# Close API (remote · mcp.close.city)

Walk, bike, and transit travel times from every US census block to nearby amenities.

- Trust score: 64/100 (medium)
- Change this week: +2
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `mcp.close.city`: 64/100 (this document), [markdown](https://verifymcp.io/servers/city-close-close-api/mcp.md), [page](https://verifymcp.io/servers/city-close-close-api/mcp)

## Channel facts

- Endpoint: `https://mcp.close.city/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.2.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 10 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 74/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1260 tokens (~126/item across 10 items; 10 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 91/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 73% of tool parameters carry a description.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http city-close-close-api https://mcp.close.city/mcp
```

### Codex

```toml
[mcp_servers.city-close-close-api]
url = "https://mcp.close.city/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "city-close-close-api": {
      "type": "remote",
      "url": "https://mcp.close.city/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add city-close-close-api --url https://mcp.close.city/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  city-close-close-api:
    url: "https://mcp.close.city/mcp"
```

### Other

```json
{
  "mcpServers": {
    "city-close-close-api": {
      "type": "http",
      "url": "https://mcp.close.city/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 64, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-01 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 62, −2)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 64, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-28 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 62, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 61)

First indexed and scored.

## MCP tools (10)

### `find_place` (~91 tokens)

Look up a US city or town by name (free, no key). Returns matches with their census place GEOID and centre point (lon/lat). The entry point: feed a GEOID to blocks_in_area, or a centre to walkability_summary.

Input parameters:

- `limit` (integer): Max matches (1-20).
- `query` (string, required): City or town name, e.g. 'Providence'.

### `get_catalog` (~52 tokens)

List the travel modes and the destination-type taxonomy (free, no key). Use it to resolve type names to the numeric ids the other tools take. Modes are walk, bike, transit — there is no drive mode.

### `walkability_summary` (~204 tokens)

Fastest travel time from a location to each destination category, by mode (metered: 1 token per returned row). One origin: block_geoid or lat+lon. Many origins (up to 250): block_geoids or points — one batch call and one rate-limit request, with rows tagged by origin. Batching saves requests and context, not tokens: it still charges per row. A non-empty truncated (+ truncated_reason) means the balance or row budget cut the batch short. A missing category means it is not reachable within 30 minutes.

Input parameters:

- `block_geoid` (string): 15-digit census block GEOID.
- `block_geoids` (array): Many block GEOIDs — one batch call.
- `lat` (number)
- `lon` (number)
- `mode` (string): walk, bike, or transit. Omit for all three.
- `points` (array): Many lat/lon points — one batch call.

### `nearby_pois` (~243 tokens)

Nearby points of interest and the travel time to each, from a location (metered: 1 token per returned row). One origin: block_geoid or lat+lon; keep limit small to control spend and context size. Many origins (up to 250): block_geoids or points — one batch call and one rate-limit request, rows tagged by origin, no limit/pagination, so filter with type/mode/max_minutes. Batching saves requests and context, not tokens: it still charges per row. A non-empty truncated (+ truncated_reason) means the balance or row budget cut the batch short.

Input parameters:

- `block_geoid` (string)
- `block_geoids` (array): Many block GEOIDs — one batch call.
- `lat` (number)
- `limit` (integer): Max rows (first page).
- `lon` (number)
- `max_minutes` (integer): Upper bound on travel time (<=30).
- `mode` (string): walk, bike, or transit.
- `points` (array): Many lat/lon points — one batch call.
- `type` (integer): Destination type id (see get_catalog).

### `isochrone` (~151 tokens)

The area reachable from a location within a time budget, as GeoJSON contours (metered: 10 tokens per contour). Give block_geoid or lat+lon. Defaults to a single 30-minute contour; ask for more only when needed (bodies can be large).

Input parameters:

- `block_geoid` (string)
- `contours` (array): Up to four ascending thresholds, instead of minutes.
- `direction` (string): 'from' the origin (default) or 'to' it.
- `lat` (number)
- `lon` (number)
- `minutes` (integer): A single threshold (1-60).
- `mode` (string): walk, bike, or transit.

### `blocks_in_area` (~163 tokens)

Per-block travel times for every census block in an area (metered: 1 token per returned row). Give place_geoid (from find_place) for a whole city, or center {lat, lon} + radius_m. Rows carry a numeric mode_id.

Input parameters:

- `lat` (number): Circle centre latitude (with lon + radius_m).
- `limit` (integer): Max rows (first page).
- `lon` (number): Circle centre longitude.
- `mode` (string): walk, bike, or transit.
- `place_geoid` (string): Census place GEOID (a whole city/town).
- `radius_m` (number): Circle radius in metres (<=28000).
- `type` (integer): Destination type id (see get_catalog).

### `get_token_balance` (~38 tokens)

Check the token balance of the API key in use, without spending any tokens. Works even at a zero balance. Requires the Authorization bearer key.

### `request_sign_in` (~77 tokens)

Start free sign-up for the user: email them a six-digit code. The user must read the code from their own inbox and give it to you, then call redeem_code. This is how an agent gets the user an API key (5,000 free tokens, no card).

Input parameters:

- `email` (string, required): The user's email address.

### `redeem_code` (~92 tokens)

Complete sign-up with the six-digit code the user received, and return a new API key (shown once). Call request_sign_in first. The key grants 5,000 free tokens; store it and pass it as the Authorization bearer on future calls.

Input parameters:

- `code` (string, required): The six-digit code from the email.
- `email` (string, required)
- `label` (string): Optional label for the key.

### `join_close_plus` (~97 tokens)

Get a Stripe Checkout URL for the Close+ membership ($10/month: 5,000 API tokens granted monthly plus member features on the close.city map). The user pays in their own browser: give them the returned URL and stop. Needs a fresh six-digit code from request_sign_in, read by the user from their own inbox.

Input parameters:

- `code` (string, required): The six-digit code from the email.
- `email` (string, required)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/city-close-close-api/mcp#diagnostics

## Score history

- 2026-08-03: 64
- 2026-08-02: 63
- 2026-08-01: 63
- 2026-07-31: 62
- 2026-07-30: 64
- 2026-07-29: 63
- 2026-07-28: 63
- 2026-07-27: 62
- 2026-07-26: 61

## Links

- Remote endpoint: https://mcp.close.city/mcp
- Repository: https://github.com/henryspatialanalysis/wtm.api
- Website: https://docs.close.city/ai/
- Changelog RSS feed: https://verifymcp.io/servers/city-close-close-api/mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/city-close-close-api/mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/city-close-close-api/mcp