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

Package Pricing Lab

Builds fixed-price service packages from costs and capacity, with margin and capacity math.

Checks passed
12 / 22

2 failed · 8 not measured

Median response
628 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
4

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?
222

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 628 ms.

  • Pass
    Valid handshake

    protocolVersion 2025-11-25, serverInfo.name Package Pricing Lab by Modern Mustard Seed.

  • Pass
    Lists tools

    tools/list returned 4 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 628 ms over 1 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.

  • Not measured
    Consistent (p95)

    95th percentile 628 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

    45 of 54 parameters have a description (83%). 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.

  • 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 2026-10-11T19:11:51.33685Z, within 180 days.

  • Not measured
    Open-source licence

    No GitHub repository to ask about a licence.

Start using Package Pricing Lab

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 package-pricing-lab https://mcp.modernmustardseed.com/pricing-lab

Capabilities

Tools 4

build_packages

Turn the work a service business does into three fixed-price packages (smallest, middle, largest). Takes the cost base (fixed costs, owner pay, staff, delivery capacity) and the deliverables the business offers, each marked core (every client needs it), common (most clients want it) or premium (some clients want it), with its typical effort and direct cost. Returns each tier with what it includes and leaves out, its cost, break-even price, target price, a recommended price rounded up to a clean number, margin and profit per sale, how far the work can overrun before the margin hits zero, and a capacity check: hours needed, break-even clients a month, and the month profit after owner pay. All results are deterministic arithmetic with the method explained. Adjustments to what was built are treated as included, so effort carries a variance buffer.

Discovered
compare_models

Compare the economics of how a business charges today, by the hour or by the day, with fixed packages for the same work. Takes the cost base, the current rate and unit, the share of hours worked that reach an invoice, one to three packages with price and typical effort, and jobs per month. The current rate always comes from the user and is never assumed. Returns, at several efficiency gains (default 0, 15 and 30 percent less effort as delivery gets repeatable), revenue and profit per job and per month under each model, earnings per hour worked, revenue ceilings at full capacity, the package price that matches what each job collects today, and plain findings. Deterministic arithmetic with the method explained.

Discovered
package_scope_language

Write plain scope language for one to three fixed packages: an included line for each deliverable, an adjustments line (adjustments to anything delivered are included at no added cost), out-of-scope lines (deliverables from larger packages and anything listed as excluded), the rule that a genuinely new deliverable becomes a new package scoped and priced before work starts, worked boundary examples, and a ready-to-paste text block per package. Lines that use time-based or extra-charge wording are left out and named in notes. Written in "we" by default or "I" for a solo business.

Discovered
stress_test_package

Show what scope creep and a slow month do to one fixed-price package. Takes the cost base, the package price, its typical effort and direct cost, and optionally sales per month and a cash reserve. Returns margin and profit per sale at each scope creep level (default 10, 25 and 50 percent more effort on the same deliverables), the overrun at which the package earns nothing, the price that holds the target margin at the worst case, and the month view: a normal month, a slow month (default 40 percent fewer sales), a slow month with creep, break-even sales a month, and how many slow months the reserve covers. Deterministic arithmetic with the method explained.

Discovered

Recent measurements

Probe history

View status
Latest stored probes. Raw probe rows are kept for 14 days.
CheckedResultResponseTools
Connected628 ms4