Skip to main content
Glama
ai-market-intelligence

ai-market-intelligence

by gabivech

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: LLM Benchmark MCP Server

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.

  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.

Available Tools

4 tools
compare_modelsComparar modelosB

Compara até quatro modelos para um cenário específico e mostra a classificação.

Inputs: ids (required), scenario (required).

explain_scenariosExplicar cenáriosA

Explica os cenários avaliados e os pesos usados pelo mecanismo de recomendação.

Inputs: no named parameters.

list_modelsListar modelosB

Lista os perfis de modelos presentes no catálogo local.

Inputs: provider.

recommend_modelRecomendar modeloC

Ordena modelos do catálogo para um cenário, orçamento e requisito de hospedagem própria.

Inputs: scenario (required), limit, budget, requiresSelfHosted.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.3/5.0

    Scored across 4 tools

    Disambiguation4/5

    The tools are mostly distinct: list_models lists catalog items, recommend_model ranks them, compare_models compares a subset, and explain_scenarios describes the reasoning. However, recommend_model and compare_models could be confused since both rank/compare for a scenario, though compare_models explicitly limits to four.

    Naming Consistency4/5

    All tools follow a verb_noun pattern (list_models, recommend_model, compare_models, explain_scenarios). However, the verbs vary in style - 'list', 'recommend', 'compare' are action verbs, while 'explain' is also action but the noun 'scenarios' differs from 'models' - but the pattern is consistent.

    Tool Count4/5

    With 4 tools, the set is slightly small for a domain that includes model cataloging, recommendation, comparison, and explanation, but it is reasonable for a focused utility. Each tool serves a distinct function and the count is acceptable, though a bit sparse.

    Completeness3/5

    The domain appears to be model recommendation and comparison, and the tools cover listing, recommending, comparing, and explaining the logic. However, there is no tool to get details of a single model or to manage the catalog (add/update/delete), which are notable gaps for a complete surface.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      D
      quality
      D
      maintenance
      Describe your AI use case in plain English, get ranked model recommendations with cost estimates and tradeoff reasoning. Covers 62 models across 29 providers. Available as a web app (BYOK + guest tier) and as an MCP server for Claude Desktop and Cursor — same recommendation engine, two interfaces.
      1
      1
      MIT