StackGuide MCP Server
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., "@StackGuide MCP Server review the codebase for quality issues"
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.
StackGuide MCP Server
Dynamic context + active engineering workflow for AI coding assistants in Cursor, VS Code, and other MCP clients.
What It Does
@stackguide/mcp-server helps teams standardize implementation quality with:
project-aware rule/context loading
code review and health scoring
auto-detected setup and stack scaffolding
active agent workflow that executes real work (
intake,plan,verify,release)adaptive TDD preferences per project (model + token profile)
Jira ticket creation from strict
MAIN DESCRIPTIONtemplatestracker + VCS + test orchestration for delivery flow
This server is built for real team usage, not just prompt templates.
Related MCP server: corbat
What's New In v4.x
Full history: CHANGELOG.md.
v4.3.1 - Update notifier: StackGuide checks npm once a day in the background and tells you once per session when a newer version exists, with a safe update command. Disable with
STACKGUIDE_NO_UPDATE_CHECK=1.v4.3.0 - Team mode:
setup wizard:trueasks stack, architecture, methodology, conventions and tracker, then writes a sharedstackguide.config.jsonat the repo root. Commit it so every teammate gets the same context.On startup StackGuide finds that file (also from subfolders) and loads it without running
setupor re-detecting the project.contextreturns one guidance line per architecture and methodology.Optional
ruleCategorieslimits which rules are loaded (saves tokens). ExistinghealthWeightsin the file are preserved.Multi-agent roles that follow the IDE you are using (detected from the MCP client). Defaults: Claude Code
opus/haiku/haiku; Cursorinherit(your selected model, e.g. Composer or Grok) /fast/fast; other IDEsinherit. The wizard asks which model each role should use (recommended default, your most used models first, or type any id your IDE lists); answer withmodels:{planner,implementer,verifier}ormodels:{}to accept the defaults. Choices are saved per IDE instackguide.config.json, so mixed teams do not clash.agent action:"plan"returns adelegationblock for the current IDE, and the wizard writesstackguide-implementer.md/stackguide-verifier.mdinto.claude/agents/and.cursor/agents/. Edited files are kept; only theirmodel:line is refreshed.Re-running
setup wizard:trueedits the saved config;.stackguide/stays local and guarded.
Added active
agenttool (execution-first workflow).initnow generates.stackguide/config.jsonautomatically.Added tracker service support for GitHub, GitLab, and Jira.
Added VCS service for branch checks, commit parsing, CI status, and PR/MR creation.
Added test runner service for structured
test/lint/buildexecution.Updated TDD prompts to use active tool calls instead of large passive markdown payloads.
Hardened local persistence:
.stackguideartifacts removed from version controlrepository guard blocks accidental tracking of local artifacts
cache and health history include integrity validation and safer writes
Install By IDE
Cursor
File (workspace):
.cursor/mcp.jsonFile (global):
~/.cursor/mcp.json
{
"mcpServers": {
"stackguide": {
"command": "npx",
"args": ["-y", "@stackguide/mcp-server@latest"]
}
}
}JetBrains (IntelliJ, WebStorm, PhpStorm, etc.)
Open
Settings | Tools | AI Assistant | Model Context Protocol (MCP).Click Add and paste JSON config.
Recommended: set it as Project-level unless you want global scope.
{
"mcpServers": {
"stackguide": {
"command": "npx",
"args": ["-y", "@stackguide/mcp-server@latest"]
}
}
}VS Code
Requirement: GitHub Copilot Chat with MCP enabled.
File (workspace):
.vscode/mcp.jsonVS Code MCP schema uses
serversas root key.
{
"servers": {
"stackguide": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@stackguide/mcp-server@latest"]
}
}
}Visual Studio (Windows, 2022 17.14+ / 2026+)
Enable GitHub Copilot Agent mode.
Supported config locations include:
%USERPROFILE%\\.mcp.json(global)<solution>\\.mcp.json(repo-scoped)<solution>\\.vs\\mcp.json(solution/user-scoped)
Visual Studio MCP schema uses
serversas root key.
{
"servers": {
"stackguide": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@stackguide/mcp-server@latest"]
}
}
}How To Use (Any IDE)
Restart the IDE after adding the MCP configuration.
Open AI chat in agent/tool mode.
Call
setupto detect project context.Call
init action:"full"to scaffold.stackguide/and defaults.Use
agentactions (intake,create_ticket,plan,verify,release) for delivery flow.
Quick Start
Team setup (once per project, then commit stackguide.config.json):
setup wizard:true
setup wizard:true type:"nextjs" architecture:"clean" methodology:"tdd" conventions:["Use named exports"] tracker:"jira"Personal setup:
Configure your project:
setup type:"react-typescript" enableAdaptiveTdd:true model:"gpt-5" integrations:["jira","github"] tokenMode:"compact"
init action:"full" model:"gpt-5" tokenMode:"compact" integrations:["jira","github"] mcpSyncTargets:["cursor","root"] applyMcpTemplates:trueCheck generated setup:
init action:"status"
agent action:"status"Run active TDD workflow:
agent action:"intake" ticket:"PROJ-123"
agent action:"create_ticket" mainDescription:"<MAIN DESCRIPTION>" projectKey:"PROJ"
agent action:"plan" brief:"<brief-from-intake>"
agent action:"verify"
agent action:"release" version:"v1.2.0"Tools (16)
Core
setup: configure StackGuide context for project typecontext: show currently loaded contextrules: list/search/get/select rule setsknowledge: list/search/get knowledge filesreview: analyze files/URLs/project code quality
Utility
cursor: browse/import community rulesdocs: fetch/search/list documentationconfig: save/load/export/import configurationscustom_rule: create/update/delete/list project custom ruleshelp: usage help by topic
Advanced
generate: boilerplate generation (component/hook/service/test/api/model/util)health: project health score and recommendationsanalyze: project intelligence (structure/config/dependency/generate/apply)
Workflow
workflow: lazy-load raw workflow assets (agents/skills/hooks/commands)init: scaffold.stackguidewith stack-aware defaultsagent: active workflow executor (status,intake,create_ticket,plan,verify,release)
Active Workflow Details
agent action:"intake"
reads ticket from configured tracker
returns normalized brief + gaps
proposes branch name convention
can optionally create a Jira ticket first (
createFromDescription:true)
agent action:"create_ticket"
creates Jira issues using strict
MAIN DESCRIPTIONformatuses project defaults from
.stackguide/config.json(projectKey,issueType)derives
summaryfrom first line ofMAIN DESCRIPTIONwhen omitted
agent action:"plan"
inspects conventions + project shape
creates vertical-slice plan
returns exactly 3 target tests in structured format
agent action:"verify"
executes configured tests/lint/build per layer
checks branch naming + commit convention + TDD test budget
returns blocker list and final pass/fail report
agent action:"release"
checks CI status
parses commits since last tag
suggests semver impact (
major/minor/patch)can create tag and PR/MR (when enabled)
Local Data And Security
init generates:
.stackguide/config.json(project workflow config)
Runtime/local artifacts:
.stackguide/analysis-cache.json.stackguide/health-history.json
These are machine-local and must not be committed.
Repository Guard
pnpm lint includes:
pnpm run guard:repoThe guard fails if .stackguide artifacts are tracked.
Integrity Hardening
Cache/history persistence includes:
boundary/symlink checks
file size and entry limits
atomic write strategy
checksum validation
optional HMAC signature using:
STACKGUIDE_INTEGRITY_KEY=<long-random-secret>For teams, configure STACKGUIDE_INTEGRITY_KEY in local/dev and CI environments for stronger tamper resistance.
Supported Stacks
python-django, python-fastapi, python-flask, react-node, react-typescript, vue-node, nextjs, express, nestjs, laravel, rails, golang, rust, custom.
Development
Use pnpm for all commands.
pnpm install
pnpm lint
pnpm test
pnpm build
pnpm devRelease And Version Policy
Current secure baseline:
4.1.2+Versions from
3.0.0up to4.1.1are deprecated in npm due to local artifact hygiene issues.Use the latest
4.xrelease in all environments.
Registry Identifiers
npm package:
@stackguide/mcp-serverMCP Registry server:
io.github.isucorp-taimiralain/stackguide-mcp
License
GPL-3.0
Available Tools
16 toolsagentC
Active agent workflow actions: intake/plan/verify/release plus Jira ticket creation from strict MAIN DESCRIPTION templates.
Inputs: path, brief, action, labels, +22 more.
analyzeC
Project Intelligence: Comprehensive analysis of project structure, configuration, and dependencies. Provides smart recommendations, generates optimal configs, and suggests improvements based on framework best practices.
Inputs: path, action, format, autoFix, +1 more.
configC
Manage saved configurations: save, load, list, delete, export, or import.
Inputs: id, json, name, action.
contextA
Get current context with all loaded rules and knowledge. Use this to see what StackGuide has configured.
Inputs: full.
cursorB
Browse, search, and import rules from cursor.directory community.
Inputs: slug, query, action.
custom_ruleC
Create, update, delete, or list custom rules for your project.
Inputs: id, json, name, action, +2 more.
docsC
Fetch and manage web documentation. Fetch URLs, search cached docs, or list available.
Inputs: url, urls, query, action.
generateA
Generate boilerplate code from templates. Create components, hooks, services, tests, API routes, models, and utilities with best practices built in.
Inputs: name (required), type (required), options.
healthA
Get a comprehensive health score for your project. Analyzes configuration, code quality, structure, documentation, and testing readiness. Returns a grade (A-F) with detailed recommendations.
Inputs: detailed, projectPath.
helpC
Get help about StackGuide tools and how to use them.
Inputs: topic.
initA
Initialize a project with the StackGuide TDD workflow. Auto-detects your stack and scaffolds a .stackguide/ directory with only the relevant agents, skills, hooks and scripts (including the optional OJ health gate).
Inputs: path, type, model, action, +6 more.
knowledgeB
Manage knowledge base: list, search, or get architecture patterns and solutions.
Inputs: query, action, category.
reviewA
Analyze code for issues using pattern matching. Detects security vulnerabilities, performance problems, coding standard violations, and architecture issues. Returns a score (0-100) and detailed report with suggestions. Works on files, URLs, or entire projects.
Inputs: url, file, focus, project.
rulesB
Manage rules: list, search, get, or select rules for your project.
Inputs: ids, query, action, category.
setupB
Configure StackGuide for your project. Auto-detects project type or lets you specify one manually.
Inputs: path, type, model, tokenMode, +5 more.
workflowB
TDD agentic workflow with lazy loading. Load agents, skills, hooks, commands, scripts and the OJ policy on demand to save tokens. Five roles: Intake → Planner → Implementer → Verifier → Releaser.
Inputs: name, action, category.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 16 tools
Several tools have overlapping purposes: knowledge, rules, custom_rule, and cursor all involve managing rules or knowledge, while review, analyze, and health all analyze project quality. Workflow, init, and agent also cover overlapping workflow functionality, making it difficult to choose the correct tool.
All tool names are lowercase with underscores for multi-word names, but there is no consistent verb-noun pattern. Names mix verbs (generate, review, analyze) and nouns (health, context, workflow), and some are ambiguous (setup vs init, agent vs workflow).
With 16 tools, the count is slightly above the typical 3-15 range but reasonable given the broad scope of the server (project setup, code analysis, workflow management). Each tool appears to serve a distinct purpose in the overall system.
The tool surface covers major workflows like code review, project analysis, rule management, and TDD workflow initialization. However, knowledge management lacks create/update/delete operations, and there is no obvious way to manage docs entries beyond fetching/searching, leaving some gaps.
Maintenance
Related MCP Connectors
Read-only AI coding tools for change verification, release readiness, capacity, and guidance.
QA platform for agents: coverage signals, in-repo test plans, verified tests and release governance.
AI code governance and code review for Claude Code, Copilot and Cursor. Checks rules and security.
Scope products with your team, check what is ready to build, and hand ready work to coding agents.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceProvides comprehensive codebase analysis including project structure evaluation, cross-language duplicate detection, microservices validation, and configuration optimization with AI-powered pattern learning that generates actionable improvement reports.MIT

corbatofficial
AlicenseAqualityDmaintenancePolicy and quality engine for AI coding agents that enforces team coding standards and provides validation gates for agent-assisted software delivery.754 npm5MIT- AlicenseAqualityCmaintenanceEnables AI agents to enforce a software delivery standard by validating artifacts against declarative rules, providing templates, glossary terms, and pass/fail verdicts with actionable blockers.8MIT
- AlicenseAqualityBmaintenanceEnables AI coding agents to enforce UI/UX best practices and backend performance auditing, providing design guidelines, compliance checks, component search, and performance optimizations to eliminate generic or sloppy code.7MIT