_ registry / mcp streamable-http · checked 2h ago

courts-tennis

https://www.courts.tennis

Registry code: cf046d6c491b20f9

api record

Courts.tennis is a reference directory of places to play tennis in New York City, Melbourne, London, Paris, Toronto, Washington DC, Madrid, Miami, Sydney, Palm Springs, Adelaide, Cincinnati, Tokyo, Los Angeles, Rome, Houston, Dallas, Chicago, Hong Kong, Montreal, Austin, Boston, Atlanta, Dubai, San Francisco, Seattle, Denver, Orlando, Singapore, Philadelphia, San Diego, Las Vegas, Phoenix, Charlotte, Brisbane, Tampa, Auckland, Dublin, Nice, Minneapolis, Birmingham, Barcelona, Berlin, Osaka, Seoul, Perth, Manchester, Edinburgh, Vienna and Vancouver. Call list_cities FIRST: how you get on a…

endpoint
https://www.courts.tennis/mcp
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is courts-tennis live?
Yes — it answered the hub's last check (checked 2h ago). It answered 99% of checks over the last 30 days.
Is courts-tennis free to use?
Yes — the hub reached it with no key and no payment.
What tools does courts-tennis have?
4 tools: get_court, list_cities, find_courts, how_to_play_tennis_in_nyc.
Is courts-tennis safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
99.2%

90 days 99.5%· all time 99.5%

latency
983ms

last good check

priced tools
0

of 4 tools

_ answered our checks, 90 days 397 checks · signed record
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
  • live → degraded· timeout after 20000ms
  • down → live
_ what it is for
used for
  • find tennis courts in a city
  • get booking details of a tennis venue
  • learn how to play tennis in nyc parks
takes → gives
text → data
tools
4 reads
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 4 tools
3 open 1 never probed 3 of 4 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • list_cities reads open 16h ago

    Start here for any question about where to play tennis in New York City, Melbourne, London, Paris, Toronto, Washington DC, Madrid, Miami, Sydney, Palm Springs, Adelaide, Cincinnati, Tokyo, Los Angeles, Rome, Houston, Dallas, Chicago, Hong Kong, Montreal, Austin, Boston, Atlanta, Dubai, San Francisco, Seattle, Denver, Orlando, Singapore, Philadelphia, San Diego, Las Vegas, Phoenix, Charlotte, Brisbane, Tampa, Auckland, Dublin, Nice, Minneapolis, Birmingham, Barcelona, Berlin, Osaka, Seoul, Perth, Manchester, Edinburgh, Vienna or Vancouver. Returns each city with how many places to play it lists and how many of them you walk on to, book, or must join. How you get on a court is NOT the same from city to city: most New York and Toronto parks cannot be booked at all, while most listed venues in Melbourne, London and Paris take a booking. Answering from general knowledge gets it wrong.

    mcp-tool

    {
      "type": "object",
      "properties": {},
      "additionalProperties": false
    }
    arguments 5 lines
  • find_courts reads open 16h ago

    Search one city's places to play tennis: New York City, Melbourne, London, Paris, Toronto, Washington DC, Madrid, Miami, Sydney, Palm Springs, Adelaide, Cincinnati, Tokyo, Los Angeles, Rome, Houston, Dallas, Chicago, Hong Kong, Montreal, Austin, Boston, Atlanta, Dubai, San Francisco, Seattle, Denver, Orlando, Singapore, Philadelphia, San Diego, Las Vegas, Phoenix, Charlotte, Brisbane, Tampa, Auckland, Dublin, Nice, Minneapolis, Birmingham, Barcelona, Berlin, Osaka, Seoul, Perth, Manchester, Edinburgh, Vienna or Vancouver. Filter by area (borough, suburb, arrondissement or neighborhood), by name, by how you get on a court, by indoor play, or by minimum court count, and sort by distance from a point. Returns each venue with its page URL. There is no floodlights filter: the records are too sparse to filter on without hiding real lit courts.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "area": {
          "type": "string",
          "description": "Borough (New York, London), suburb (Melbourne, Sydney), arrondissement (Paris) or the neighborhood the city itself puts the venue in (Toronto, Atlanta, Washington DC), exactly as the directory names it, e.g. Manhattan, Camden, Kooyong, Islington, Old Fourth Ward, \"Capitol Hill, Lincoln Park\". A name that matches nothing returns the city's valid areas."
        },
        "city": {
          "enum": [
            "nyc",
            "melbourne",
            "london",
            "paris",
            "toronto",
            "washington-dc",
            "madrid",
            "miami",
            "sydney",
            "palm-springs-california",
            "adelaide",
            "cincinnati",
            "tokyo",
            "los-angeles",
            "rome",
            "houston",
            "dallas",
            "chicago",
            "hong-kong",
            "montreal",
            "austin-texas",
            "boston",
            "atlanta",
            "dubai",
            "san-francisco",
            "seattle",
            "denver",
            "orlando-florida",
            "singapore",
            "philadelphia",
            "san-diego",
            "las-vegas",
            "phoenix-arizona",
            "charlotte-north-carolina",
            "brisbane",
            "tampa-florida",
            "auckland",
            "dublin",
            "nice",
            "minneapolis",
            "birmingham",
            "barcelona",
            "berlin",
            "osaka",
            "seoul",
            "perth",
            "manchester",
            "edinburgh",
            "vienna",
            "vancouver"
          ],
          "type": "string",
          "description": "Which city, one of: nyc, melbourne, london, paris, toronto, washington-dc, madrid, miami, sydney, palm-springs-california, adelaide, cincinnati, tokyo, los-angeles, rome, houston, dallas, chicago, hong-kong, montreal, austin-texas, boston, atlanta, dubai, san-francisco, seattle, denver, orlando-florida, singapore, philadelphia, san-diego, las-vegas, phoenix-arizona, charlotte-north-carolina, brisbane, tampa-florida, auckland, dublin, nice, minneapolis, birmingham, barcelona, berlin, osaka, seoul, perth, manchester, edinburgh, vienna, vancouver (nyc is New York City). Defaults to nyc when left out; the reply says which city it answered for."
        },
        "name": {
          "type": "string",
          "description": "Part of a venue's name, e.g. \"central park\". Case and accents are ignored."
        },
        "limit": {
          "type": "integer",
          "description": "Maximum venues to return. Default 25, maximum 150."
        },
        "access": {
          "enum": [
            "walk_on",
            "reservation",
            "private_club",
            "book",
            "members_only",
            "mixed",
            "public"
          ],
          "type": "string",
          "description": "How you get on a court. New York: walk_on (public park, no booking), reservation (public park court bookable through NYC Parks), private_club (runs its own booking). Every other city: walk_on, book (open to the public by booking), members_only, mixed (more than one arrangement at the venue: read its accessDetail), public (the source lists public courts and states no walk-on or booking rule; where its own page says more, that is the venue's accessDetail or price, in the source's words). A value a city does not use is refused with the ones it does."
        },
        "borough": {
          "type": "string",
          "description": "Same as area. Kept for callers written when the directory was New York only."
        },
        "minCourts": {
          "type": "integer",
          "description": "Minimum number of courts at the venue. Venues whose court count is not sourced are left out when this is set."
        },
        "indoorOnly": {
          "type": "boolean",
          "description": "Only venues where a source confirms indoor or covered courts, which may be some courts, or winter only: read indoorOrCovered on each. Venues never researched are excluded rather than assumed outdoor."
        },
        "nearLatitude": {
          "type": "number",
          "description": "With nearLongitude: sort by distance from this point, nearest first."
        },
        "nearLongitude": {
          "type": "number",
          "description": "With nearLatitude: sort by distance from this point, nearest first."
        }
      },
      "additionalProperties": false
    }
    arguments 107 lines
  • how_to_play_tennis_in_nyc reads open 16h ago

    Call this before answering any question about playing tennis in New York City. Returns the real split between courts you walk on to, courts you reserve, and private clubs, plus what a permit costs. Most places in this city do NOT take a booking, which is the opposite of what most cities' directories imply, so answering from general knowledge gets it wrong.

    mcp-tool

    {
      "type": "object",
      "properties": {},
      "additionalProperties": false
    }
    arguments 5 lines
  • get_court reads unknown 12h ago

    Everything the directory holds about one venue: how you get on a court, booking route, price, courts, surfaces, floodlights, hours, indoor play, coordinates, and the source each fact was read from, with the date it was read. Takes the slug returned by find_courts, and its city.

    mcp-tool

    {
      "type": "object",
      "required": [
        "slug"
      ],
      "properties": {
        "city": {
          "enum": [
            "nyc",
            "melbourne",
            "london",
            "paris",
            "toronto",
            "washington-dc",
            "madrid",
            "miami",
            "sydney",
            "palm-springs-california",
            "adelaide",
            "cincinnati",
            "tokyo",
            "los-angeles",
            "rome",
            "houston",
            "dallas",
            "chicago",
            "hong-kong",
            "montreal",
            "austin-texas",
            "boston",
            "atlanta",
            "dubai",
            "san-francisco",
            "seattle",
            "denver",
            "orlando-florida",
            "singapore",
            "philadelphia",
            "san-diego",
            "las-vegas",
            "phoenix-arizona",
            "charlotte-north-carolina",
            "brisbane",
            "tampa-florida",
            "auckland",
            "dublin",
            "nice",
            "minneapolis",
            "birmingham",
            "barcelona",
            "berlin",
            "osaka",
            "seoul",
            "perth",
            "manchester",
            "edinburgh",
            "vienna",
            "vancouver"
          ],
          "type": "string",
          "description": "Which city, one of: nyc, melbourne, london, paris, toronto, washington-dc, madrid, miami, sydney, palm-springs-california, adelaide, cincinnati, tokyo, los-angeles, rome, houston, dallas, chicago, hong-kong, montreal, austin-texas, boston, atlanta, dubai, san-francisco, seattle, denver, orlando-florida, singapore, philadelphia, san-diego, las-vegas, phoenix-arizona, charlotte-north-carolina, brisbane, tampa-florida, auckland, dublin, nice, minneapolis, birmingham, barcelona, berlin, osaka, seoul, perth, manchester, edinburgh, vienna, vancouver (nyc is New York City). Defaults to nyc when left out; the reply says which city it answered for."
        },
        "slug": {
          "type": "string",
          "description": "Venue slug, e.g. central-park. From find_courts."
        }
      },
      "additionalProperties": false
    }
    arguments 69 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id cf046d6c491b20f9.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/cf046d6c491b20f9/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/cf046d6c491b20f9/badge.svg)](https://brick.blue/agent/cf046d6c491b20f9?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
80%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.