filing session will likely be gone before one finishes. Status vocabulary: 'received'/'screening' (still being screened; check waiting_on -- 'operator' means screening failed and a human has to look), 'matched' (the catalog already answered it, use resume), 'awaiting_confirm' (a near-miss or clarify needs you), 'rejected' (typed codes in disposition, terminal), 'queued'/'claimed'/'building'/'in_review'/'approved'/'publishing' (a build is in progress), 'live' (done, resume works now), 'blocked'/'expired' (terminal, no build). Requests are visible only to the credential that filed them; an id that doesn't exist -- or belongs to someone else -- is the same 404, never a 403 (a 403 would confirm the id exists).

NameTypeReqDescription
request_idstringyes

Structured output declared, but exposes no named fields.

No examples provided.

mireye_geocode ~203

Resolve a US street address to a coordinate, with the quality of that coordinate. Feed lat/lng to mireye_fetch or mireye_ask. ALWAYS check accuracy_type before trusting the result: 'rooftop' is on the parcel, but 'range_interpolation' is estimated along a street centerline and can be ~2.9 km out in rural areas — far enough to describe a neighbouring property instead. An address that can only be placed at a ZIP/city/county centroid is REJECTED as address_too_coarse rather than returned — if you get that, ask the user for a more complete address instead of retrying. The address you send is retained alongside the coordinate it resolves to, so a result can be audited later; pass lat/lng instead if that does not suit the caller.

NameTypeReqDescription
addressstringyesUS street address. Include a city+state or a ZIP — the upstream cannot place a bare street line.

Structured output declared, but exposes no named fields.

No examples provided.

mireye_lookup ~415

Turn a messy human locator (address, "lat,lng", or APN) into canonical join keys: a coordinate, resolved address, and -- when the geocode is parcel-quality -- a parcel (id, boundary, owner). Unlike mireye_geocode, this detects genuine ambiguity across multiple candidate matches instead of trusting a single top result, so an underspecified input like '1100 King St W, Toronto' returns disposition='clarify' with candidates instead of silently landing on the wrong Toronto. ALWAYS check `disposition` first: 'resolved' carries a coordinate and confidence (plus a parcel when safe); 'clarify' means the input is genuinely ambiguous -- present the candidates to the user, never auto-pick one; 'no_match' is an honest failure with a `reason`. A parcel-lookup failure never demotes a good geocode -- 'resolved' can still come back with `parcel_unavailable: true` and a `parcel_unavailable_reason` (e.g. the vendor's own quota being exhausted) rather than an error. Swapped coordinates (e.g. lng where lat belongs) are rejected as a bounds error, never silently treated as a nearest-match. APN-only lookup is not supported yet -- supply an address or coordinate. A 'resolved' response also carries free area context gathered concurrently with the parcel lookup: jurisdiction codes (state, block/block-group, congressional district, CBSA/metro area) alongside county/tract, elevation and FEMA flood-zone fields, a county_market bundle (population, growth, employment, home-price change, median income), Opportunity Zone status, and an IANA timezone -- every one of these degrades independently to null on its own failure and never blocks the primary coordinate/parcel answer.

NameTypeReqDescription
include_parcelboolean
inputstringyesUS street address, "lat,lng" coordinate pair, or APN. Include a city+state or a ZIP for an address -- the upstream cannot place a bare street line.

Structured output declared, but exposes no named fields.

No examples provided.

mireye_request_field ~399

Ask Mireye for a data field it doesn't have yet, in plain language, at one or more example locations. If the catalog already answers it you get the value now with a citation (disposition 'matched_existing'/'partial') and never spend a build; if something close exists you get 'near_miss_confirm' to accept or reject; otherwise the field is queued to build and you get a request_id to poll with mireye_field_request_status. ALWAYS pass idempotency_key for agent-originated requests: the same key replays the existing request's state instead of filing a second build. Answering use_case/decision_threshold (what decision this feeds, and the value that flips it) is optional but sharply improves match quality and build speed. example_locations (1-10 entries) each carry exactly one of address, lat+lng, or polygon, plus optional claimed_value/note -- see docs.mireye.ai/api-reference/field-requests for the full entry shape. requested_fields optionally pre-splits a bundled ask into atomic sub-questions (plain-language asks); the server decomposes bundles anyway. extra carries the rarer structured fields verbatim (area_of_interest, expected_volume, freshness, constraints, known_sources, output_preference) -- same doc has their shapes. A 'rejected' disposition carries a typed rejection_code and routing_hint, never a bare no; a genuinely ambiguous location returns a stateless 'clarify' with candidates instead of guessing. Filing a request never spends /v1/fetch credits; plans carry a separate included build allowance.

NameTypeReqDescription
callback_email
callback_webhook_url
context_blob
deadline
decision_threshold
descriptionstringyes
example_locationsarrayyes
extra
idempotency_key
requested_fields
use_case

Structured output declared, but exposes no named fields.

No examples provided.

Common questions

What is the com.mireye/earth MCP server?

com.mireye/earth is an MCP server listed in the public MCP registry as com.mireye/earth. MCP server for Mireye Earth, federal-source-cited geospatial data for any MCP-aware agent. This page covers its PyPI package (mireye-mcp).

Is the com.mireye/earth MCP server safe to use?

com.mireye/earth scores 82 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the com.mireye/earth MCP server expose?

com.mireye/earth exposes 6 tools: mireye_ask, mireye_fetch, mireye_geocode, mireye_lookup, mireye_request_field, mireye_field_request_status. Their descriptions and schemas cost roughly 1,626 tokens of context every time the server is loaded.

Is the com.mireye/earth MCP server still maintained?

com.mireye/earth is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the com.mireye/earth MCP server under?

com.mireye/earth declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.