MercadoLibre MCP Server

by dedero1985

Overview Schema Source Related Servers Discussions Admin

Search Items

search_items

Search products on MercadoLibre across Latin American sites using filters like query, price range, and condition to find items in Argentina, Brazil, Uruguay, and more.

Instructions

Search for products on MercadoLibre across a site (public data — any authenticated profile can read it, regardless of which country it belongs to).

Usage examples:

"Find iPhone 15 in Argentina" → query="iPhone 15", site_id="MLA"
"Search for zapatillas running under 5000 pesos in Uruguay" → query="zapatillas running", price_max=5000, site_id="MLU"
"Find laptops in Brazil" → query="notebook", site_id="MLB"

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "input": "<input>"
    },
    "name": "search_items"
  }
}

Input Schema

Name	Required	Description	Default
`input`	Yes

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 11, 2026

TDQS

A3.6/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the behavioral burden and does add one valuable trait: the data is public and readable by any authenticated profile regardless of country. It says nothing about pagination behavior, result caps, or rate/permission limits that a search tool would benefit from disclosing.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded ahead of the examples, and the parenthetical about public data is worth its words. The bulleted example block is well-structured; the only slight drag is the length of the access note.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained, and the nested schema documents the query parameters. For a no-annotation tool the description covers access semantics and realistic invocations, though it omits pagination guidance and any note on which sibling to prefer for owned-listing or category browsing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Reported coverage is 0%, though the nested schema fields do carry their own descriptions. The description compensates only partially, demonstrating query, site_id, and price_max usage in examples while leaving condition, category_id, offset, and account undiscussed. The examples are useful but not a full substitute.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb+resource ('Search for products on MercadoLibre') and adds the scoping detail 'across a site', so an agent knows exactly what it retrieves. It does not contrast itself against siblings like list_my_items or list_categories, so differentiation is left to inference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The three worked examples ('Find iPhone 15 in Argentina' → query + site_id, price-constrained search, laptops in Brazil) make the intended invocation context very concrete. There is no explicit when-not-to-use or routing to an alternative tool, so it stops short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.