// MCP TOOL REFERENCE

AI DESIGN BLUEPRINT TOOLS

24 tools from the AI Design Blueprint MCP Server, categorised by risk level.

View the AI Design Blueprint policy → Token cost: 12,410 tokens →

// ALL 24 AI DESIGN BLUEPRINT TOOLS

READ 12 tools

Read clusters.list List all principle clusters with their stable slugs and linked principle titles. Use this to discover which... Read examples.get Get one curated example by stable slug. Returns title, summary, source-code links, principle coverage (the ... Read examples.search Search curated examples by free-text query, ranked by relevance, with optional filters: principle_ids (only... Read guides.get Get a full application guide by its stable slug (e.g. 'security-application', 'observable-evaluation'). Ret... Read guides.list List application guides that show how Blueprint principles apply to engineering challenges (security, evalu... Read guides.search Search application guides by free-text query, matched against section answers and action items. Use this wh... Read me.coaching_context Authenticated — returns stages in the caller's active course where recorded evidence is thin relative to th... Read me.learning_path Authenticated — returns the caller's Blueprint learning-path state: current course slug, stage progress, ce... Read principles.get Get one Blueprint principle by stable slug. Returns id, title, cluster, definition, rationale, risk-if-viol... Read principles.list List all 10 Blueprint principles with stable slugs, titles, and clusters. Use this when you need the full i... Read principles.search Search Blueprint principles by free-text query and return the closest matches ranked by relevance. Use this... Read team.summarize Pro/Teams — summarises the caller's tool-usage patterns and value signals over a configurable window (defau...

WRITE 6 tools

Write clusters.get Get one principle cluster by stable slug. Returns the cluster definition, shared rationale, and the full se... Write handoffs.agency Authenticated — submit an agency engagement enquiry on behalf of the caller for a founder-led discovery cal... Write handoffs.operator Authenticated — creates a support handoff record when an agent needs human review, account-specific escalat... Write handoffs.partnership Authenticated — creates a partnerships handoff record for design-partner, ecosystem, training, or advisory ... Write me.add_evidence Authenticated — append a free-text evidence note to a specific stage in the caller's active course. Notes r... Write signals.feedback Public — records explicit free-text user feedback about the Blueprint, this tool surface, or a specific pri...

DESTRUCTIVE 3 tools

Destructive architect.validate Pro/Teams — first-pass doctrine review of agentic code/workflow against the 10-principle Agentic AI Bluepri... Destructive assets.list Public — list downloadable doctrine and agent asset artifacts (skill packs, rule packs, MCP setup snippets)... Destructive signals.report Pro/Teams — records a value moment (review_confidence, runtime_risk_found, regression_caught, recommendatio...

EXECUTE 3 tools

Execute architect.certify Pro/Teams — second-pass adversarial certification of an architect.validate run that scored production_ready... Execute architect.validate_consensus Pro/Teams — N-shot CONSENSUS doctrine review of agentic code. ON CLIENT TIMEOUT — DO NOT RETRY THIS TOOL. L... Execute me.validation_history Pro/Teams — return the authenticated user's architect.validate run history with the Blueprint Readiness Sco...

// FAQ

How many tools does the AI Design Blueprint MCP server have? +

The AI Design Blueprint MCP server exposes 24 tools across 4 categories: Read, Write, Destructive, Execute.

How do I enforce policies on AI Design Blueprint tools? +

Route the AI Design Blueprint server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do AI Design Blueprint tools fall into? +

AI Design Blueprint tools are categorised as Read (12), Write (6), Destructive (3), Execute (3). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.