# Idea to Product Sequencer

> Rule-based product method: scores an idea, finds its riskiest assumption, sequences the build.

- name: com.modernmustardseed/idea-sequencer
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 83/100 flags: no-repository
- quality: 96/100 (strong)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.modernmustardseed%2Fidea-sequencer
- tools: https://api.protogrid.dev/v1/servers/com.modernmustardseed%2Fidea-sequencer/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "idea-sequencer": {
      "type": "http",
      "url": "https://mcp.modernmustardseed.com/idea-sequencer"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 100
- freshness: 100
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-100% +updated-9d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 96/100 (strong)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 7 of 7 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 6,761 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 7, about 6,761 tokens to load them all
- tool set hash: 25c56d2a71bf4a7ee8e1234b04e5be0f
- badge: [![protogrid quality](https://protogrid.dev/badge/com.modernmustardseed/idea-sequencer.svg)](https://protogrid.dev/servers/com.modernmustardseed/idea-sequencer)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://mcp.modernmustardseed.com/idea-sequencer (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (7)

- `build_scope_and_sequence`: Run the full Idea to Product method on one idea and its feature list and return a Scope and Sequence plan as a Markdown document, followed by a short JSON summary. The document covers the problem and buyer, the riskiest assumption with its risk table, this week's validation test with pass and kill lines, red flags, the MVP cut (must, should, not now, with reasons), the build sequence with builders and dates, milestones through Hand Off, the launch plan and success metric, kill criteria written before the work, build rules for the product type, and a Hand Off checklist. When there is no commitment-level evidence yet, the build is scheduled to start after the test's decision date.
- `classify_idea`: Classify a product or business idea with fixed rules (no AI model): one of 10 product types and 9 buyer types with the words that matched, a 0 to 100 risk score on each of 10 assumptions (problem, buyer access, willingness to pay, solution fit, feasibility, retention, supply, regulatory, unit economics, operator capacity) with every rule that moved each score, the riskiest assumption written as a sentence a test can prove wrong, red flags, the stage of the Idea to Product method it is in, the build rules for its type, and the cheapest validation test for this week with pass and kill lines. Evidence already gathered (interviews, signups, deposits, payments) lowers risk along a fixed evidence ladder. The same input always gives the same answer.
- `cut_mvp`: Sort a feature list into must, should and not now using 15 explicit rules on each feature's tags (core_job, revenue, compliance, trust_safety, onboarding, measurement, retention, integration, automation, admin, growth, analytics, customization, platform, scale, delight), whether it could be done by hand at first, and how many buyers asked for it. Dependencies of a must become must. Should-haves fill the build window by value per effort point in dependency order. Returns each feature with its tier, the rule and the reason, effort totals against capacity, and when the must-haves do not fit, the specific cuts that would make them fit. Rejects duplicate ids, unknown dependencies and cycles with the chain named.
- `explain_method`: Return one of the method's reference tables: the four stages and their exit gates, the 10 assumptions, the evidence ladder, the 18 validation tests, the MVP cut rules, the feature tags, the 10 product types with their risk priors and build rules, the 9 buyer types, the decision rules, or the risk scoring rules. Static reference, no computation on user data.
- `kill_or_continue`: Make a push, iterate, park or kill call on 1 to 12 products from their metrics (target, actual, kill line, must-hit), evidence, stage, review date, last activity, and monthly revenue and cost, using 10 named decision rules: a must-hit metric past its kill line on the review date kills; a weighted score under 30 on the review date kills; more than 45 days idle parks; revenue under cost and falling kills or forces a price or cost change; 80 or more with the stage gate evidence pushes. Returns each call with its score, rule, reason, next action, next review date and what would flip it, then portfolio notes. Money and time already spent are recorded and deliberately ignored.
- `sequence_build`: Turn a feature list with dependencies into a dated build plan: applies the MVP cut, orders tasks by dependency, schedules them across the given number of builders on working days (weekends skipped), computes the critical path and each task's slack, adds the method's own tasks (record the success metric, take payment, launch kit, Hand Off) where missing, and dates the milestones: first core job end to end, MVP in real users' hands, launch, success metric review, and Hand Off. Every plan carries a success metric and a review date; a default per product type is used and flagged when none is given.
- `validation_plan`: Pick the cheapest test that can prove one assumption about an idea wrong within the days available, from a library of 18 named tests (for example Five Past-Behavior Interviews, Pay Link Pre-sale, Smoke Test Landing Page, Letter of Intent Round, Concierge MVP, Wizard of Oz, Feasibility Spike, Hand-Seeded Supply, Unit Cost Teardown, Regulatory Read and One Call). Tests are filtered by the buyer type, the price, the audience, reachable buyers, budget and whether someone can build, then ranked by strength of evidence against cost and days. Returns the sample, steps, a pass line, a kill line and an inconclusive rule set before the test runs, the decision date, a backup test, and every ruled-out test with the reason. Defaults to the riskiest assumption; pass assumption to choose another.