Utilizes Zod for input validation in the MCP server, ensuring reliable data handling when processing requests and responses.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Mercado Livre MCP Server get products for iPhone 15"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
This project is part of the Model Context Protocol (MCP) ecosystem and provides tools for integrating with external sources and managing specific domain models. It is designed to demonstrate how to build an MCP server that scrapes products from Mercado Livre, with strong data validation to ensure reliability.
Related MCP server: Investidor10 MCP Server
get-produtos: Fetch basic product information.
Input validation using Zod.
Integration with the Mercado Livre API using fetch (infrastructure layer).
The project follows a layered architecture inspired by Domain-Driven Design (DDD) patterns:
Domain (src/domain):
Defines interfaces and types that represent data structures (e.g., Mercado Livre).
Infrastructure (src/infrastructure):
Implements external services, such as MercadoLivreApiService, responsible for making HTTP calls to the Mercado Livre API.
Application (src/application):
Contains business logic in MercadoLivreService, which processes and formats data from the infrastructure.
Interface (src/interface):
Includes controllers (MercadoLivreToolsController) that register tools in the MCP server, define validation schemas, and return results.
Entry Point (src/main.ts):
Initializes the McpServer, configures the transport (StdioServerTransport), instantiates services and controllers, and starts listening on stdio.
The folder structure is as follows:
src/
├── domain/
│ └── models/ # Domain interfaces
├── infrastructure/
│ └── services/ # External API implementations (Mercado Livre)
├── application/
│ └── services/ # Business logic and data formatting
├── interface/
│ └── controllers/ # MCP tool registration and validation
└── main.ts # Server entry point
build/ # Compiled JavaScript code
.vscode/ # Contains the mcp.json file, MCP Server configgit clone git@github.com:newerton/mcp-mercado-livre.git
cd mcp-mercado-livre
npm install
npm run buildPress Ctrl+Shift+P and select "MCP: List Servers"
Select "products" and then "Start Server"
Press Ctrl+Shift+P and select "MCP: List Servers"
Select "products" and then "Show Output"
Pull requests are welcome! Feel free to open issues and discuss improvements.
This project is licensed under the MIT license - see the LICENSE file for details.
Buscar informações básicas de produtos
| Name | Required | Description | Default |
|---|---|---|---|
| products | Yes | Array of product names |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It states the tool searches for basic product information, but doesn't disclose behavioral traits like whether it's read-only, requires authentication, has rate limits, or what happens with invalid inputs. This leaves significant gaps in understanding how the tool behaves.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence in Portuguese ('Buscar informações básicas de produtos') that's appropriately sized and front-loaded. There's no wasted text, though it could be slightly more informative without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations, no output schema, and a simple input schema, the description is incomplete. It doesn't explain what 'basic information' includes, how results are returned, or any error handling, making it inadequate for a tool that presumably returns data based on product names.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, with the 'products' parameter documented as 'Array of product names'. The description adds no additional meaning beyond this, so it meets the baseline of 3 where the schema does the heavy lifting, but doesn't compensate or enhance parameter understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Buscar informações básicas de produtos' (Search for basic product information) states a clear verb ('Buscar') and resource ('produtos'), but it's vague about what constitutes 'basic information' and doesn't specify scope or format. Without sibling tools, differentiation isn't needed, but the purpose remains somewhat ambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool—there's no mention of prerequisites, alternatives, or specific contexts. The description implies it's for searching product info, but offers no further usage instructions, leaving the agent to infer appropriate scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
get-produtosScored across 1 tool
With only one tool, there is no possibility of confusion or overlap between tools. The tool has a clear and distinct purpose, making disambiguation trivial.
The single tool name follows a consistent verb-noun pattern (get-produtos), and with no other tools to compare, there is no inconsistency in naming conventions.
One tool is too few for a server named 'Mercado Livre MCP Server', which suggests a marketplace domain. This minimal set likely leaves significant gaps in functionality, such as creating, updating, or deleting products, or handling orders and users.
The tool surface is severely incomplete for a marketplace server. It only provides basic product information retrieval, missing essential operations like product creation, updates, order management, and user interactions, which are critical for such a domain.
The Mercado Pago MCP Server implements the Model Context Protocol to provide AI agents and LLMs with access to Mercado Pago's APIs and tools within compatible development environments. It acts as an intermediary that translates Mercado Pago resources into executable functions (tools) that AI applications can invoke to perform actions and automate flows. The server simplifies integration, enables using documentation to implement or improve code, and optimizes operations through natural language interactions without manual implementations.
Mercado Livre (Latin America's largest marketplace) via the official API, seller profile and reputat
MCP server for Product Management
Unified MCP server for 70+ eCommerce platforms: products, orders, customers, and more.
