# io.github.hoklims/stacksfinder (npm · @stacksfinder/mcp-server)

Deterministic tech stack recommendations, audits, and project estimates. No hallucinations.

- Trust score: 67/100 (medium)
- Change this week: +21
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@stacksfinder/mcp-server`: 67/100 (this document), [markdown](https://verifymcp.io/servers/hoklims-stacksfinder/stacksfinder-mcp-server.md), [page](https://verifymcp.io/servers/hoklims-stacksfinder/stacksfinder-mcp-server)

## Channel facts

- Registry: `npm`
- Package: `@stacksfinder/mcp-server`
- Version: `1.3.7`
- 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 (95 of 99), 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 (95 of 99), 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 (MIT).
  - Actively maintained (last published 185 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 64/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2561 tokens (~111/item across 23 items; 23 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **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.

## Install

### Claude

```bash
claude mcp add hoklims-stacksfinder -- npx -y @stacksfinder/mcp-server
```

### Codex

```bash
codex mcp add hoklims-stacksfinder -- npx -y @stacksfinder/mcp-server
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add hoklims-stacksfinder --command npx --arg -y --arg @stacksfinder/mcp-server
```

### Hermes

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

### Other

```json
{
  "mcpServers": {
    "hoklims-stacksfinder": {
      "command": "npx",
      "args": [
        "-y",
        "@stacksfinder/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.

### 2026-08-03 (score 67, +4)

- [functional improvement] Stability: unverified → 0.27

### 2026-08-02 (score 63, +42)

- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] Schema quality: unverified → good
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] License: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional] Licence: MIT

### 2026-08-01 (score 21, +15)

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

### 2026-07-31 (score 6, −40)

- [security regression] Malware scan: pass → unverified
- [functional regression] Tool coverage: 100 → unverified

### 2026-07-30 (score 46, +21)

- [functional regression] Dependency health: partial → unverified
- [functional improvement] Tool coverage: unverified → 100

### 2026-07-28 (score 25, −21)

- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] Dependency health: unverified → partial
- [functional] First check of Schema quality: unverified

### 2026-07-27 (score 46)

First indexed and scored.

## MCP tools (23)

### `list_technologies` (~38 tokens)

List Technologies

Lists all available technology IDs for use with other tools. Essential for discovering valid technology identifiers.

Input parameters:

- `category` (string): Filter by category

### `analyze_tech` (~50 tokens)

Analyze Technology

Detailed analysis of a technology with 6-dimension scores, strengths, weaknesses, and compatible technologies.

Input parameters:

- `context` (string): Context for scoring
- `technology` (string, required): Technology ID to analyze

### `compare_techs` (~49 tokens)

Compare Technologies

Side-by-side comparison of 2-4 technologies with per-dimension winners and compatibility matrix.

Input parameters:

- `context` (string): Context for scoring
- `technologies` (array, required): Technologies to compare

### `recommend_stack_demo` (~86 tokens)

Recommend Stack (Demo)

Try StacksFinder's tech stack recommendations for FREE - once per day, no account required.

Returns the optimal technology for each category based on deterministic scoring.
For unlimited access, priorities, constraints, and AI-generated narratives, upgrade to Pro at https://stacksfinder.com/pricing

Input parameters:

- `projectType` (string, required): Type of project
- `scale` (string): Project scale

### `recommend_stack` (~72 tokens)

Recommend Stack

Recommends the best tech stack for a project using real-time scoring with context adjustments. Requires API key.

Input parameters:

- `constraints` (array): Project constraints
- `priorities` (array): Top priorities (max 3)
- `projectType` (string, required): Type of project
- `scale` (string): Project scale

### `get_blueprint` (~43 tokens)

Get Blueprint

Fetches an existing blueprint by ID. Blueprints are generated via the StacksFinder web UI. Requires API key.

Input parameters:

- `blueprintId` (string, required): Blueprint UUID

### `create_blueprint` (~207 tokens)

Create Blueprint

Creates a new tech stack blueprint for a project. Requires API key with 'blueprint:write' scope.

The blueprint generation is asynchronous. By default, this tool waits for completion and returns the full blueprint.
Set waitForCompletion=false to get the job ID immediately for manual polling.

Example usage:
\- Create a SaaS MVP: projectType="saas", scale="mvp", priorities=["time-to-market", "cost-efficiency"]
\- Create an enterprise API: projectType="api", scale="enterprise", priorities=["security", "scalability"]

Input parameters:

- `constraints` (array): Technology constraint IDs (optional)
- `priorities` (array): Top 3 priorities (optional)
- `projectDescription` (string): Brief description (optional)
- `projectName` (string): Project name (optional)
- `projectType` (string, required): Type of project
- `scale` (string, required): Project scale
- `waitForCompletion` (boolean): Wait for completion (default: true)

### `setup_api_key` (~81 tokens)

Setup API Key

Authenticates with your StacksFinder account and creates an API key. Requires Pro or Team tier. The key is returned once and should be saved securely.

Input parameters:

- `email` (string, required): Your StacksFinder account email
- `keyName` (string): Optional name for the API key
- `password` (string, required): Your StacksFinder account password

### `list_api_keys` (~23 tokens)

List API Keys

Lists your StacksFinder API keys. Requires a configured API key.

### `revoke_api_key` (~37 tokens)

Revoke API Key

Revokes an API key. This action cannot be undone.

Input parameters:

- `keyId` (string, required): The UUID of the API key to revoke

### `create_audit` (~88 tokens)

Create Technical Debt Audit

Create a technical debt audit for a list of technologies. 
Analyzes your stack for deprecated packages, security vulnerabilities, EOL versions, and upgrade recommendations.
Returns findings with severity (critical/high/medium/low/info) and actionable suggestions.
Requires API key with audit:write scope.

Input parameters:

- `name` (string, required): Name for the audit report
- `technologies` (array, required): Technologies to audit

### `get_audit` (~35 tokens)

Get Audit Report

Fetch a completed audit report by ID. Returns all findings and health score.

Input parameters:

- `auditId` (string, required): Audit report UUID

### `list_audits` (~47 tokens)

List Audit Reports

List your audit reports with pagination. Shows name, status, health score, and creation date.

Input parameters:

- `limit` (number): Max results
- `offset` (number): Pagination offset

### `compare_audits` (~74 tokens)

Compare Audit Reports

Compare two audit reports to track technical debt trends over time.
Shows new issues introduced, issues resolved, and health score change.
Useful for measuring progress on debt reduction.

Input parameters:

- `baseAuditId` (string, required): Base (older) audit ID
- `compareAuditId` (string, required): Compare (newer) audit ID

### `get_audit_quota` (~20 tokens)

Get Audit Quota

Check your remaining audit quota for this month.

### `get_migration_recommendation` (~88 tokens)

Get Migration Recommendation

Analyze an audit report for migration opportunities.
Returns a detailed migration recommendation including:
\- Technologies that should be replaced
\- Recommended modern alternatives
\- Migration roadmap with phases
\- Risk assessment
\- Builder constraints to pre-fill for generating a migration blueprint

Use this after create_audit to get actionable migration guidance.

Input parameters:

- `auditId` (string, required): Audit report UUID to analyze for migration

### `generate_mcp_kit` (~218 tokens)

Generate MCP Kit

Generate a complete project kit with optimal tech stack and MCP recommendations based on your project description.

Describe your project and get:
1\. **Optimal Tech Stack**: Best technologies for each category (frontend, backend, database, auth, hosting, payments)
2\. **MCP Recommendations**: AI-assistant tools tailored to your chosen technologies
3\. **Install Configurations**: Ready-to-use configs for Claude Desktop, Cursor, and Windsurf

Example prompts:
\- "I'm building a SaaS for project management with real-time collaboration"
\- "Building an MVP for a marketplace connecting freelancers with clients"
\- "Creating an e-commerce platform with Stripe payments and PostgreSQL"

Input parameters:

- `constraints` (array): Tech constraints (e.g., must-use-postgresql)
- `priorities` (array): Top priorities (max 3)
- `projectDescription` (string, required): Describe your project (50-5000 chars)
- `projectType` (string): Project type (if known)
- `scale` (string): Project scale (if known)

### `analyze_repo_mcps` (~191 tokens)

Analyze Repository MCPs

Analyze your current repository to detect the tech stack and recommend relevant MCP servers.

This tool examines your project files (package.json, .env, config files, etc.) to:
1\. Detect frontend, backend, database, auth, hosting, and payment technologies
2\. Find already installed MCP servers
3\. Recommend new MCPs that would enhance your development workflow
4\. Generate ready-to-use install configurations for Cursor, Claude Desktop, and Windsurf

Example use cases:
\- "What MCPs would help with my project?"
\- "Analyze my repo and suggest useful MCP servers"
\- "Which MCPs am I missing based on my tech stack?"

Input parameters:

- `includeInstalled` (boolean): Include already installed MCPs (default: false)
- `mcpConfigPath` (string): Override path to MCP configuration file
- `workspaceRoot` (string): Override workspace root directory (default: current directory)

### `prepare_mcp_installation` (~303 tokens)

Prepare MCP Installation

Analyze your repository and generate a .env-mcp configuration file for MCP server installation.

This tool:
1\. Detects your tech stack from project files (package.json, .env, etc.)
2\. Identifies which MCP servers would benefit your project
3\. Finds already installed MCPs to avoid duplicates
4\. Generates a .env-mcp template file with all required environment variables

The generated .env-mcp file contains:
\- INSTALL_xxx flags to control which MCPs to install
\- Required and optional environment variables for each MCP
\- Documentation links and examples

After running this tool:
1\. Open the generated .env-mcp file
2\. Fill in the API keys and configuration values
3\. Set INSTALL_xxx=false for MCPs you don't want
4\. Run execute_mcp_installation to complete the setup

Example use cases:
\- "Prepare MCP installation for my project"
\- "Generate .env-mcp for my tech stack"
\- "What MCPs do I need and what credentials do they require?"

Input parameters:

- `envMcpPath` (string): Path where .env-mcp will be created (default: .env-mcp in workspaceRoot)
- `includeInstalled` (boolean): Include already installed MCPs in the preparation (default: false)
- `mcpConfigPath` (string): Override path to existing MCP configuration file
- `workspaceRoot` (string): Workspace root directory (default: current directory)

### `execute_mcp_installation` (~302 tokens)

Execute MCP Installation

Read a .env-mcp configuration file and generate installation commands for the MCPs.

This tool:
1\. Reads the .env-mcp file generated by prepare_mcp_installation
2\. Validates that required environment variables are present
3\. Generates installation commands for the target IDE/client
4\. Returns post-installation instructions

Prerequisites:
\- Run prepare_mcp_installation first to generate .env-mcp
\- Fill in the required API keys and credentials in .env-mcp
\- Set INSTALL_xxx=false for MCPs you want to skip

Supported targets:
\- claude-code: Generates 'claude mcp add-json' commands
\- claude-desktop: Generates JSON config for claude_desktop_config.json
\- cursor: Generates JSON config for Cursor MCP settings
\- vscode: Generates JSON config for VS Code MCP extension
\- windsurf: Generates JSON config for Windsurf

Output:
\- Individual commands/configs for each ready MCP
\- Aggregate command (for Claude Code) or config (for others)
\- List of MCPs missing required credentials
\- Post-installation instructions

Input parameters:

- `dryRun` (boolean): Only generate commands without marking ready to execute (default: false)
- `envMcpPath` (string): Path to .env-mcp file (default: .env-mcp in current directory)
- `targetClient` (string): Target IDE/client for installation (default: claude-code)

### `check_mcp_compatibility` (~270 tokens)

Check MCP Compatibility

Check compatibility between MCP servers. Detects conflicts (e.g., two database providers), redundancies (e.g., two ORMs), and synergies (e.g., GitHub + Vercel).

Returns a health score (0-100) with grade (A/B/C/D) and detailed breakdown.

\**Examples:**
\- Check database compatibility: `["supabase-mcp", "neon-mcp"]` → conflict detected
\- Check ORM redundancy: `["prisma-mcp", "drizzle-mcp"]` → redundancy warning
\- Check synergies: `["stripe-mcp", "resend-mcp"]` → synergy detected

\**Supported MCP IDs include:**
\- supabase-mcp
\- neon-mcp
\- planetscale-mcp
\- turso-mcp
\- prisma-mcp
\- drizzle-mcp
\- clerk-mcp
\- auth0-mcp
\- stripe-mcp
\- paddle-mcp
...and more.

\**Aliases supported:**
\- "supabase" → "supabase-mcp"
\- "@neondatabase/mcp" → "neon-mcp"
\- "stripe" → "stripe-mcp"

Input parameters:

- `mcps` (array, required): Array of MCP server IDs to check compatibility between

### `estimate_project` (~217 tokens)

Estimate Project

Estimate scope, pricing, and analyze market for a software project.

Provides:
\- Detailed hour breakdown by feature (with complexity assessment)
\- Price ranges by team seniority level (junior/mid/senior/expert)
\- Competitor analysis and market trends (real-time via Perplexity) [Pro tier]
\- Market size and gaps identification [Pro tier]
\- Risk identification with mitigation suggestions

Perfect for freelancers and agencies creating quotes.
Requires API key with estimate:write scope.

\**Pricing is 100% deterministic** - same inputs always produce same outputs.
Market analysis is best-effort and may vary with web data changes.

Input parameters:

- `includeMarket` (boolean): Include market analysis (default: true, Pro tier only)
- `region` (string): Region for pricing (default: france)
- `seniorityLevel` (string): Average team seniority (default: mid)
- `specs` (string, required): Project specifications (min 100 chars, max 10,000)
- `teamSize` (number): Number of developers

### `get_estimate_quota` (~22 tokens)

Get Estimate Quota

Check your remaining estimate quota for this week and month.

## Diagnostics

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

## Score history

- 2026-08-03: 67
- 2026-08-02: 63
- 2026-08-01: 21
- 2026-07-31: 6
- 2026-07-30: 46
- 2026-07-28: 25
- 2026-07-27: 46

## Links

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