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 · Payments & trading

Penny Rounding

Round cash totals to the nearest nickel correctly — after tax, on the total, cash only.

Checks passed
14 / 22

1 failed · 7 not measured

Median response
619 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
3

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?
103
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 728 ms.

  • Pass
    Valid handshake

    protocolVersion 2025-11-25, serverInfo.name penny-rounding.

  • Pass
    Lists tools

    tools/list returned 3 tools.

  • Pass
    Current protocol

    Negotiated 2025-11-25. The bar is 2025-06-18 or newer.

  • Pass
    HTTPS

    The endpoint URL is https.

Performance

  • Not measured
    Fast (p50)

    Median latency 619 ms over 2 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.

  • Not measured
    Consistent (p95)

    95th percentile 717 ms over 2 samples in 7 days. The bar is 3000 ms. Need at least 20 samples.

  • Not measured
    Reliable (uptime)

    2 of 2 attempts returned a tool list in 30 days (100%). The bar is 99%. Need at least 30 samples.

  • Pass
    Stable tool list

    No tool was removed and no required parameter was added in the last 30 days.

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

    12 of 12 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.

  • Fail
    Website matches publisher

    The website host does not match the reverse-domain namespace.

  • Pass
    Source repo linked

    A 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 2026-09-05T20:40:52.807011Z, within 180 days.

  • Not measured
    Open-source licence

    The GitHub licence lookup has not returned an OSI result yet.

Start using Penny Rounding

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 penny-rounding https://penny-rounding.gumballtools.com/api/mcp

Capabilities

Tools 3

price_band

For a list price and a tax rate, find every nearby list price that settles to the SAME cash total, and the highest one. Use this for "what price should I charge" and "can I price to gain from rounding" questions. There is exactly one free move here and it is easy to get backwards, so do not reason about it unaided: Rounding collapses a band of five consecutive list prices onto one nickel. At 0% tax, $19.98 through $20.02 all settle to $20.00 in cash. Within that band the cash collected is IDENTICAL, so the highest price in it is strictly better — same from cash customers, up to 4 cents more from every card customer. That is genuinely free. The move that looks clever and is not: pricing BELOW a nickel so rounding "adds" a couple of cents. You collect the same cash and less on card. The rounding delta is not revenue. Do not recommend it. Input: `listPrice` as a dollar string, `taxRatePercent`, and optionally `spreadCents` (1-50, default 5) for how far either side to look. Returns: the whole band, the highest price in it, the free gain in cents (never more than 4), and a verdict. Tell the user the size of the number. Four cents is not a pricing strategy.

Discovered
round_cash_total

Settle a transaction under post-penny cash rounding: exact subtotal, tax on the exact subtotal, then round the final total to the nearest nickel — and only for cash. Use this for any "what does X round to" or "what do I owe in cash" question. Four things are wrong in most explanations of this, and each one changes the answer: 1. CASH ONLY. Card, EFT, and gift-card payments are still priced to the cent. The same basket legitimately comes to two different amounts by tender. If asked about a card payment, do not round. 2. THE TOTAL, NOT EACH ITEM. Rounding per item multiplies the effect by the basket size. Five items at $0.99 total $4.95 — already a nickel, no rounding — where per-item rounding would collect $5.00. 3. AFTER TAX. Tax is computed on the exact subtotal and the rounding comes last. Rounding the base first changes the tax owed. 4. THE DIGIT DECIDES. 1, 2, 6, 7 round down; 3, 4, 8, 9 round up; 0 and 5 stand. Do not reason about "nearest" from scratch, and do not assume rounding is always up. Input: pass `subtotal` as a dollar string ("19.99") or `items` as a list. A NUMERIC amount is read as CENTS and a STRING as dollars — 1999 and "19.99" are the same amount, 19.99 as a number is refused. Pass `taxRatePercent` as a percentage (8.25, not 0.0825); rounding depends on it, so omitting it usually gives the wrong nickel. `tender` is cash or card, default cash. `rule` is symmetric (default), always-down, always-up, or none. Returns: the exact subtotal, tax, exact total, the rounded amount due, the signed delta, which digit decided it, warnings, and a `disclaimer` field. THIS IS NOT LEGAL OR TAX ADVICE. There was no federal rounding law as of September 2026 and state law varies. Do not tell a user what their jurisdiction requires — report the arithmetic and the caveats.

Discovered
rounding_impact

Compute what cash rounding is actually worth across a list of prices: mean delta per transaction, the up/down/unchanged split, and a per-thousand figure. Use this whenever someone asks whether rounding costs or earns money — a very common question and one usually answered with a guess. Do not guess. Symmetric rounding nets to EXACTLY zero over evenly spread totals, because that is what it was designed to do. Real price lists all end in .99 and are not evenly spread, so the true figure is small but not always zero and it moves with the tax rate. This computes it for the actual prices given. Input: `prices` is a list of dollar strings or integer cents. `taxRatePercent` matters, because tax decides which nickel each total lands on. `rule` defaults to symmetric; pass always-up to quantify what the "just round everything up" idea would be worth (about 2 cents a sale, and no jurisdiction has adopted it for retail). Returns: mean and total delta in cents, the split, a per-thousand transaction figure, a per-price breakdown, and a plain-language verdict. Report the verdict — the size of the number is the answer.

Discovered

Recent measurements

Probe history

View status
Latest stored probes. Raw probe rows are kept for 14 days.
CheckedResultResponseTools
Connected728 ms3
Connected510 ms3