Atlas / MCP servers / connectry-io / Architect Cert

Architect CertCAUTION

Name: Architect Cert
Author: connectry-io

mcp/connectry-io/architect-cert

MCP server by connectry-io · anthropic · architect · certification · Audited 2026-10-08

⚑ Report / re-scan Source ↗

Free certification prep for the Claude Certified Architect exam. 390 questions. Spaced repetition. Zero sycophancy.

Verdict

CAUTION

Grade

Trust score

87 /100

Exposed tools

53 38r · 14w · 1d

Transport

stdio

License

MIT

Stars

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

Ace the Claude Certified Architect exam

Adaptive certification prep powered by the Model Context Protocol. 390 questions. Guided capstone build. 30 concept handouts. 6 reference projects. Practice exams. Interactive dashboard. Spaced repetition. Zero sycophancy.

Read from source at commit c5bf7b9c541aOBSERVED · 2026-10-08

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.

claude-code (npm)

claude mcp add connectry-architect-mcp -- npx -y [email protected]

Exposed tools (53)

38 read · 14 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.

Tool	Risk	Description
`cancel_invoice`	read	Cancel an existing invoice. Only invoices in
`capstone_build_status`	read	Check your guided capstone build progress \u2014 current step, criteria coverage, and quiz performance.
`capstone_build_step`	read	Drive your guided capstone build — quiz, build, and advance through 18 progressive steps. IMPORTANT: - When presenting quiz questions, use AskUserQuestion with header
`compare_agent_scoping`	read	Compare tool access between two agent roles. Shows shared tools,
`compare_findings`	read	Compare multiple research findings to identify consensus, contradictions, and gaps.
`create_invoice`	write	Create a new draft invoice for a customer. The invoice is created in
`decompose_query`	read	Break a research query into subtasks. Returns a list of subtasks with types, descriptions, and dependencies.
`dispatch_analysis`	read	Dispatch an analysis subtask to an analyzer subagent. Pass research results for the analyzer to process.
`dispatch_research`	write	Dispatch a research subtask to a researcher subagent. The subagent will execute independently and return results.
`evaluate_evidence`	read	Evaluate a piece of evidence for reliability, relevance, and strength. Returns a structured assessment.
`explain_tool_choice`	read	Get a detailed explanation of a tool_choice mode (auto, any, or tool).
`follow_up`	write	Handle post-answer follow-up actions. Use after submit_answer to explore concepts, code examples, handouts, or reference projects.
`get_agent_config`	read	Inspect the tool-scoping configuration for a specific agent role.
`get_article`	read	Retrieve a specific knowledge base article by its ID. Returns the full article content.
`get_curriculum`	read	View the full certification curriculum with domains, task statements, and your current mastery for each.
`get_customer`	read	Retrieve a customer profile by their UUID. Returns name, email, and tier.
`get_dashboard`	read	Open the study progress dashboard in Claude Preview. Shows mastery levels, exam history, activity timeline, and capstone progress.\n\nIMPORTANT: After getting the URL, use the preview_start tool to open it in Claude Preview. If the user says
`get_exam_history`	read	View all completed practice exam attempts with scores, pass/fail status, and per-domain breakdowns. Compare your progress across attempts.
`get_invoice`	read	Retrieve a single invoice by its exact invoice ID (format: INV-XXXXXX).
`get_practice_question`	read	Get the next practice question. Prioritizes review questions, then weak areas, then new material. IMPORTANT — present the question using AskUserQuestion: - header:
`get_progress`	read	Get your certification study progress overview including mastery levels, accuracy, and review status.
`get_section_details`	read	Get detailed information about a specific task statement including concept lesson, mastery, and history.
`get_study_plan`	read	Get a personalized study plan based on your assessment results, weak areas, and learning path. IMPORTANT — after showing the study plan, use AskUserQuestion with header
`get_ticket`	read	Retrieve a support ticket by its ID. Returns the full ticket including subject, body, customer info, priority, category, status, tags, and complete event history.
`get_weak_areas`	read	Identify your weakest task statements based on accuracy below 70%. Focus your study on these areas.
`list_invoices`	read	List all invoices for a specific customer, optionally filtered by status.
`my_tool`	read
`pii_exposure`	read	Document contains personally identifiable information (SSN, full DOB,
`process_ticket`	read	Process a support ticket end-to-end using multi-agent orchestration. Analyzes the ticket, researches the knowledge base, and drafts a response. Returns the full analysis, research findings, draft response, and pipeline execution details.
`read_document`	read	Read a document or web page and extract its text content.
`regulatory_violation`	read	Document contains claims, promises, or disclosures that violate
`reset_progress`	destructive	WARNING: Permanently deletes ALL your study progress including answers, mastery data, and review schedules. This cannot be undone.
`save_extracted_contacts`	write	Saves extracted contact information from a document.
`scaffold_project`	read	Get instructions for a reference project to practice certification concepts hands-on.
`search_knowledge_base`	read	Search the knowledge base for articles relevant to a support issue. Returns articles ranked by relevance.
`search_tickets`	read	Search support tickets by query text, status, priority, or category. Returns matching tickets sorted by relevance.
`send_invoice`	write	Send a draft invoice to the customer via email. Changes status from
`start_assessment`	write	Start the initial assessment. Returns ONE question at a time (15 total, 3 per domain). IMPORTANT — follow this flow for EVERY question: 1. Check if
`start_capstone_build`	write	Start or refine a guided capstone build. Build your own project while learning all 30 certification task statements hands-on.
`start_practice_exam`	write	Start a full 60-question practice exam (D1:16, D2:11, D3:12, D4:12, D5:9). Scored 0-1000, passing 720. IMPORTANT — present the first question using AskUserQuestion: - header:
`structure_output`	read	Structure analysis results into the required output format with claims, evidence, confidence, and gaps.
`submit_answer`	write
`submit_classification`	write	Submit your ticket classification. You MUST call this tool with your analysis results.
`submit_exam_answer`	write
`submit_research`	write	Submit your research findings after searching the knowledge base.
`submit_response`	write	Submit your drafted customer response. You MUST call this tool with the response.
`synthesize_results`	read	Combine all subagent results into a final research report.
`take_notes`	read	Record a research finding with a confidence score and source attribution.
`tone_professionalism`	read	Document uses language that is unprofessional, aggressive, or
`unauthorized_commitment`	read	Document contains language that commits the organization to financial
`update_ticket`	write	Update a ticket
`validate_request`	read	Validate that a user request is well-formed before processing.
`web_search`	read	Search the web for information on a topic. Returns relevant snippets and URLs.

Trust audit

CAUTIONgrade B · trust 87/100 Install with care. The audit found things worth knowing before you trust its output.

Layer	What it checks	Result
L0	Provenance & inventory	PASS
L1	Static analysis of the code	WARN
L2	Instruction surface (what it tells the agent)	PASS
L3	Class-specific surface	WARN
L4	Behavioural (sandbox)	SKIPPED

What the source does

Filesystem: declared (1 observation(s))
Network: declared (1 observation(s))
Shell: none-observed
Dependencies: not all pinned
Secrets in source: none-found

Findings (14)

MEDIUMInformation disclosure · disclose.log_secret · CWE-209, CWE-532

projects/d4-prompts/src/review/multi-pass.ts:345

console.log(\`User logged in: \${email}, token: \${token}\`);

MEDIUMNetwork egress · net.raw_ip · CWE-200, CWE-319

src/tools/dashboard.ts:18

const url = `http://127.0.0.1:${cachedServer.port}/dashboard`;

MEDIUMFilesystem / path · mcp.destructive_tools · CWE-22, CWE-59

reset_progress

Why it matters. 1 tool(s) can delete or overwrite

Fix. prefer a read-only mode or scoped tokens; the page states the blast radius

LOWFilesystem / path · fs.traversal · CWE-22, CWE-59

tests/db/store.test.ts:2

import { createDatabase } from '../../src/db/store.js';

LOWFilesystem / path · fs.traversal · CWE-22, CWE-59

tests/engine/adaptive-path.test.ts:2

import { recommendPath, getDomainOrder, getNextRecommendedDomain, estimateTimeRemaining } from '../../src/engine/adaptive-path.js';

LOWFilesystem / path · fs.traversal · CWE-22, CWE-59

tests/engine/adaptive-path.test.ts:3

import type { DomainMastery } from '../../src/types.js';

LOWFilesystem / path · fs.traversal · CWE-22, CWE-59

tests/engine/grading.test.ts:2

import { gradeAnswer } from '../../src/engine/grading.js';

LOWFilesystem / path · fs.traversal · CWE-22, CWE-59

tests/engine/grading.test.ts:3

import type { Question } from '../../src/types.js';

LOWSupply chain · supply.unpinned · CWE-829, CWE-1357

package.json

@modelcontextprotocol/sdk, better-sqlite3, zod, @types/better-sqlite3, @types/node, marked, puppeteer, tsup

Why it matters. 11 dependency range(s) float