spring-mosaic
spring-mosaic is an MCP server that reviews Java/Spring Boot/PostgreSQL repositories against organizational standards, delivering structured and actionable feedback.
Detect Spring context (
detect_spring_context): Identify Spring Boot/Java version, build tool (Maven/Gradle), and module structure.Explore quality domains (
list_quality_domains): List all available Java/Spring quality domains.Retrieve quality guides (
get_quality_guide): Access detailed standards for domains including architecture, spring-boot, rest-api, data-jpa, security, testing, performance, anti-patterns, review-format, scaffolding, modernization, and git-conventions.Deep-dive into patterns (
explain_pattern): Get in-depth explanations on topics like JPA, REST DTOs, constructor injection, or Boot 3 migration.Generate PR review brief (
get_pr_review_brief): Obtain minimal review format and common anti-patterns.Get diff-relevant sections (
get_review_sections_for_diff): Return quality guide sections relevant to changed file extensions (e.g., .java, .yml).Orchestrate full PR review (
review_pr_diff): Produce a step-by-step review plan based on changed files with extension-specific guidance.Audit files/workspace (
audit_changed_files,audit_workspace): Provide structured feedback on a set of changed files or an entire directory.Review architecture (
review_architecture): Execute a layer-by-layer architecture checklist on Java/Spring diffs.Scan for anti-patterns (
scan_violations): Heuristic scan of a single Java/Kotlin file for common Spring violations.Setup tool (
spring-mosaic-setup): Automatically wire the server into a Java repository (Cursor/Cline compatible).
Provides tools for reviewing Java/Spring architecture, quality, and PR diffs, including detecting Spring context, listing quality domains, explaining patterns, scanning for anti-patterns, and reviewing architecture layer checklist.
Specifically focused on Spring Boot, providing context detection (Boot version), quality guides, and review tools for Spring Boot projects.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@spring-mosaic Review PR diff for Spring Boot anti-patterns"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
spring-mosaic
MCP server that reviews SoftTech Java / Spring Boot / PostgreSQL repositories, scores changes against org standards, and returns actionable feedback so teams follow best practices.
Sibling of ai-mosaic (Angular / TS frontends).
Package: @himakarinv-stack/spring-mosaic · GitHub Packages
What it does for SoftTech repos
Step | Tool |
Detect stack |
|
Plan the review |
|
Scan changes |
|
Standards |
|
Architecture |
|
Agents should install this MCP in backend repos (HRMS, APIs, etc.) and run the workflow on every PR / local change set.
Related MCP server: GitHub PR Review MCP Server
Install into a Spring / Java repo
1. Authenticate (one-time)
@himakarinv-stack:registry=https://npm.pkg.github.com
//npm.pkg.github.com/:_authToken=YOUR_GITHUB_TOKEN2. Install + wire Cursor
npm install --save-dev @himakarinv-stack/spring-mosaic
npx spring-mosaic-setupOr:
npx --registry=https://npm.pkg.github.com -p @himakarinv-stack/spring-mosaic spring-mosaic-setupSuggested review workflow
detect_spring_context
→ review_pr_diff (changed files)
→ audit_changed_files
→ get_pr_review_brief + get_review_sections_for_diff
→ write human feedback (blockers → info) using review-formatTools
Tool | Purpose |
| Boot/Java version, Maven/Gradle, modules |
| Domain index |
| One standards section |
| Topic deep-dive |
| Review format + anti-patterns |
| Sections for changed extensions |
| PR orchestration plan |
| Structured feedback on a change set |
| Scan a path under the repo |
| Layer checklist |
| Single-file heuristic scan |
Local develop
cd "d:/softtech/MCP servers/spring-mosaic"
npm install
npm run build
npx spring-mosaic-setup --local --target path/to/java-repoSee CONTRIBUTING.md and PUBLISH.md.
Available Tools
9 toolsdetect_spring_contextA
Detect Spring Boot / Java version, build tool, and modules. Call first.
Inputs: workspaceRoot.
explain_patternC
Deep-dive on a Spring/Java topic (jpa, rest, security, transactions, etc.).
Inputs: topic (required), workspaceRoot.
get_pr_review_briefC
Minimal PR review brief: review format + anti-patterns.
Inputs: workspaceRoot.
get_quality_guideC
Fetch ONE quality guide. spring-boot is version-scoped (boot2 vs boot3).
Inputs: domain (required), workspaceRoot.
get_review_sections_for_diffC
Return only quality sections relevant to changed file types.
Inputs: changedExtensions (required), workspaceRoot.
list_quality_domainsA
Index of Java/Spring quality domains. Call first to discover what to fetch.
Inputs: no named parameters.
review_architectureC
Architecture checklist for a Java/Spring diff.
Inputs: changedFiles (required), workspaceRoot.
review_pr_diffD
PR review orchestration: changed files, extensions, and review steps.
Inputs: changedFiles (required), workspaceRoot.
scan_violationsC
Heuristic scan of Java/Kotlin source for common Spring anti-patterns.
Inputs: source (required), filePath (required), workspaceRoot.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 9 tools
Tools are mostly distinct with clear purposes. Some overlap exists between PR review tools (e.g., get_pr_review_brief vs review_pr_diff), but descriptions differentiate them effectively.
All tool names follow a consistent verb_noun pattern in snake_case (e.g., detect_spring_context, list_quality_domains), making them predictable and easy to use.
With 9 tools, the server is well-scoped for its purpose (Spring/Java quality and PR review). No tool feels unnecessary, and the count is appropriate for the domain.
The tool set covers the full lifecycle of quality analysis: detection (detect_spring_context), exploration (list_quality_domains, get_quality_guide, explain_pattern), and PR review (brief, sections, orchestration, architecture, scanning). No obvious gaps.
Maintenance
Related MCP Connectors
Scan any public GitHub MCP-server repo for security issues. 37 MCP-specific L1 rules, 8 languages.
Repository knowledge graph MCP server for codebase understanding and debugging.
A MCP server built for developers enabling Git based project management with project and personal…
Scan any MCP server for tool-poisoning, security, auth & license. Trust score before install.
Related MCP Servers
- AlicenseBqualityDmaintenanceA code review tool server based on Model Context Protocol (MCP), providing multi-dimensional code review and scoring functions.42Apache 2.0
- AlicenseNot gradedqualityFmaintenanceComprehensive MCP server for analyzing GitHub pull requests, detecting security vulnerabilities, assessing code quality, and providing risk ratings across multiple languages.3 npmMIT
- AlicenseCqualityDmaintenanceA secure-by-default MCP server and CLI for AI agents to inspect Spring Boot repositories and interact with runtime Actuator endpoints, enabling code review, dependency scanning, and monitoring.44MIT
- AlicenseNot gradedqualityDmaintenanceMCP server for automated code review using AI agents. It analyzes code diffs or file paths for bugs, security issues, and style violations.MIT