_ registry / mcp streamable-http · checked 16h ago

getsize

https://www.getsize.shoes

Registry code: c94b866ff55a28b9

api record

GetSize finds the right shoe size across brands. Start with start_session, then ask which shoes the person already owns and fit well: the recommendation is built from those rather than from a measurement, and one good shoe is worth more than a guess. Identify every shoe with find_shoe before adding it. Sizes come from the brand's published size chart — for the exact model where one exists, otherwise the brand's general chart — so say which shoe an answer came from.

endpoint
https://www.getsize.shoes/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 getsize live?
Yes — it answered the hub's last check (checked 16h ago). It answered 67% of checks over the last 30 days.
Is getsize free to use?
Yes — the hub reached it with no key and no payment.
What tools does getsize have?
8 tools: add_shoe, list_shoes, remove_shoe, recommend_size, start_session, set_foot_measurement, rate_fit, find_shoe.
Is getsize 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
66.7%

90 days 66.7%· all time 66.7%

latency
135ms

last good check

priced tools
0

of 8 tools

_ answered our checks, 90 days 3 checks · signed record
  • degraded → live
  • unknown → degraded· timeout after 20000ms
_ 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 8 tools
1 open 7 never probed 1 of 8 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.

  • find_shoe open 16h ago

    Identifies a shoe one answer at a time. Call it with no answers to get the list of brands, then again with each answer appended: brand, then model, then colourway, then size. It replies with the next question and the answers allowed, until the shoe is identified. Append each option's id, not the name shown beside it: the name is for the person, the id is the answer. Always work through this rather than guessing, because only the answers it offers exist and a shoe we do not hold cannot be sized.

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {
    "answers": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "The answers so far, in order. Each is the id of an option the previous call offered. Empty or omitted to start."
    },
    "purpose": {
      "enum": [
        "own",
        "considering"
      ],
      "type": "string",
      "description": "What the shoe is for. A shoe they own needs a size, so the walk asks for one. A shoe they are considering does not, because working the size out is the point, and that walk finishes a step earlier."
    }
  },
  "additionalProperties": false
}
    arguments 22 lines
  • add_shoe unknown never probed

    Records a shoe the person owns and the size they wear in it. This is what every recommendation is built from, so ask for at least one shoe that fits them well before calling recommend_size. Use find_shoe first to get the identifiers.

    mcp-tool

    {
  "type": "object",
  "required": [
    "sessionId",
    "answers"
  ],
  "properties": {
    "answers": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "The complete set of answers from find_shoe, including the size they wear. find_shoe says when it is complete."
    },
    "sessionId": {
      "type": "string",
      "description": "The session id returned by start_session. Everything the person tells you is stored against it, and it is the only thing linking one call to the next."
    }
  },
  "additionalProperties": false
}
    arguments 21 lines
  • list_shoes unknown 16h ago

    Shows what the person has told us they own, with the id needed to remove one or to record how it fits.

    mcp-tool

    {
  "type": "object",
  "required": [
    "sessionId"
  ],
  "properties": {
    "sessionId": {
      "type": "string",
      "description": "The session id returned by start_session. Everything the person tells you is stored against it, and it is the only thing linking one call to the next."
    }
  },
  "additionalProperties": false
}
    arguments 13 lines
  • remove_shoe unknown never probed

    Removes a shoe the person no longer wants counted, using the id from list_shoes. Anything they said about how it fits goes with it.

    mcp-tool

    {
  "type": "object",
  "required": [
    "sessionId",
    "shoeId"
  ],
  "properties": {
    "shoeId": {
      "type": "integer",
      "description": "The id from list_shoes."
    },
    "sessionId": {
      "type": "string",
      "description": "The session id returned by start_session. Everything the person tells you is stored against it, and it is the only thing linking one call to the next."
    }
  },
  "additionalProperties": false
}
    arguments 18 lines
  • recommend_size unknown 16h ago

    Works out which size to buy in a shoe the person does not own yet, from the shoes they do own and any foot measurement. Needs at least one owned shoe or a measurement first. Returns the size and what it was based on.

    mcp-tool

    {
  "type": "object",
  "required": [
    "sessionId",
    "answers"
  ],
  "properties": {
    "answers": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "The answers from find_shoe identifying the shoe they are considering. A size is not needed here: working it out is the point."
    },
    "sessionId": {
      "type": "string",
      "description": "The session id returned by start_session. Everything the person tells you is stored against it, and it is the only thing linking one call to the next."
    }
  },
  "additionalProperties": false
}
    arguments 21 lines
  • start_session unknown never probed

    Call this first, once per conversation. Returns a session id that every other tool needs. No personal data is required and none is asked for.

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {},
  "additionalProperties": false
}
    arguments 6 lines
  • set_foot_measurement unknown never probed

    Records the length of the person's foot in millimetres, heel to longest toe. More precise than a shoe they own, and worth asking for when they have no shoes to give or the answer matters. A measurement and owned shoes can both be present.

    mcp-tool

    {
  "type": "object",
  "required": [
    "sessionId",
    "lengthMm"
  ],
  "properties": {
    "lengthMm": {
      "type": "integer",
      "description": "Foot length in millimetres. A typical adult is between 220 and 320."
    },
    "sessionId": {
      "type": "string",
      "description": "The session id returned by start_session. Everything the person tells you is stored against it, and it is the only thing linking one call to the next."
    }
  },
  "additionalProperties": false
}
    arguments 18 lines
  • rate_fit unknown never probed

    Records what the person says about wearing a shoe they own: whether it is the right length and width. This is the most valuable thing they can tell us, because it is the difference between what the chart says and what happened. Use the shoe id from list_shoes.

    mcp-tool

    {
  "type": "object",
  "required": [
    "sessionId",
    "shoeId",
    "dimension",
    "verdict"
  ],
  "properties": {
    "shoeId": {
      "type": "integer",
      "description": "The id from list_shoes."
    },
    "verdict": {
      "enum": [
        "TOO_SMALL",
        "PERFECT",
        "TOO_LARGE"
      ],
      "type": "string",
      "description": "What they said. PERFECT means they would buy it again."
    },
    "dimension": {
      "enum": [
        "LENGTH",
        "WIDTH"
      ],
      "type": "string",
      "description": "Which way it fits or does not."
    },
    "sessionId": {
      "type": "string",
      "description": "The session id returned by start_session. Everything the person tells you is stored against it, and it is the only thing linking one call to the next."
    }
  },
  "additionalProperties": false
}
    arguments 37 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 c94b866ff55a28b9.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/c94b866ff55a28b9/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/c94b866ff55a28b9/badge.svg)](https://brick.blue/agent/c94b866ff55a28b9?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
100%

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.