# io.github.taimiralain/stackguide-mcp (npm · @stackguide/mcp-server)

Dynamic context loading for AI assistants with TDD workflow and AST analysis

- Trust score: 65/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@stackguide/mcp-server`: 65/100 (this document), [markdown](https://verifymcp.io/servers/taimiralain-stackguide-mcp/stackguide-mcp-server.md), [page](https://verifymcp.io/servers/taimiralain-stackguide-mcp/stackguide-mcp-server)

## Channel facts

- Registry: `npm`
- Package: `@stackguide/mcp-server`
- Version: `4.2.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (141 of 145), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (141 of 145), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (GPL-3.0).
  - Actively maintained (last published 3 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 73/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 2248 tokens (~51/item across 44 items; 16 tools + 28 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add taimiralain-stackguide-mcp -- npx -y @stackguide/mcp-server
```

### Codex

```bash
codex mcp add taimiralain-stackguide-mcp -- npx -y @stackguide/mcp-server
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "taimiralain-stackguide-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@stackguide/mcp-server"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add taimiralain-stackguide-mcp --command npx --arg -y --arg @stackguide/mcp-server
```

### Hermes

```yaml
mcp_servers:
  taimiralain-stackguide-mcp:
    command: "npx"
    args: ["-y", "@stackguide/mcp-server"]
```

### Other

```json
{
  "mcpServers": {
    "taimiralain-stackguide-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@stackguide/mcp-server"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 65, +34)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: 100 → unverified
- [functional improvement] License: unverified → pass
- [functional improvement] Schema quality: unverified → fair
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional] Licence: GPL-3.0

### 2026-08-01 (score 31, −4)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-31 (score 35)

First indexed and scored.

## MCP tools (16)

### `setup` (~189 tokens)

Configure StackGuide for your project. Auto-detects project type or lets you specify one manually.

Input parameters:

- `enableAdaptiveTdd` (boolean): Enable the adaptive TDD setup wizard that asks for model and integration preferences
- `integrations` (array): External MCP integrations to scaffold as templates
- `jiraIssueType` (string): Default Jira issue type (Task, Story, Bug...)
- `jiraProjectKey` (string): Default Jira project key used when creating tickets from descriptions
- `mcpSyncTargets` (array): Where MCP template servers should be synchronized
- `model` (string): Preferred model identifier for TDD runs (saved in .stackguide/config.json)
- `path` (string): Project path (default: current directory)
- `tokenMode` (string): Token profile for prompts and workflow responses
- `type` (string): Project type to use (auto-detected if not specified)

### `context` (~47 tokens)

Get current context with all loaded rules and knowledge. Use this to see what StackGuide has configured.

Input parameters:

- `full` (boolean): Include full rule/knowledge content (default: false, shows summary)

### `rules` (~75 tokens)

Manage rules: list, search, get, or select rules for your project.

Input parameters:

- `action` (string): Action to perform
- `category` (string): Filter by category
- `ids` (array): Rule IDs to select (for select action)
- `query` (string): Search term or rule ID (for search/get actions)

### `knowledge` (~54 tokens)

Manage knowledge base: list, search, or get architecture patterns and solutions.

Input parameters:

- `action` (string): Action to perform
- `category` (string): Filter by category
- `query` (string): Search term or knowledge ID

### `review` (~100 tokens)

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.

Input parameters:

- `file` (string): File path to review
- `focus` (string): Focus area for review
- `project` (boolean): Review entire project structure
- `url` (string): URL to fetch and review

### `cursor` (~53 tokens)

Browse, search, and import rules from cursor.directory community.

Input parameters:

- `action` (string): Action to perform
- `query` (string): Category to browse or search term
- `slug` (string): Rule slug for import

### `docs` (~67 tokens)

Fetch and manage web documentation. Fetch URLs, search cached docs, or list available.

Input parameters:

- `action` (string): Action to perform
- `query` (string): Search query
- `url` (string): URL to fetch or document ID
- `urls` (array): Multiple URLs to fetch

### `config` (~72 tokens)

Manage saved configurations: save, load, list, delete, export, or import.

Input parameters:

- `action` (string): Action to perform
- `id` (string): Configuration ID (for load/delete/export)
- `json` (string): JSON string (for import)
- `name` (string): Configuration name (for save)

### `custom_rule` (~86 tokens)

Create, update, delete, or list custom rules for your project.

Input parameters:

- `action` (string): Action to perform
- `category` (string): Rule category
- `content` (string): Rule content in markdown
- `id` (string): Rule ID (for update/delete)
- `json` (string): JSON string (for import)
- `name` (string): Rule name

### `help` (~28 tokens)

Get help about StackGuide tools and how to use them.

Input parameters:

- `topic` (string): Help topic

### `generate` (~81 tokens)

Generate boilerplate code from templates. Create components, hooks, services, tests, API routes, models, and utilities with best practices built in.

Input parameters:

- `name` (string, required): Name for the generated code (e.g., UserCard, useAuth, ApiService)
- `options` (object): Generation options
- `type` (string, required): Type of code to generate

### `health` (~76 tokens)

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.

Input parameters:

- `detailed` (boolean): Include detailed breakdown by category (default: true)
- `projectPath` (string): Project path to analyze (default: current project)

### `workflow` (~110 tokens)

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.

Input parameters:

- `action` (string): Action to perform
- `category` (string): Filter list by category
- `name` (string): Name of the item to load (e.g. "tdd-planner", "tdd-core", "verify", "oj-verify")

### `init` (~207 tokens)

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).

Input parameters:

- `action` (string): Action to perform
- `applyMcpTemplates` (boolean): If true, writes MCP integration templates into selected manifests
- `integrations` (array): External MCP integrations to scaffold in local manifests
- `jiraIssueType` (string): Default Jira issue type (Task by default)
- `jiraProjectKey` (string): Default Jira project key for ticket creation
- `mcpSyncTargets` (array): Target manifest files for MCP synchronization
- `model` (string): Preferred model identifier saved for adaptive TDD
- `path` (string): Project path (default: current directory)
- `tokenMode` (string): Token profile for adaptive TDD
- `type` (string): Force a project type instead of auto-detecting

### `agent` (~450 tokens)

Active agent workflow actions: intake/plan/verify/release plus Jira ticket creation from strict MAIN DESCRIPTION templates.

Input parameters:

- `acceptanceCriteria` (array): Acceptance criteria list for strict Jira template
- `action` (string): Active workflow action
- `brief` (string): Structured or plain brief text for planning
- `createFromDescription` (boolean): When action is intake, create Jira ticket first from MAIN DESCRIPTION template
- `createPullRequest` (boolean): If true, release action opens PR/MR when provider is configured
- `createTag` (boolean): If true, release action creates annotated git tag when CI is green
- `dataTransformation` (string): DATA TRANSFORMATION section content
- `destinationController` (string): DESTINATION section value: Controller
- `destinationModel` (string): DESTINATION section value: Model
- `destinationRoute` (string): DESTINATION section value: Route
- `destinationView` (string): DESTINATION section value: View
- `issueType` (string): Optional Jira issue type override (Task/Story/Bug)
- `labels` (array): Optional labels to set when creating Jira tickets
- `mainDescription` (string): MAIN DESCRIPTION body used to create Jira tickets
- `originComponent` (string): ORIGIN section value: Component
- `originKeyLogic` (string): ORIGIN section value: Key Logic
- `originOldQuery` (string): ORIGIN section value: Old Query
- `path` (string): Project path (default: current directory)
- `projectKey` (string): Optional Jira project key override
- `prototypeDesignPattern` (string): PROTOTYPES section value: Design Pattern
- `prototypeProps` (string): PROTOTYPES section value: Props
- `prototypeRelatedFiles` (array): PROTOTYPES related files list
- `prototypeView` (string): PROTOTYPES section value: View
- `summary` (string): Optional Jira summary (defaults to first line of MAIN DESCRIPTION)
- `ticket` (string): Ticket key for intake/plan actions (e.g. PROJ-123)
- `version` (string): Target release version for release action (e.g. v1.2.0)

### `analyze` (~108 tokens)

Project Intelligence: Comprehensive analysis of project structure, configuration, and dependencies. Provides smart recommendations, generates optimal configs, and suggests improvements based on framework best practices.

Input parameters:

- `action` (string): Type of analysis to perform
- `autoFix` (boolean): Automatically apply safe fixes (default: false)
- `configType` (string): Config type to generate (for action:"generate")
- `format` (string): Output format
- `path` (string): Project path to analyze (default: current directory)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/taimiralain-stackguide-mcp/stackguide-mcp-server#diagnostics

## Score history

- 2026-08-03: 65
- 2026-08-02: 65
- 2026-08-01: 31
- 2026-07-31: 35

## Links

- npm package: https://www.npmjs.com/package/@stackguide/mcp-server
- Socket report: https://socket.dev/npm/package/@stackguide/mcp-server
- Repository: https://github.com/taimiralain/StackGuide-MCP
- Changelog RSS feed: https://verifymcp.io/servers/taimiralain-stackguide-mcp/stackguide-mcp-server/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/taimiralain-stackguide-mcp/stackguide-mcp-server/changelog.json
- HTML version of this page: https://verifymcp.io/servers/taimiralain-stackguide-mcp/stackguide-mcp-server