AI Design Blueprint

michelangelo-z/ai-design-blueprint

A read-only doctrine layer for AI coding agents that enforces enterprise design principles without training on your code. Exposes 12 public tools via streamable HTTP to retrieve principles, clusters, and examples. Ships with skill packs for Claude Code, Cursor, Codex, Gemini CLI, and others, plus static rule files and downloadable markdown exports. Pro tier adds architect.validate for per-repo readiness scoring with regression tracking. Built for teams that want deterministic agent behavior and EU data residency. Install the MCP endpoint for live lookups or drop the static artifacts into your IDE for offline enforcement. UK/EU hosted, zero training policy, versioned content at 7ede0dd793a4.

tools: 29
transport: HTTP
last updated: Sep 24, 2026

View on GitHub

Install

From registry metadata

$ npx add-mcp https://aidesignblueprint.com/mcp --name blueprint

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport http blueprint https://aidesignblueprint.com/mcp

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 29 tools

Verified live against the running server on Nov 6, 2026.

principles.listList Blueprint doctrine with stable slugs, titles, and clusters. The lens selects which of the three public doctrines: 'architecture' = the 10 agentic principles (default, the architect.validate rubric); 'surface' = the 8 experience-design laws (the design.validate rubric); 's...2 params

List Blueprint doctrine with stable slugs, titles, and clusters. The lens selects which of the three public doctrines: 'architecture' = the 10 agentic principles (default, the architect.validate rubric); 'surface' = the 8 experience-design laws (the design.validate rubric); 's...

Parameters* required

clustervalue

Cluster slug to filter by (e.g. 'delegation', 'visibility', 'trust', 'orchestration'). Omit to return all principles.

lensstring

Which public doctrine: 'architecture' = the 10 agentic principles (default), 'surface' = the 8 experience-design laws, 'spec' = the 8 spec-quality laws.one of architecture · surface · specdefault: architecture

clusters.listList all principle clusters with their stable slugs and linked principle titles. Use this to discover which clusters exist before drilling in with clusters.get or filtering principles.list by cluster. Prefer clusters.get when you already know the cluster slug and need full det...

List all principle clusters with their stable slugs and linked principle titles. Use this to discover which clusters exist before drilling in with clusters.get or filtering principles.list by cluster. Prefer clusters.get when you already know the cluster slug and need full det...

No parameters. Call it with no arguments.

principles.getGet one doctrine entry by stable slug. The lens selects the doctrine: 'architecture' = one of the 10 agentic principles (default); 'surface' = one of the 8 experience-design laws; 'spec' = one of the 8 spec-quality laws. Returns id, title, cluster, definition, rationale, impli...2 params

Get one doctrine entry by stable slug. The lens selects the doctrine: 'architecture' = one of the 10 agentic principles (default); 'surface' = one of the 8 experience-design laws; 'spec' = one of the 8 spec-quality laws. Returns id, title, cluster, definition, rationale, impli...

Parameters* required

lensstring

Which public doctrine the slug belongs to: 'architecture' (10 principles, default), 'surface' (8 design laws), or 'spec' (8 spec laws).one of architecture · surface · specdefault: architecture

slug*string

Stable slug of the principle (e.g. 'establish-trust-through-inspectability').

clusters.getGet one principle cluster by stable slug. Returns the cluster definition, shared rationale, and the full set of member principles (slug + title) so the caller can pivot into principles.get without a second list call. WHEN TO CALL: the user has already named a specific cluster...1 params

Get one principle cluster by stable slug. Returns the cluster definition, shared rationale, and the full set of member principles (slug + title) so the caller can pivot into principles.get without a second list call. WHEN TO CALL: the user has already named a specific cluster...

Parameters* required

slug*string

Stable slug of the principle cluster (e.g. 'delegation', 'visibility', 'trust', 'orchestration').

examples.getGet one curated example by stable slug. Returns title, summary, source-code links, principle coverage (the principle slugs the example demonstrates), difficulty, library/framework, and implementation notes. Use this when you already have the slug from examples.search, a princi...1 params

Get one curated example by stable slug. Returns title, summary, source-code links, principle coverage (the principle slugs the example demonstrates), difficulty, library/framework, and implementation notes. Use this when you already have the slug from examples.search, a princi...

Parameters* required

slug*string

Stable slug of the curated example (e.g. 'agents-building-blocks-5-control').

principles.searchSearch Blueprint principles by free-text query and return the closest matches ranked by relevance. Use this to find principles related to a specific design challenge, failure mode, or keyword (e.g. 'reversibility', 'approval flow', 'delegation boundary'). Returns principle tit...3 params

Search Blueprint principles by free-text query and return the closest matches ranked by relevance. Use this to find principles related to a specific design challenge, failure mode, or keyword (e.g. 'reversibility', 'approval flow', 'delegation boundary'). Returns principle tit...

Parameters* required

lensstring

Which public doctrine to search: 'architecture' = the 10 agentic principles (default), 'surface' = the 8 experience-design laws, 'spec' = the 8 spec-quality laws, 'all' = all three.one of architecture · surface · spec · alldefault: architecture

limitinteger

Maximum number of results to return. Capped at server maximum.default: 5

query*string

Free-text search query matched against principle title, definition, rationale, and cluster.

examples.searchSearch curated examples by free-text query, ranked by relevance, with optional filters: principle_ids (only examples covering those principles), difficulty (beginner/intermediate/advanced), library (e.g. 'langgraph', 'openai'). Returns each match's slug, title, summary, princi...6 params

Search curated examples by free-text query, ranked by relevance, with optional filters: principle_ids (only examples covering those principles), difficulty (beginner/intermediate/advanced), library (e.g. 'langgraph', 'openai'). Returns each match's slug, title, summary, princi...

Parameters* required

difficultyvalue

Filter by difficulty level.

libraryvalue

Filter by library or framework name (e.g. 'langgraph', 'openai', 'anthropic').

limitinteger

Maximum number of results to return. Capped at server maximum.default: 5

pattern_familyvalue

Filter to one agentic-pattern family. Implies patterns only, since no upstream cookbook example carries a family.

principle_idsvalue

Filter to examples that cover these principle IDs.

query*string

Free-text search query matched against example title, summary, and metadata.

assets.listPublic: list downloadable doctrine and agent asset artifacts (skill packs, rule packs, MCP setup snippets) the user can drop into their AI coding tool to import the Blueprint as native skill/rule files. Returns a list of assets with name, format (one of: zip / md / markdown /...

Public: list downloadable doctrine and agent asset artifacts (skill packs, rule packs, MCP setup snippets) the user can drop into their AI coding tool to import the Blueprint as native skill/rule files. Returns a list of assets with name, format (one of: zip / md / markdown /...

No parameters. Call it with no arguments.

guides.listList application guides that show how Blueprint principles apply to engineering challenges (security, evaluation, observability, etc.). Use this to discover which guides exist before drilling in. Prefer guides.search when the user describes a topic or failure mode in natural l...

List application guides that show how Blueprint principles apply to engineering challenges (security, evaluation, observability, etc.). Use this to discover which guides exist before drilling in. Prefer guides.search when the user describes a topic or failure mode in natural l...

No parameters. Call it with no arguments.

guides.getGet a full application guide by its stable slug (e.g. 'security-application', 'observable-evaluation'). Returns sections, action items, and linked principles. Use this when you already have the guide slug from guides.list or guides.search. Prefer guides.search when the user de...1 params

Get a full application guide by its stable slug (e.g. 'security-application', 'observable-evaluation'). Returns sections, action items, and linked principles. Use this when you already have the guide slug from guides.list or guides.search. Prefer guides.search when the user de...

Parameters* required

slug*string

Stable slug of the application guide (e.g. 'security-application', 'observable-evaluation').

guides.searchSearch application guides by free-text query, matched against section answers and action items. Use this when the user describes an engineering challenge (security review, evaluation harness, observability) and wants matching guides. Prefer guides.get when you already have the...2 params

Search application guides by free-text query, matched against section answers and action items. Use this when the user describes an engineering challenge (security review, evaluation harness, observability) and wants matching guides. Prefer guides.get when you already have the...

Parameters* required

limitinteger

Maximum number of results to return. Capped at server maximum.default: 5

query*string

Free-text search query matched against all guide content including section answers and action items.

signals.reportRecords a value moment (e.g. review_confidence, runtime_risk_found, workflow_clarity) after a successful validate run on any lens (architect.validate, design.validate, or spec.validate) or a doctrine session. Each event stores event_type, surface_used (mcp or the site section)...7 params

Records a value moment (e.g. review_confidence, runtime_risk_found, workflow_clarity) after a successful validate run on any lens (architect.validate, design.validate, or spec.validate) or a doctrine session. Each event stores event_type, surface_used (mcp or the site section)...

Parameters* required

brief_contextvalue

1–2 plain-English sentences summarising what was helpful. Example: 'Validation identified a missing approval gate before email send.' No code snippets, no proprietary content, no user PII. Max 500...

event_type*string

Pick the type that best matches what just happened: 'review_confidence': a validator lens (architect.validate / design.validate / spec.validate) returned aligned; 'runtime_risk_found': a validate r...one of

workflow_clarity · runtime_risk_found · agent_setup_success · onboarding_helped · review_confidence · research_time_saved

perceived_valuevalue

Ask the user: 'On a scale of 1–5, how valuable was this session?' Map their answer directly: 1=low, 5=high. Do not guess: only set this if the user gave an explicit score.

surface_usedvalue

Where the value was experienced. Use 'mcp' when called from Claude Code, Cursor, Windsurf, or any MCP client. Use 'principles' if the user was browsing or searching principles. Use 'examples' if th...

team_sizevalue

If the user mentions their team size during the session, record it here. Do not ask for it explicitly: only capture if volunteered.

workflow_stagevalue

Infer from what the user was doing: 'exploring': reading doctrine, browsing principles; 'designing': planning architecture or agent flows; 'implementing': writing or refactoring code; 'reviewing':...

would_recommendvalue

Ask the user: 'Would you recommend the Blueprint to a colleague?' Set true/false based on their answer. Only set if asked: do not assume.

signals.feedbackPublic: records explicit free-text user feedback about the Blueprint, this tool surface, or a specific principle/example. Captures two 1-5 ratings (rating_clarity, rating_usefulness), what_helped, what_missing, would_use_again, the task_type and surface, and an optional contac...9 params

Public: records explicit free-text user feedback about the Blueprint, this tool surface, or a specific principle/example. Captures two 1-5 ratings (rating_clarity, rating_usefulness), what_helped, what_missing, would_use_again, the task_type and surface, and an optional contac...

Parameters* required

contact_emailvalue

Only ask for this if the user explicitly says they want a follow-up response. Never prompt for email unprompted. Only stored when permission_to_follow_up=true.

permission_to_follow_upboolean

Set to true only if the user explicitly said they want a follow-up. Must be confirmed before storing contact_email.default: false

rating_clarityvalue

Ask the user: 'How clear was the Blueprint guidance? Rate 1–5.' 1 = very unclear, 5 = very clear. Only set if the user gives an explicit number.

rating_usefulnessvalue

Ask the user: 'How useful was the Blueprint for this task? Rate 1–5.' 1 = not useful, 5 = very useful. Only set if the user gives an explicit number.

surfacevalue

Which Blueprint surface the feedback is about. Use 'mcp' if the session was via Claude Code or another MCP client. Use 'principles', 'examples', 'guides', 'coaching', or 'validation' based on what...

task_typevalue

What the user was doing when they decided to give feedback. Use plain English: e.g. 'code-review', 'architecture-design', 'agent-setup', 'onboarding', 'validation'. Infer from context.

what_helpedvalue

Ask the user: 'What was most helpful?' Record their answer verbatim or paraphrased in plain English. Max 1000 chars. No code snippets, no proprietary content.

what_missingvalue

Ask the user: 'What was missing or could be improved?' Record their answer verbatim or paraphrased. Max 1000 chars.

would_use_againvalue

Ask the user: 'Would you use the Blueprint again for a similar task?' Set true/false based on their answer. Only set if they answer explicitly.

architect.validatePro/Teams: first-pass doctrine review of agentic code/workflow against the 10-principle AI Design Blueprint doctrine. ON CLIENT TIMEOUT: DO NOT RETRY THIS TOOL. Long-running LLM call (60-180s typical); MCP clients commonly close the call before the server returns. Retrying re-...10 params

Pro/Teams: first-pass doctrine review of agentic code/workflow against the 10-principle AI Design Blueprint doctrine. ON CLIENT TIMEOUT: DO NOT RETRY THIS TOOL. Long-running LLM call (60-180s typical); MCP clients commonly close the call before the server returns. Retrying re-...

Parameters* required

example_limitinteger

Maximum number of curated examples to include in recommendations.default: 3

filesvalue

List of file paths relevant to the implementation context.

focus_areavalue

Narrow the evaluation to a specific principle cluster or slug (e.g. 'delegation', 'visibility', 'establish-trust-through-inspectability').

goalsvalue

Specific safety or quality goals to evaluate against (e.g. 'prevent irreversible actions', 'explicit approvals').

implementation_context*string

The artifact under review. SEND FULL FILE CONTENTS VERBATIM: the architect cites per-line evidence (identifiers, branch ordering, structural choices); any compression destroys evidence and produces...

languagevalue

Programming language of the code being evaluated (e.g. 'python', 'typescript').

private_sessionboolean

Set to true to skip the stored run AND prior-run anchoring AND run_id recovery for this call. Operational security and cost logs are still kept, per the Privacy Policy. The request is also not pers...default: false

repositoryvalue

Iteration key. SAME value across calls auto-resolves the most recent prior run as `prior_run_baseline` for iteration-aware grading (per-principle severity deltas, regressions/improvements). CHANGIN...

session_idvalue

Optional Governed Session to attach this run to (GEP-M2). Must reference a session YOU own (list via me.sessions; sessions are created in the web app at /app/sessions): foreign ids are refused befo...

taskvalue

What the agent or workflow is trying to accomplish. Adds evaluation context.

design.validatePro/Teams: first-pass surface-craft review of a FRONTEND artefact (component, screen, or flow) against the 8 laws of the Experience Design Blueprint. The surface-craft companion to architect.validate: where architect.validate scores agentic ARCHITECTURE against the 10 agentic...7 params

Pro/Teams: first-pass surface-craft review of a FRONTEND artefact (component, screen, or flow) against the 8 laws of the Experience Design Blueprint. The surface-craft companion to architect.validate: where architect.validate scores agentic ARCHITECTURE against the 10 agentic...

Parameters* required

filesvalue

File paths relevant to the artefact, for context.

goalsvalue

Specific craft/UX goals to weight (e.g. 'WCAG 2.2 AA', 'one primary action per screen').

implementation_context*string

The frontend artefact under review. SEND FULL SOURCE VERBATIM: the reviewer cites specific elements, values, and structure; any compression destroys evidence and produces findings on code that isn'...

private_sessionboolean

Set true to skip the stored run AND run_id recovery (operational security and cost logs are still written) for this call (a private one-shot that does not appear in the dashboard). The request is a...default: false

repositoryvalue

Project/repository key. Groups this run with prior design.validate runs on the same project in your validation-history dashboard (the same grouping architect.validate uses), under the 'surface' dim...

session_idvalue

taskvalue

What this surface is for (e.g. 'the closed-beta apply form'). Adds evaluation context.

spec.validatePro/Teams: first-pass specification-quality review of a WRITTEN SPEC (proposal, design doc, task breakdown, or an OpenSpec-style change bundle) against the 8 laws of the Spec Quality Blueprint. The what-to-build lens of the doctrine trio, applied BEFORE code exists: where arch...7 params

Pro/Teams: first-pass specification-quality review of a WRITTEN SPEC (proposal, design doc, task breakdown, or an OpenSpec-style change bundle) against the 8 laws of the Spec Quality Blueprint. The what-to-build lens of the doctrine trio, applied BEFORE code exists: where arch...

Parameters* required

filesvalue

File paths relevant to the spec, for context.

goalsvalue

Specific quality goals to weight (e.g. 'ready for an agent to build unattended', 'tight scope').

implementation_context*string

The specification under review. SEND FULL TEXT VERBATIM: the reviewer cites specific requirements, decisions, and tasks; any compression destroys evidence and produces findings on content that isn'...

private_sessionboolean

repositoryvalue

Project/repository key. Groups this run with prior spec.validate runs on the same project in your validation-history dashboard (the same grouping the other lenses use), under the 'spec' dimension.

session_idvalue

taskvalue

What this spec is for (e.g. 'the closed-beta apply flow rework'). Adds evaluation context.

architect.validate_consensusPro/Teams: N-shot CONSENSUS doctrine review of agentic code. ON CLIENT TIMEOUT: DO NOT RETRY THIS TOOL. Long-running (~80-120s for N=3 parallel LLM calls); MCP clients often close the call before the server returns. Retrying re-runs N × 60-180s LLM calls from scratch and burns...9 params

Pro/Teams: N-shot CONSENSUS doctrine review of agentic code. ON CLIENT TIMEOUT: DO NOT RETRY THIS TOOL. Long-running (~80-120s for N=3 parallel LLM calls); MCP clients often close the call before the server returns. Retrying re-runs N × 60-180s LLM calls from scratch and burns...

Parameters* required

example_limitinteger

Max curated examples per child run.default: 3

filesvalue

List of file paths relevant to the implementation.

focus_areavalue

Optional: narrow the review to a principle cluster or slug.

goalsvalue

Specific safety or quality goals to evaluate against.

implementation_context*string

The artifact under review. SEND FULL FILE CONTENTS VERBATIM: same constraint as architect.validate. Truncation produces hallucinated findings on code that isn't there.

languagevalue

Programming language of the code (e.g. 'python').

ninteger

Number of parallel child runs. Default 3 (the variance signal is visible at N=3; cost = 3× LLM bill). Capped server-side by Settings.consensus_n_max (default 5).default: 3

repositoryvalue

Iteration key. Consensus children all run unanchored (`private_session=True`), but the consolidated row IS persisted under this key: discoverable as prior baseline for the next single-shot `archite...

taskvalue

What the agent or workflow is trying to accomplish.

architect.certifyPro/Teams: second-pass adversarial certification of an architect.validate run that scored production_ready (A or B first-pass tier). ON CLIENT TIMEOUT: DO NOT RETRY THIS TOOL. **RECOVERY FIRST**: the run_id is emitted in the FIRST notifications/progress event at t=0s (BEFORE t...2 params

Pro/Teams: second-pass adversarial certification of an architect.validate run that scored production_ready (A or B first-pass tier). ON CLIENT TIMEOUT: DO NOT RETRY THIS TOOL. **RECOVERY FIRST**: the run_id is emitted in the FIRST notifications/progress event at t=0s (BEFORE t...

Parameters* required

codestring

The same code that was sent to architect.validate to produce this run_id. Sent verbatim: the cert reviewer needs the actual code to surface production_blockers the first pass missed. May be omitted...default:

run_id*string

The run_id from a prior architect.validate call. Returned in the validate response when persistence_status='saved'. Must be owned by the caller (per-user authorisation, same gate as me.validation_h...

team.summarizeTeams/Enterprise: summarises the caller's tool-usage patterns and value signals over a configurable window (default 30 days). Returns period_days, most_used_tools (call counts and average latency), value_events by event_type, observed_usage_stage, validator_lenses_used, recomm...2 params

Teams/Enterprise: summarises the caller's tool-usage patterns and value signals over a configurable window (default 30 days). Returns period_days, most_used_tools (call counts and average latency), value_events by event_type, observed_usage_stage, validator_lenses_used, recomm...

Parameters* required

days_backinteger

Number of days of usage history to include in the summary.default: 30

private_sessionboolean

No effect on this tool: accepted only so clients can pass the same flag to every tool. This read stores no run, and the per-call tool-usage record is written on every call.default: false

me.learning_pathAuthenticated: returns the caller's Blueprint learning-path state: current course slug, stage progress, certification status (Foundation, Practitioner, Capstone), Capstone track eligibility flags, and the next recommended stage. WHEN TO CALL: the user asks 'where am I', 'what'...

Authenticated: returns the caller's Blueprint learning-path state: current course slug, stage progress, certification status (Foundation, Practitioner, Capstone), Capstone track eligibility flags, and the next recommended stage. WHEN TO CALL: the user asks 'where am I', 'what'...

No parameters. Call it with no arguments.

me.coaching_contextAuthenticated: returns stages in the caller's active course where recorded evidence is thin relative to the stage's principle requirements. Each thin stage carries the missing principle slugs + a short diagnostic so the caller can suggest the user record concrete evidence. WHE...

Authenticated: returns stages in the caller's active course where recorded evidence is thin relative to the stage's principle requirements. Each thin stage carries the missing principle slugs + a short diagnostic so the caller can suggest the user record concrete evidence. WHE...

No parameters. Call it with no arguments.

me.add_evidenceAuthenticated: append a free-text evidence note to a specific stage in the caller's active course. Notes record concrete implementation observations, decisions, or artefacts that demonstrate progress through a Blueprint principle (e.g. how a delegation boundary was implemented...3 params

Authenticated: append a free-text evidence note to a specific stage in the caller's active course. Notes record concrete implementation observations, decisions, or artefacts that demonstrate progress through a Blueprint principle (e.g. how a delegation boundary was implemented...

Parameters* required

course_slug*string

Slug of the course the stage belongs to (e.g. 'agentic-fundamentals').

note*string

Evidence note to append to the delegation boundary notes for this stage.

stage_id*string

ID of the stage to append the evidence note to.

me.sessionsPro/Teams: list or inspect the authenticated user's Governed Sessions (GEP-M2): durable, owner-scoped containers that group validation runs across lenses (architect.validate → 'architecture', design.validate → 'surface', spec.validate → 'spec') into one timeline for one piece...1 params

Pro/Teams: list or inspect the authenticated user's Governed Sessions (GEP-M2): durable, owner-scoped containers that group validation runs across lenses (architect.validate → 'architecture', design.validate → 'surface', spec.validate → 'spec') into one timeline for one piece...

Parameters* required

session_idvalue

Session id to inspect (returns the session + its run timeline). Owner-scoped: ids you don't own answer 'Session not found.'. Omit to list all your sessions.

me.session_eventPro/Teams: append a TYPED TEAM EVENT to a Governed Session's timeline (GEP-M6). This is how the user's own harness makes trio work inspectable: handoffs between role lenses, pushbacks, plan previews, gates, and acks land as structured events next to the validation runs, so the...4 params

Pro/Teams: append a TYPED TEAM EVENT to a Governed Session's timeline (GEP-M6). This is how the user's own harness makes trio work inspectable: handoffs between role lenses, pushbacks, plan previews, gates, and acks land as structured events next to the validation runs, so the...

Parameters* required

actor*string

Who acted: pm | engineer | designer | system (`human` is reserved for AIDB Studio)one of pm · engineer · designer · system

event_type*string

handoff | pushback | plan_preview | gate | ack (ack = started working on a steer; `steer` itself is AIDB Studio-only and refused on this channel)one of handoff · pushback · plan_preview · gate · ack

session_id*integer

The Governed Session to post to. Must be YOURS and have team_agents enabled; list sessions via me.sessions.

summary*string

One-to-two sentence event summary (truncated to 500 chars): a decision or transition, not a chat message.

me.await_steerPro/Teams. BLOCK until the session owner posts the next `steer` event to a Governed Session from AIDB Studio, then return it. DELIVERY GUARANTEE: the durable cursor read against the session log is authoritative (at-least-once: a lost response is safely re-issuable with the sam...3 params

Pro/Teams. BLOCK until the session owner posts the next `steer` event to a Governed Session from AIDB Studio, then return it. DELIVERY GUARANTEE: the durable cursor read against the session log is authoritative (at-least-once: a lost response is safely re-issuable with the sam...

Parameters* required

after_event_idinteger

Cursor: highest session-event id you have already seen (0 = deliver any existing steer). Pass the value from your previous await_steer result or me.sessions read. Non-destructive at-least-once deli...default: 0

session_id*integer

The Governed Session to watch. Must be YOURS and have team_agents enabled; list sessions via me.sessions.

timeout_sinteger

Seconds to wait before returning timed_out. Clamped to 5-240, DEFAULT 45: safe under Claude Code's 60-second first-response-byte timer for HTTP servers. Longer waits require the per-server timeout...default: 45

me.validation_historyPro/Teams: return the authenticated user's validation run history for all three lenses (architect.validate → validator='architecture', design.validate → validator='surface', spec.validate → validator='spec') with the Blueprint Readiness Score (0-100), letter grade (A-F), and t...3 params

Pro/Teams: return the authenticated user's validation run history for all three lenses (architect.validate → validator='architecture', design.validate → validator='surface', spec.validate → validator='spec') with the Blueprint Readiness Score (0-100), letter grade (A-F), and t...

Parameters* required

limitinteger

Maximum number of runs to return when scoped to a single repository. Capped at 50. Ignored when `run_id` is provided.default: 10

repositoryvalue

Repository name or path to scope the history to. Pass the same value you would pass to architect.validate. Omit to get one summary per repository. Mutually exclusive with `run_id`: if both are pass...

run_idvalue

Single-run lookup by run_id (UUID). Returns the persisted result_json verbatim: the same payload architect.validate would have returned if your client hadn't timed out. Use this to recover a result...

handoffs.operatorAuthenticated: creates a support handoff record when an agent needs human review, account-specific escalation, or operator follow-up that cannot be resolved with the read-only doctrine tools. Persists a SupportHandoff row (reason, topic, page_url, agent_name, agent_platform, t...7 params

Authenticated: creates a support handoff record when an agent needs human review, account-specific escalation, or operator follow-up that cannot be resolved with the read-only doctrine tools. Persists a SupportHandoff row (reason, topic, page_url, agent_name, agent_platform, t...

Parameters* required

agent_namestring

Name of the agent or client triggering the handoff.default: mcp-client

agent_platformvalue

Platform or runtime the agent is running on (e.g. 'claude-code', 'cursor', 'copilot').

localestring

Response locale for the handoff acknowledgment.one of en · itdefault: en

page_urlvalue

URL of the page or context where the handoff was triggered.

reason*string

Clear description of why a human operator review is needed.

topicstring

Topic category for routing (e.g. 'agent', 'billing', 'access', 'general').default: agent

trace_summaryvalue

Optional summary of the agent's recent actions or trace for operator context.

handoffs.partnershipAuthenticated: creates a partnerships handoff record for design-partner, ecosystem, training, or advisory conversations needing human review. Persists a PartnershipHandoff row routed to the partnerships inbox; the user is contacted by the team. WHEN TO CALL: user explicitly wa...9 params

Authenticated: creates a partnerships handoff record for design-partner, ecosystem, training, or advisory conversations needing human review. Persists a PartnershipHandoff row routed to the partnerships inbox; the user is contacted by the team. WHEN TO CALL: user explicitly wa...

Parameters* required

agent_namestring

Name of the agent or client triggering the handoff.default: mcp-client

agent_platformvalue

Platform or runtime the agent is running on.

localestring

Response locale for the handoff acknowledgment.one of en · itdefault: en

organizationvalue

Name of the organization or company making the partnership inquiry.

reason*string

Clear description of the partnership opportunity or inquiry.

rolevalue

Role or title of the person submitting the partnership inquiry.

topicstring

Partnership topic category.one of ecosystem · design-partner · training · advisorydefault: ecosystem

trace_summaryvalue

Optional agent trace summary for operator context.

websitevalue

Website of the organization for additional context.

handoffs.agencyAuthenticated: submit an agency engagement enquiry on behalf of the caller for a founder-led discovery call. Persists an AgencyHandoff row routed to the agency inbox; the user is contacted by the team for a scoped proposal. Engagement scopes: workflow sprint (rapid agentic wor...10 params

Authenticated: submit an agency engagement enquiry on behalf of the caller for a founder-led discovery call. Persists an AgencyHandoff row routed to the agency inbox; the user is contacted by the team for a scoped proposal. Engagement scopes: workflow sprint (rapid agentic wor...

Parameters* required

agent_namestring

Name of the agent or client triggering the handoff.default: mcp-client

agent_platformvalue

Platform or runtime the agent is running on.

companyvalue

Company or team name submitting the agency inquiry.

localestring

Response locale for the acknowledgment.one of en · itdefault: en

reason*string

Description of the engagement need: workflow sprint, proof-of-concept, pilot support, or advisory.

rolevalue

Role or title of the person submitting the agency inquiry.

support_typevalue

Type of support needed.

trace_summaryvalue

Optional agent trace summary for operator context.

websitevalue

Website or relevant URL for the team or project.

workflow_stagevalue

Current workflow stage.

Readme

Details

Repository: github.com/michelangelo-z/ai-design-blueprint
Website: aidesignblueprint.com/en/for-agents
Categories: AI & LLM Tools, Design & Creative
Transport: HTTP
Registry: MCP registry, active
Tools verified: Nov 6, 2026

Related AI & LLM Tools MCP servers

View all

Invinoveritasbabyblueviper1/invinoveritas-mcpSecond opinion before an irreversible agent action; signed proofs, free verify, public ledger.0stars

Codegworkspace Mcpclauxel/codeg-agent-workspace-mcpA paid remote MCP for CodeG, built to return verdicts, receipts, usage logs, and audit-ready JSON.0stars

Geminiomnirights Mcpclauxel/gemini-omni-rights-receipt-mcpRemote MCP for Gemini Omni commercial rights receipt MCP, structured receipts, audit logs, and revie0stars

Lixversion Mcpclauxel/lix-agent-version-control-mcpA paid remote MCP for Lix, built to return verdicts, receipts, usage logs, and audit-ready JSON.0stars

Rtkcontext Mcpclauxel/rtk-context-compressor-mcpA paid remote MCP for OpenAI Codex context compressor, built to return verdicts, receipts, usage log0stars

Zerolangcompiler Mcpclauxel/zerolang-agent-compiler-mcp-mcpA paid remote MCP for ZeroLang, built to return verdicts, receipts, usage logs, and audit-ready JSON0stars