_ registry / mcp streamable-http · checked 47m ago

clousd

https://api.clousd.com

Registry code: fa89b6b11977c08f

api record

Real Android phones in the cloud. Call observe before acting; prefer act tap_text over coordinates; use snapshots restore to start each run from the same state.

endpoint
https://api.clousd.com/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 clousd live?
Yes — it answered the hub's last check (checked 47m ago). It answered 100% of checks over the last 30 days.
Is clousd free to use?
Not measured yet.
What tools does clousd have?
4 tools: devices, observe, act, snapshots.
Is clousd 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
100%

90 days 100%· all time 100%

latency
192ms

last good check

priced tools
0

of 4 tools

_ answered our checks, 90 days 1 checks · signed record
  • unknown → live
_ 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
4 never probed 0 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.

  • devices unknown never probed

    Phones this API key can use. op=list (default): name, state (running / stopped / starting / error), model, Android, network of each phone. op=start / op=stop with `device`: start a stopped phone (waits until it has booted, one to three minutes) or stop one (a stopped phone keeps its state and costs nothing).

    mcp-tool

    {
      "type": "object",
      "title": "devicesArguments",
      "properties": {
        "op": {
          "type": "string",
          "title": "Op",
          "default": "list"
        },
        "device": {
          "type": "string",
          "title": "Device",
          "default": ""
        }
      }
    }
    arguments 16 lines
  • observe unknown never probed

    Look at the phone: a fresh screenshot plus (with_text) the app on screen and its elements with centre coordinates. Give tap/swipe coordinates in this image's pixels.

    mcp-tool

    {
      "type": "object",
      "title": "observeArguments",
      "required": [
        "device"
      ],
      "properties": {
        "device": {
          "type": "string",
          "title": "Device"
        },
        "with_text": {
          "type": "boolean",
          "title": "With Text",
          "default": true
        }
      }
    }
    arguments 18 lines
  • act unknown never probed

    Do one thing on the phone, then wait until the screen settles. action is one of: tap (x, y) · swipe (x, y, x2, y2, ms) · scroll (text=down|up) · tap_text (text: tap the element whose text contains it - usually more reliable than coordinates) · wait_text (text, timeout up to 120 s) · type (text into the focused field, any language) · key (text=home|back|recents|enter|tab|del|menu|power|volume_up|volume_down) · open_app (text=package, e.g. com.android.chrome) · close_app (text=package) · open_url (text=https://…) · installed (list apps you can open). Coordinates are in the pixels of the last observe image.

    mcp-tool

    {
      "type": "object",
      "title": "actArguments",
      "required": [
        "device",
        "action"
      ],
      "properties": {
        "x": {
          "anyOf": [
            {
              "type": "number"
            },
            {
              "type": "null"
            }
          ],
          "title": "X",
          "default": null
        },
        "y": {
          "anyOf": [
            {
              "type": "number"
            },
            {
              "type": "null"
            }
          ],
          "title": "Y",
          "default": null
        },
        "ms": {
          "type": "integer",
          "title": "Ms",
          "default": 300
        },
        "x2": {
          "anyOf": [
            {
              "type": "number"
            },
            {
              "type": "null"
            }
          ],
          "title": "X2",
          "default": null
        },
        "y2": {
          "anyOf": [
            {
              "type": "number"
            },
            {
              "type": "null"
            }
          ],
          "title": "Y2",
          "default": null
        },
        "text": {
          "type": "string",
          "title": "Text",
          "default": ""
        },
        "action": {
          "type": "string",
          "title": "Action"
        },
        "device": {
          "type": "string",
          "title": "Device"
        },
        "timeout": {
          "type": "integer",
          "title": "Timeout",
          "default": 30
        }
      }
    }
    arguments 81 lines
  • snapshots unknown never probed

    Saved states of a phone, for starting every run from the same point. op=list (default): id, created, android, current, restorable. op=save: save the current state. op=restore with snapshot_id: reset the phone to that state. op=clone with snapshot_id and new_name (letters and digits, up to 16): a new phone from that state.

    mcp-tool

    {
      "type": "object",
      "title": "snapshotsArguments",
      "required": [
        "device"
      ],
      "properties": {
        "op": {
          "type": "string",
          "title": "Op",
          "default": "list"
        },
        "device": {
          "type": "string",
          "title": "Device"
        },
        "new_name": {
          "type": "string",
          "title": "New Name",
          "default": ""
        },
        "snapshot_id": {
          "type": "string",
          "title": "Snapshot Id",
          "default": ""
        }
      }
    }
    arguments 28 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 fa89b6b11977c08f.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/fa89b6b11977c08f/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/fa89b6b11977c08f/badge.svg)](https://brick.blue/agent/fa89b6b11977c08f?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.