Loading…
Agentic AI Blueprint doctrine and 13 public tools for learning and prototyping agent patterns.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 1 month ago Due for re-check
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The Agentic AI Blueprint Doctrine MCP server exposes 29 tools, focused primarily on developer capabilities. Its published description reads: "Agentic AI Blueprint doctrine and 13 public tools for learning and prototyping agent patterns". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates Agentic AI Blueprint Doctrine F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Cross-tool shadowing" and "Cross-tool shadowing". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check Agentic AI Blueprint Doctrine's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add Agentic AI Blueprint Doctrine to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://aidesignblueprint.com/mcpStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
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 rubri
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.
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: principles.list
A tool description tries to alter the model’s use of another tool.
anguage. Prefer principles.get when you already know the exact slug and need fRecommendationDescriptions must describe only their own tool.
tool: clusters.list
A tool description tries to alter the model’s use of another tool.
et or filtering principles.list by cluster. Prefer clusters.get when you alreadRecommendationDescriptions must describe only their own tool.
tool: principles.get
A tool description tries to alter the model’s use of another tool.
exact slug from principles.list; prefer principles.search when the user describRecommendationDescriptions must describe only their own tool.
tool: clusters.get
A tool description tries to alter the model’s use of another tool.
clusters.list / principles.list response and need its full definition + memberRecommendationDescriptions must describe only their own tool.
tool: examples.get
A tool description tries to alter the model’s use of another tool.
mples.search, a principles.get response, or a guide cross-link; prefer exampleRecommendationDescriptions must describe only their own tool.
tool: principles.search
A tool description tries to alter the model’s use of another tool.
refer this over principles.list when you have a specific topic in mind rather tRecommendationDescriptions must describe only their own tool.
tool: examples.search
A tool description tries to alter the model’s use of another tool.
g is the handle examples.get hydrates. Default limit 5, capped server-side.RecommendationDescriptions must describe only their own tool.
tool: assets.list
A tool description tries to alter the model’s use of another tool.
r symmetry with principles.list / clusters.list / guides.list. WHEN TO CALL: thRecommendationDescriptions must describe only their own tool.
tool: guides.list
A tool description tries to alter the model’s use of another tool.
anguage. Prefer guides.get when you already know the guide slug and need fRecommendationDescriptions must describe only their own tool.
tool: guides.get
A tool description tries to alter the model’s use of another tool.
guide slug from guides.list or guides.search. Prefer guides.search when theRecommendationDescriptions must describe only their own tool.
tool: guides.search
A tool description tries to alter the model’s use of another tool.
de slug; prefer guides.list when you need the full inventory.RecommendationDescriptions must describe only their own tool.
tool: signals.report
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
. Auth: Bearer <token>, Pro or Teams plan required. UK/EU residency.RecommendationRemove side-channel parameters; constrain tool inputs.
tool: signals.report
A tool description tries to alter the model’s use of another tool.
n on any lens — architect.validate, design.validate, or spec.validate — or a doctrRecommendationDescriptions must describe only their own tool.
tool: signals.feedback
A tool description tries to alter the model’s use of another tool.
g report'). Use signals.report instead for value-moment metrics (rating validaRecommendationDescriptions must describe only their own tool.
tool: architect.validate
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
. Auth: Bearer <token>, Pro/Teams plan. UK/EU residency; transient OpRecommendationRemove side-channel parameters; constrain tool inputs.
tool: architect.validate
A tool description tries to alter the model’s use of another tool.
an speed, call `architect.validate_consensus` (N=3-5 aggregated, median verdict + per-princiRecommendationDescriptions must describe only their own tool.
tool: design.validate
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
your validation-history dashboard tagged as the 'surface' dimension, diRecommendationRemove side-channel parameters; constrain tool inputs.
tool: design.validate
A tool description tries to alter the model’s use of another tool.
y re-runs the full 60-180s call). Runs appear in your validation-history dRecommendationDescriptions must describe only their own tool.
tool: spec.validate
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
your validation-history dashboard tagged as the 'spec' dimension, distiRecommendationRemove side-channel parameters; constrain tool inputs.
tool: spec.validate
A tool description tries to alter the model’s use of another tool.
re-runs the full 60-180s call). Runs appear in your validation-history dasRecommendationDescriptions must describe only their own tool.
tool: architect.validate_consensus
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
. AUTH: Bearer <token>, Pro/Teams plan. Same paid-plan gate as architRecommendationRemove side-channel parameters; constrain tool inputs.
tool: architect.validate_consensus
A tool description tries to alter the model’s use of another tool.
beat pattern as architect.validate — the run_id is emitted in the FIRST progress eRecommendationDescriptions must describe only their own tool.
tool: architect.certify
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
. Auth: Bearer <token>, Pro or Teams plan required. UK/EU data resideRecommendationRemove side-channel parameters; constrain tool inputs.
tool: architect.certify
A tool description tries to alter the model’s use of another tool.
ification of an architect.validate run that scored production_ready (A or B first-RecommendationDescriptions must describe only their own tool.
tool: architect.certify
An exec/shell/run-code tool exposes a command/code/args parameter that is a free-form string with no enum/pattern guard — a direct command-injection / RCE surface. A tool constraining the command to an `enum` of allowed operations does not fire.
unconstrained command parameter "code"RecommendationReplace the free-form command with a fixed `enum` of allowed operations (or structured, escaped arguments) and require explicit human approval.
tool: team.summarize
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
ely or on every conversation turn (the summary is an explicit retrospective,RecommendationRemove side-channel parameters; constrain tool inputs.
tool: me.coaching_context
A tool description tries to alter the model’s use of another tool.
sult. Pair with me.add_evidence to close gaps. WHEN NOT TO CALL: to lecture theRecommendationDescriptions must describe only their own tool.
tool: me.add_evidence
A tool description tries to alter the model’s use of another tool.
are surfaced on me.learning_path / me.coaching_context. Confirms the stage_slugRecommendationDescriptions must describe only their own tool.
tool: me.sessions
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
. Auth: Bearer <token>. Pro or Teams plan required. {"properties":{"sRecommendationRemove side-channel parameters; constrain tool inputs.
tool: me.sessions
A tool description tries to alter the model’s use of another tool.
across lenses (architect.validate → 'architecture', design.validate → 'surface',RecommendationDescriptions must describe only their own tool.
tool: me.session_event
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
. Auth: Bearer <token>, Pro/Teams plan. {"properties":{"session_id":{RecommendationRemove side-channel parameters; constrain tool inputs.
tool: me.session_event
A tool description tries to alter the model’s use of another tool.
events back via me.sessions(session_id=...). WHEN TO CALL: at every role haRecommendationDescriptions must describe only their own tool.
tool: me.await_steer
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
. Auth: Bearer <token>, Pro/Teams plan. {"properties":{"session_id":{RecommendationRemove side-channel parameters; constrain tool inputs.
tool: me.await_steer
A tool description tries to alter the model’s use of another tool.
a task -> post me.session_event handoff -> call me.await_steer -> on a steer, FRecommendationDescriptions must describe only their own tool.
tool: me.validation_history
A tool description tries to alter the model’s use of another tool.
l three lenses (architect.validate → validator='architecture', design.validate → vRecommendationDescriptions must describe only their own tool.
tool: handoffs.operator
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "page_url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: handoffs.operator
A tool description tries to alter the model’s use of another tool.
s answerable by principles.search / guides.search. BEHAVIOR: write-only, single iRecommendationDescriptions must describe only their own tool.
tool: handoffs.partnership
A tool description tries to alter the model’s use of another tool.
ess issues (use handoffs.operator); for paid-engagement enquiries (use handoffs.aRecommendationDescriptions must describe only their own tool.
tool: handoffs.agency
A tool description tries to alter the model’s use of another tool.
g / access (use handoffs.operator); proactively or as a sales push. BEHAVIOR: wriRecommendationDescriptions must describe only their own tool.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: architect.validate
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: architect.validate
One tool both accesses the filesystem and reaches the network. Combining two capability classes in a single tool widens its blast radius and is the substrate for confused-deputy and exfiltration abuse.
,"description":"List of file paths relevant to the implementation context.","titleRecommendationSeparate filesystem and network capabilities into distinct, independently-scoped tools.
tool: design.validate
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: spec.validate
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: architect.validate_consensus
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: architect.validate_consensus
One tool both accesses the filesystem and reaches the network. Combining two capability classes in a single tool widens its blast radius and is the substrate for confused-deputy and exfiltration abuse.
,"description":"List of file paths relevant to the implementation.","title":"FilesRecommendationSeparate filesystem and network capabilities into distinct, independently-scoped tools.
tool: architect.certify
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: handoffs.operator
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: handoffs.partnership
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: handoffs.agency
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: architect.validate
An unusually long description is a common injection-padding tactic.
description length 8710 charsRecommendationKeep descriptions concise.
tool: design.validate
An unusually long description is a common injection-padding tactic.
description length 3421 charsRecommendationKeep descriptions concise.
tool: spec.validate
An unusually long description is a common injection-padding tactic.
description length 3415 charsRecommendationKeep descriptions concise.
tool: architect.validate_consensus
An unusually long description is a common injection-padding tactic.
description length 3312 charsRecommendationKeep descriptions concise.
tool: architect.certify
An unusually long description is a common injection-padding tactic.
description length 6977 charsRecommendationKeep descriptions concise.
tool: me.session_event
An unusually long description is a common injection-padding tactic.
description length 2102 charsRecommendationKeep descriptions concise.
Vantaj uptime monitoring via MCP — manage monitors, heartbeats, incidents, and status pages.
Unified gateway to Algeria's TKAWEN ecosystem: commerce, certification, and AI tools.
Provides access to the Cohereon Doctrine AI safety framework with governance components, tiered access, and agent onboarding.
Agentic rails for complex workflows with receipts, fees, and MCP tool access.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
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
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 s
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
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. 'r
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
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 fil
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. Pref
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
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, observab
Pro/Teams — 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 —
Public — records explicit free-text user feedback about the Blueprint, this tool surface, or a specific principle/example. Captures category (bug, doctrine_critique, missing_example, ergonomics, other
Pro/Teams — first-pass doctrine review of agentic code/workflow against the 10-principle Agentic AI Blueprint. ON CLIENT TIMEOUT — DO NOT RETRY THIS TOOL. Long-running LLM call (60-180s typical); MCP
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
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 w
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 th
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**: th
Pro/Teams — summarises the caller's tool-usage patterns and value signals over a configurable window (default 30 days). Returns tool_call_counts, top principles cited in validate runs, value_event_cou
Authenticated — returns the caller's Blueprint learning-path state: current course slug, stage progress, certification status (Foundation, Practitioner, Capstone), Capstone track eligibility flags, an
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 sho
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
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.
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,
Pro/Teams. BLOCK until the session owner posts the next `steer` event to a Governed Session from the AIDB Studio cockpit, then return it. DELIVERY GUARANTEE: the durable cursor read against the sessio
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
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. Persist
Authenticated — creates a partnerships handoff record for design-partner, ecosystem, training, or advisory conversations needing human review. Persists a PartnershipHandoff row routed to the partnersh
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 tea