ZBS Index What actually exists in applied AI, with the source next to it

mcp server

Close API

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

Description as published by the maintainer. Source

  • version 1.2.0
  • archived

archived — The linked repository returns 404. It was deleted, renamed or made private.

What this server can do

10 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.

blocks_in_area(lat, lon, mode, type, limit, radius_m, place_geoid)
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.
find_place(limit, query)
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. Required: query.
get_catalog
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.
get_token_balance
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.
isochrone(lat, lon, mode, minutes, contours, direction, block_geoid)
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).
join_close_plus(code, email)
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. Required: email, code.
nearby_pois(lat, lon, mode, type, limit, points, block_geoid, max_minutes, block_geoids)
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.
redeem_code(code, email, label)
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. Required: email, code.
request_sign_in(email)
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). Required: email.
walkability_summary(lat, lon, mode, points, block_geoid, block_geoids)
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.

Last successful function declaration observed on . Source: https://mcp.close.city/mcp. We list what the server declared; we do not call any of these functions.

Endpoint status observed on . Source: https://mcp.close.city/mcp.

Signals

These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.

Signal Value What it measures Window Observed Source
Latest published version 1.2.0 Latest version string the maintainer published to the registry. as of fetch Model Context Protocol
Registry record last updated 2026-07-24 When the registry record was last updated by its maintainer. point in time Model Context Protocol
First listed in the MCP Registry 2026-07-24 Date this server was first published to the official MCP Registry. Not a usage or quality measure. point in time Model Context Protocol
repository status not_found GitHub returned 404 for the repository the maintainer listed. The project was deleted, renamed or made private, so the listing points at nothing. as of fetch GitHub
mcp tools declared 10 tools Number of functions the server itself declared when asked to list them. This is what the server offers an agent, not a measure of how well any of them work. as of probe mcp.close.city
mcp endpoint status ok The server listed 10 functions when asked. as of probe mcp.close.city

Where to get it

This record as data

Every field on this page, with its source and observation date, is in the catalog JSON. Fetch the whole kind at once instead of parsing this HTML.

GET /api/v1/entries/mcp_server.json

Sources

  1. henryspatialanalysis/wtm.api on GitHub — GitHub, observed , trust tier 3.
  2. Tools declared by the MCP server at https://mcp.close.city/mcp — mcp.close.city, observed , trust tier 1.
  3. Official MCP Registry — Model Context Protocol, observed , trust tier 1.