archify-mcp (Tai-DT/archify-mcp) is an MCP server listed on the M8ven Trust Index. It scores 58 out of 100, grade D. It declares 26 tools. No publisher has claimed this listing.
Analyzes project ideas and recommends suitable tech stacks, features, and architecture patterns.
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
Tai-DT
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
analyze_projectDeep analysis of a project idea including market insights, risks, MVP scope, technical requirements, AND environment/device/performance analysis. Supports Vietnamese.
recommend_stackRecommend the best technology stack considering deployment environment, target devices, network conditions, and infrastructure constraints. Scores 40+ technologies across 8 criteria + environment fit.
suggest_featuresSuggest features for a project organized by priority (Must-Have, Should-Have, Could-Have, Innovative). Includes complexity estimates and tech requirements.
compare_techCompare 2 or more technologies side-by-side across 8 scoring criteria. Generates a ranking table with winner.
design_architectureDesign system architecture with Mermaid diagrams, component breakdown, deployment strategy, and scaling plan.
estimate_projectEstimate project timeline, team composition, and costs based on features and scale.
generate_roadmapGenerate a development roadmap with Gantt chart, milestones, and critical path.
estimate_infrastructureEstimate monthly infrastructure costs with scaling projections and provider comparisons. Checks free tiers and budget caps.
design_databaseDesign database schema with ER diagrams, table definitions, indexes, and recommendations. Templates for e-commerce, SaaS, and more.
audit_securityAudit security of a tech stack against OWASP Top 10. Includes compliance checks (GDPR, HIPAA, PCI-DSS), scoring, and actionable checklist.
migrate_stackPlan a technology migration: compare old vs new stack, risk assessment, phased migration steps with rollback plans, and GO/NO-GO recommendation.
generate_boilerplateGenerate config files (.env, docker-compose, Dockerfile, CI/CD, .gitignore) based on the recommended tech stack.
recommend_dual_stackRecommend TWO stacks side-by-side: Module (SaaS/SDK plug-in, nhanh) vs Standard (self-build, full control). Includes comparison table, advantages, cost/time differences, and hybrid recommendation.
full_analysisCOMPLETE closed-loop analysis pipeline. Runs ALL tools in sequence: Project Analysis → Features → Stack → Architecture → Database → Security → Cost → Estimation → Roadmap → Boilerplate. Produces a comprehensive report with GO/NO-GO verdict.
design_apiDesign REST API endpoints based on project type and features. Generates endpoint tables, auth requirements, webhooks, rate limiting, and recommendations.
plan_testingCreate comprehensive testing strategy: test pyramid, tool recommendations, coverage targets, performance testing plan, CI integration, and setup checklist.
analyze_scalabilityPlan scaling from MVP to 1M users. Includes 4 growth stages, bottleneck predictions (DB, API, WebSocket, AI), caching strategy by layer, and database scaling phases.
assess_teamAssess required team: roles, skills, hiring plan, salary ranges (VN/US), organization structure, and skill gap analysis.
plan_devopsPlan DevOps strategy: CI/CD pipeline (GitHub Actions), monitoring (Sentry/Grafana), alerting rules, disaster recovery (RTO/RPO/backup), environment setup, and secret management.
map_integrationsMap all third-party services needed: costs, free tiers, API keys, alternatives, vendor lock-in. Feature-aware: adds AI, chat, video, analytics services.
generate_ui_specGenerate UI/UX specification: design system (colors, typography, spacing), component inventory with variants/states, page layouts, responsive strategy, accessibility checklist (WCAG AA).
create_performance_budgetSet performance budget: Core Web Vitals targets, bundle size limits, Lighthouse scores, network/server budgets, and optimization strategies.
plan_monetizationPlan monetization: revenue model, pricing tiers, break-even analysis, business KPIs (MRR, CAC, LTV, churn), and pricing recommendations.
smart_recommendAdvanced tech recommendation using TOPSIS ranking + AHP weighting + Constraint Satisfaction. Returns ranked alternatives with confidence score, sensitivity analysis, and breakdown.
analyze_compatibilityAnalyze compatibility between technologies using graph-based synergy/conflict detection. Shows +3 (perfect synergy) to -3 (incompatible) scores for each tech pair.
simulate_costMonte Carlo simulation for cost/timeline estimation under uncertainty. Uses PERT/triangular distributions. Returns P10 (optimistic), P50 (likely), P90 (pessimistic) with histogram.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
Tool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
26/26 tools missing one or more hints — analyze_project (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); recommend_stack (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); suggest_features (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +23 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Tool handlers catch errors
Only 0/26 tool handlers wrap calls in try/catch (0%)
Wrap each tool handler body in try/catch and return a structured error response.
License file
No license file
Add a LICENSE file (MIT, Apache-2.0, etc.).
Tests exist
No test files found
Add tests that exercise each declared tool.
Production dependencies are patched
0 critical, 3 high severity in production deps — @modelcontextprotocol/sdk@1.12.1 (high), @modelcontextprotocol/sdk@1.12.1 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/tai-dt/archify-mcp)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check