Stacksfinder

Provides deterministic tech stack recommendations and blueprints via MCP for supported clients.

typescript

0

GitHub Stars

typescript

Language

6 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "hoklims-stacksfinder-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@stacksfinder/mcp-server"
      ],
      "env": {
        "STACKSFINDER_API_KEY": "sk_live_xxx",
        "STACKSFINDER_API_URL": "https://stacksfinder.com",
        "STACKSFINDER_MCP_DEBUG": "false"
      }
    }
  }
}

You use the Stacksfinder MCP Server to get deterministic, data-driven technology stack recommendations for your projects. It integrates with MCP-enabled clients so you can request tailored stacks, blueprints, and AI-assisted narratives without leaving your workflow.

How to use

You connect an MCP client to the server by pointing the client at the Stacksfinder MCP endpoint or local runtime. With a valid API key, you unlock pro tools that generate unlimited recommendations, blueprints, and AI narratives. You can perform free actions like listing technologies, analyzing techs, comparing options, and requesting a full stack recommendation once per day in demo mode. Use the client’s MCP configuration to reference the server, and supply your API key when you need Pro features.

How to install

Prerequisites: ensure you have Node.js installed on your system. You will also need a package manager such as npm or npx available in your environment.

Step 1: Start the MCP server locally using the runtime command shown in the quick start. This runs the server directly from your development environment.

npx -y @stacksfinder/mcp-server

Configure with an API key (optional for full features)

If you want full features, provide your API key for authentication. Set the key in the environment before starting the server.

STACKSFINDER_API_KEY=sk_live_xxx npx -y @stacksfinder/mcp-server

Alternative ways to run with an API key (examples for clients)

If you are wiring this into an MCP client, you can supply the API key via environment variables in your client’s MCP configuration to enable Pro tools.

Notes for client configuration

When you add the MCP server to a client, you will typically provide a command and optional environment variables so the client can launch the server as part of your project. The examples below show a common pattern you can adapt to your setup.

Security and access

Keep your API key secret. Do not commit keys to version control. Use environment variables or secret managers in your deployment workflow.

Available tools

list_technologies

List all tech IDs by category to understand available options.

analyze_tech

Evaluate a technology with 6-dimension scores, strengths, weaknesses, and compatible techs.

compare_techs

Compare two to four technologies side-by-side to inform decisions.

recommend_stack

Generate a full stack recommendation for a project type, with optional constraints (free demo) or unlimited Pro usage.

get_blueprint

Fetch an existing blueprint by its ID.

create_blueprint

Generate a new blueprint with an AI narrative.

setup_api_key

Create and manage API keys for Pro tools.

list_api_keys

List your existing API keys.

revoke_api_key

Revoke an API key.