AI Market MCP

A local MCP server in TypeScript for comparing AI models by scenario: programming, support, documents, multimodal, agents, and privacy.

What this first version does

• lists the local model catalog;

• recommends models with explicit criteria for capability, context, relative cost, and self-hosting;

• compares selected models;

• explains the weights used in each scenario.

The profiles in src/catalog.ts are qualitative and initial: they are not official prices or benchmarks. Validate the recommendation with evaluations in your domain and update the sources before a purchase decision.

Related MCP server: ai-compass

Running

npm install
npm run build
npm run dev

To test with MCP Inspector:

npm run inspect

Connecting in VS Code

Create or update .vscode/mcp.json in the project that will use the server:

{
  "servers": {
    "ai-market-intelligence": {
      "command": "node",
      "args": ["C:/Users/gabiv/Projects/ai-market-intelligence-mcp/dist/index.js"]
    }
  }
}

After running npm run build, open the MCP section of VS Code/Copilot and start the server. The transport is stdio; therefore, the program never writes logs to stdout.

Recommended next steps

1. JSON file or SQLite database for data and version history.

2. Collector of official sources (prices, context windows, and limits), with date and URL for each data point.

3. Evaluation with real prompts and metrics from your business, instead of relying on generic comparisons.

4. HTTP interface with authentication, if you want to share the server with a team.