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

Moltline Merchant Maths

Processor fees, charge-to-net, invoice totals and proration. 3 of 6 tools free.

Checks passed
9 / 22

3 failed · 10 not measured

Median response
744 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
6

Tool definitions returned by this server

Independent monitoring

Health & checks

Status history

Check failed

The last measured handshake failed. Open the listing for evidence.

Last checked
Check summary by test group
Test areaPassedFailedUnmeasured
ConnectionCan a client connect and discover tools?
131
Reliability & speedDoes it respond consistently and quickly?
004
Access & authenticationWhat is required to use this server?
003
Tool qualityAre the tool definitions usable by an agent?
400
Publisher identityCan the publisher be traced to its source?
402

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

Inspect individual checks 22 recorded

Core

  • Fail
    Reachable

    Latest probe outcome is timeout.

  • Fail
    Valid handshake

    initialize did not return a supported protocolVersion and serverInfo.name.

  • Fail
    Lists tools

    tools/list did not return a tool.

  • Not measured
    Current protocol

    No negotiated protocol version.

  • Pass
    HTTPS

    The endpoint URL is https.

Performance

  • Not measured
    Fast (p50)

    Median latency 744 ms over 1 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.

  • Not measured
    Consistent (p95)

    95th percentile 744 ms over 1 samples in 7 days. The bar is 3000 ms. Need at least 20 samples.

  • Not measured
    Reliable (uptime)

    1 of 2 attempts returned a tool list in 30 days (50%). 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

  • Not measured
    Open access

    The latest probe was timeout, so open access is not measured.

  • 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

    20 of 20 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.

  • 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 2026-09-08T14:31:32.740795Z, within 180 days.

  • Not measured
    Open-source licence

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

Start using Moltline Merchant Maths

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 moltline-merchant-maths https://mcp.moltlinestudio.com/merchant

Capabilities

Tools 6

charge_to_net

Compute the gross price to charge so you net a target after fees. FREE. 'Charge X to receive Y' after percentage + fixed processor fees. Typical input {"net_target": 100, "pct_fee": 2.9, "fixed_fee": 0.30} returns {"charge": 103.4, "fee": 3.4, "net": 100.0}. The inverse of processor_fees - solves for gross from a target net. Use when the payout is the fixed requirement. Not when the price is already set. Errors: on invalid, missing, or malformed input this tool never raises a protocol error; it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "net_target > 0 and pct_fee < 100 required"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

Discovered
discount_stack

Stack discounts correctly: sequential vs additive comparison. PREMIUM (license). The two methods differ: this shows both, the final price, and the true total discount. Typical input {"price": 200, "discounts_pct": [20, 10]} returns {"original": 200, "sequential_price": 144.0, "sequential_total_discount_pct": 28.0, "additive_price": 140.0, "difference": 4.0, "note": "..."}. Use when more than one discount applies and the order changes the answer. Not for a single discount inside an invoice (invoice_total). Errors: on invalid, missing, or malformed input this tool never raises a protocol error; it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "price > 0 and at least one discount required"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

Discovered
installment_plan

Split a total into an installment schedule with optional deposit. PREMIUM (license). Rounding remainders land on the final payment so the schedule always sums exactly. Typical input {"total": 1000, "installments": 3, "deposit_pct": 10} returns {"deposit": 100.0, "payments": [300.0, 300.0, 300.0], "check_sum": 1000.0}. Use when one total is paid across scheduled dates. Not for partial-period adjustments (proration). Errors: on invalid, missing, or malformed input this tool never raises a protocol error; it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "total > 0 and 1-36 installments"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

Discovered
invoice_total

Total an invoice: per-line totals, subtotal, discount, tax, grand total. FREE. Typical input {"line_items": [{"desc": "Design", "qty": 2, "unit_price": 50}], "tax_pct": 8.5, "discount_pct": 10} returns {"lines": [{"desc": "Design", "qty": 2, "unit_price": 50, "line_total": 100.0}], "subtotal": 100.0, "discount": 10.0, "tax": 7.65, "total": 97.65}. Use when several line items roll up with discount and tax. Not for one transaction's fees (processor_fees) and not for spreading a total over time (installment_plan). Errors: on invalid, missing, or malformed input this tool never raises a protocol error; it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "line_items must contain at least one item,"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

Discovered
processor_fees

Break down payment-processor fees: fee, net, and effective rate. FREE. Uses editable presets for stripe/paypal/square/shopify (verify current rates) or your own custom_pct + custom_fixed. Typical input {"amount": 1000, "processor": "stripe", "transactions": 10} returns {"gross": 1000, "fee": 32.0, "net": 968.0, "effective_rate_pct": 3.2, "note": "..."}. Use when the charge amount is known and the net payout is the question. Not for the reverse: the gross needed to net a target is charge_to_net. Errors: on invalid, missing, or malformed input this tool never raises a protocol error; it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "amount must be > 0, transactions >= 1"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

Discovered
proration

Compute a prorated charge or refund for a partial billing period. PREMIUM (license). Typical input {"amount_per_period": 90, "days_used": 10, "days_in_period": 30} returns {"days_used": 10, "days_in_period": 30, "prorated_charge": 30.0, "prorated_refund": 60.0, "answer": 30.0}. Use when a plan starts, ends, or changes mid-period. Not for splitting a full amount into scheduled payments (installment_plan). Errors: on invalid, missing, or malformed input this tool never raises a protocol error; it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "need amount > 0 and 0 <= days_used <= days_in_period"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

Discovered

Recent measurements

Probe history

View status
Latest stored probes. Raw probe rows are kept for 14 days.
CheckedResultResponseTools
timeout12001 ms—
Connected744 ms6