archprint
Related Servers
Alternatives to archprint
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityAmaintenanceExposes four low-token tools — map, place, check, and plan — that let any coding agent read a codebase's declared systems, boundaries, and allowed dependency routes before it writes code. Agents can look up where a file belongs and what it may import, see whether their uncommitted edits crossed a boundary, and declare new dependencies up front so violations surface on the map, in the PR, and mid-turn instead of in review.1,129 npm5MIT
- AlicenseNot gradedqualityCmaintenanceFramework-agnostic architecture-rule enforcement for AI agents: analyzes Python codebases import graphs against declarative rulesets to report layer, forbidden-import, and cycle violations with file and line numbers. Supports MCP, OpenAI, Anthropic, LangChain, LlamaIndex, and CLI integrations.MIT
- AlicenseAqualityBmaintenanceIndexes any TypeScript / React / Next.js repo into a queryable code graph and exposes 13 MCP tools — who-renders, who-calls, find-references, blast-radius, find-cycles, dead-code orphans, and local semantic search — so agents query structure instead of reading whole files. Built on ts-morph, so edges are resolved, not grepped.142MIT
- AlicenseNot gradedqualityBmaintenanceGives your AI coding agent a bounded map of an unfamiliar TypeScript SaaS repo: where the code lives, what's risky to touch, and where the money / auth / user flows are. Provides eight MCP tools for orientation, task focus, risk assessment, and SaaS-specific observations without AST or type checking.14 npmMIT
- AlicenseAqualityBmaintenanceProvides read-only structural analysis of codebases, surfacing architecture smells with traffic-light ratings and rendering dependency relationships as Mermaid flowcharts.4MIT
- AlicenseAqualityDmaintenanceAnalyzes codebases to generate dependency graphs and architectural insights across multiple programming languages, helping developers understand code structure and validate against architectural rules.639 npm20MIT
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose: scan lists existing rules with evidence, recommend suggests a rule set, and explain drills into one rule from scan. There is no overlap in outputs or actions, and the descriptions make the boundaries explicit.
All tool names follow the same archprint_<verb> snake_case pattern with clear, consistent verbs (scan, recommend, explain). No deviations or mixed conventions.
Three tools are well-scoped for a read-only architecture analysis server, covering discovery, recommendation, and explanation without redundancy. Each tool earns its place and the set is not thin.
The surface covers listing existing rules, recommending a rule set, and explaining a single rule in detail, which is complete for a read-only advisor. A minor gap is the absence of a tool to export or apply rules, but that may be intentionally out of scope.