# Should I Live Here?

> Rank and compare US counties on health, hazards, crime, rent, internet and air, from public data.

- name: io.github.gdtilghman/should-i-live-here
- version: 0.1.0
- connection class: R0 (autonomous)
- trust: 97/100
- quality: 94/100 (new)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.gdtilghman%2Fshould-i-live-here
- tools: https://api.protogrid.dev/v1/servers/io.github.gdtilghman%2Fshould-i-live-here/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "should-i-live-here": {
      "type": "http",
      "url": "https://mcp.shouldilivehere.org/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 100
- freshness: 100
- provenance: 90
- drivers: +repository +namespace-matches-repo +website +reachable +uptime-100% +updated-4d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 94/100 (new)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 6 of 6 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 927 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: n/a (weight 15)

- n/a `stability.changes`, `stability.rug_pull`: tool history recorded for 1 of the 7 days needed

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 6, about 927 tokens to load them all
- tool set hash: 53583e21625ee0fae3244f384c484520
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.gdtilghman/should-i-live-here.svg)](https://protogrid.dev/servers/io.github.gdtilghman/should-i-live-here)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://mcp.shouldilivehere.org/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (6)

- `compare_counties`: Compare 2 to 10 counties side by side on chosen measures.
- `find_measure`: Map plain words (for example "internet", "cancer", "crime", "cost of living") to atlas measure keys. Words the atlas has no data for come back in not_available. Those words are counted (word and day only, no personal data) so the owner can consider new data.
- `get_county`: All atlas values for one county, by 5-digit FIPS or "Name, State" (state name or postal code). Missing values stay null with their status.
- `list_measures`: List the county measures in the Should I Live Here? atlas: key, label, unit, period, direction, and how many of the 3,107 counties have a value. Optional text filter.
- `rank_counties`: Rank counties in the lower 48 states on weighted measures, with the same scoring as the site's My priorities. Rank 1 has the lowest concern score. Counties with missing data are left out, never scored as low. Optional limits and state filter. Read the cautions in every answer.
- `request_measure`: Report a measure a user wanted that the atlas lacks, for example "schools". Only the measure name and the day are counted.