# AI Design Blueprint Doctrine

The industry standard reference for safe, observable, and steerable AI agent UX. Browse and search the 10 Blueprint principles, principle clusters, curated implementation examples, and application gu…

## Quick Start

```bash
# Connect this server (installs CLI if needed)
npx -y smithery mcp add zampognamichelangelo/aidesignblueprint

# Browse available tools
npx -y smithery tool list zampognamichelangelo/aidesignblueprint

# Get full schema for a tool
npx -y smithery tool get zampognamichelangelo/aidesignblueprint principles.list

# Call a tool
npx -y smithery tool call zampognamichelangelo/aidesignblueprint principles.list '{}'
```

## Direct MCP Connection

Endpoint: `https://aidesignblueprint--zampognamichelangelo.run.tools`

**Optional config:**
- `bearerToken` (query) — Firebase ID token. Required for auth-gated tools. Leave empty for public access.

## Tools (24)

- `principles.list` — List all 12 Blueprint principles with stable slugs, titles, and clusters. Use this when you need the full inventory or …
- `clusters.list` — List all principle clusters with their stable slugs and linked principle titles. Use this to discover which clusters ex…
- `principles.get` — Get one Blueprint principle by stable slug. Returns id, title, cluster, definition, rationale, risk-if-violated, implem…
- `clusters.get` — Get one principle cluster by stable slug. Returns the cluster definition, shared rationale, and the full set of member …
- `examples.get` — Get one curated example by stable slug. Returns title, summary, source-code links, principle coverage (the principle sl…
- `principles.search` — Search Blueprint principles by free-text query and return the closest matches ranked by relevance. Use this to find pri…
- `examples.search` — Search curated examples by free-text query, ranked by relevance, with optional filters: principle_ids (only examples co…
- `assets.list` — Public — list downloadable doctrine and agent asset artifacts (skill packs, rule packs, MCP setup snippets) the user ca…
- `guides.list` — List application guides that show how Blueprint principles apply to engineering challenges (security, evaluation, obser…
- `guides.get` — Get a full application guide by its stable slug (e.g. 'security-application', 'observable-evaluation'). Returns section…
- `guides.search` — Search application guides by free-text query, matched against section answers and action items. Use this when the user …
- `signals.report` — Pro/Teams — records a value moment (review_confidence, runtime_risk_found, regression_caught, recommendation_taken) aft…
- `signals.feedback` — Public — records explicit free-text user feedback about the Blueprint, this tool surface, or a specific principle/examp…
- `architect.validate` — Pro/Teams — first-pass doctrine review of agentic code/workflow against the 10-principle Agentic AI Blueprint. Returns …
- `architect.validate_consensus` — Pro/Teams — N-shot CONSENSUS doctrine review of agentic code. Runs N parallel `architect.validate` calls with private_s…
- `architect.certify` — Pro/Teams — second-pass adversarial certification of an architect.validate run that scored production_ready (A or B fir…
- `team.summarize` — Pro/Teams — summarises the caller's tool-usage patterns and value signals over a configurable window (default 30 days).…
- `me.learning_path` — Authenticated — returns the caller's Blueprint learning-path state: current course slug, stage progress, certification …
- `me.coaching_context` — Authenticated — returns stages in the caller's active course where recorded evidence is thin relative to the stage's pr…
- `me.add_evidence` — Authenticated — append a free-text evidence note to a specific stage in the caller's active course. Notes record concre…
- `me.validation_history` — Pro/Teams — return the authenticated user's architect.validate run history with the Blueprint Readiness Score (0-100), …
- `handoffs.operator` — Authenticated — creates a support handoff record when an agent needs human review, account-specific escalation, or oper…
- `handoffs.partnership` — Authenticated — creates a partnerships handoff record for design-partner, ecosystem, training, or advisory conversation…
- `handoffs.agency` — Authenticated — submit an agency engagement enquiry on behalf of the caller for a founder-led discovery call. Persists …

```bash
# Get full input/output schema for a tool
npx -y smithery tool get zampognamichelangelo/aidesignblueprint <tool-name>
```