MCP HeartbeatTHE MCP OBSERVATORY
Public workspace

Explore

Evidence for your next connection.

Independent measurements of remote MCP servers. Every observation has a timestamp.

Read-only probes

MCP server · Other

GetSize

Your personal size guide. Find your shoe size in any brand from the brand's official size chart.

Checks passed
13 / 22

1 failed · 8 not measured

Median response
2140 ms

Median of successful probes over 7 days

30-day uptime
Not measured

Share of countable probes over 30 days, including daily rollups. Auth challenges are excluded.

Discovered tools
8

Tool definitions returned by this server

Independent monitoring

Health & checks

Status history

Responded

The server completed its last measured handshake. This is an observation, not a guarantee.

Last checked
Check summary by test group
Test areaPassedFailedUnmeasured
ConnectionCan a client connect and discover tools?
500
Reliability & speedDoes it respond consistently and quickly?
004
Access & authenticationWhat is required to use this server?
102
Tool qualityAre the tool definitions usable by an agent?
400
Publisher identityCan the publisher be traced to its source?
312

Unmeasured means there is not enough evidence to decide. How these checks work

Inspect individual checks 22 recorded

Core

  • Pass
    Reachable

    Latest probe returned HTTP 200 in 2140 ms.

  • Pass
    Valid handshake

    protocolVersion 2025-06-18, serverInfo.name getsize.

  • Pass
    Lists tools

    tools/list returned 8 tools.

  • Pass
    Current protocol

    Negotiated 2025-06-18. The bar is 2025-06-18 or newer.

  • Pass
    HTTPS

    The endpoint URL is https.

Performance

  • Not measured
    Fast (p50)

    Median latency 2140 ms over 1 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.

  • Not measured
    Consistent (p95)

    95th percentile 2140 ms over 1 samples in 7 days. The bar is 3000 ms. Need at least 20 samples.

  • Not measured
    Reliable (uptime)

    1 of 1 attempts returned a tool list in 30 days (100%). The bar is 99%. Need at least 30 samples.

  • Not measured
    Stable tool list

    Fewer than two successful probes in 30 days, so tool-list stability is not measured.

Access

  • Pass
    Open access

    tools/list succeeded with no credential, and the record declares none.

  • Not measured
    Standard auth

    Auth is not required, so the OAuth metadata check does not apply.

  • Not measured
    Free tier cited

    No publisher quote has been checked.

Tools

  • Pass
    Tools described

    Every tool description is at least 20 characters.

  • Pass
    Valid input schemas

    Every inputSchema is a JSON Schema object.

  • Pass
    Parameters documented

    15 of 15 parameters have a description (100%). The bar is 80%.

  • Pass
    Safety hints

    Every tool sets readOnlyHint or destructiveHint.

Publisher

  • Pass
    Verified namespace

    Listed in the Official MCP Registry.

  • Pass
    Website matches publisher

    The website host matches the reverse-domain namespace.

  • Fail
    Source repo linked

    No repository URL is on file.

  • Not measured
    Repo owner matches

    This namespace is not an io.github login, so the owner comparison does not apply.

  • Pass
    Recently updated

    Updated 2026-11-08T22:10:55.223637Z, within 180 days.

  • Not measured
    Open-source licence

    No GitHub repository to ask about a licence.

Start using GetSize

Connect to this server

Choose your client, copy the configuration, then enable the server in your client’s MCP settings.

Run this command in your terminal, then restart Claude Code.

Claude Code

claude mcp add --transport http getsize https://www.getsize.shoes/mcp

Capabilities

Tools 8

add_shoe

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.

Discovered
find_shoe

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.

Discovered
list_shoes

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

Discovered
rate_fit

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.

Discovered
recommend_size

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.

Discovered
remove_shoe

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.

Discovered
set_foot_measurement

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.

Discovered
start_session

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.

Discovered

Recent measurements

Probe history

View status
Latest stored probes. Raw probe rows are kept for 14 days.
CheckedResultResponseTools
Connected2140 ms8