Skip to main content
Glama
zeluizr

Adobe Commerce MCP

Search Adobe Commerce docs

search-docs
Read-onlyIdempotent

Search official Adobe Commerce/Magento developer docs offline to answer how-to questions on PHP, frontend, Web APIs, and operations. Returns excerpts with URLs and source paths.

Instructions

Search the official Adobe Commerce (Magento Open Source) developer documentation bundled offline: PHP extensions, frontend core, Web APIs and operations. Use it first for any "how do I" question about modules, plugins, DI, events, declarative schema, layouts, caching, indexers, queues or configuration. Returns excerpts with title, public URL and source path; follow up with read-doc.

Input Schema

NameRequiredDescriptionDefault
areaNoRestrict to one doc set: php (PHP extensions), frontend (themes, layouts, UI components, JS), webapi (REST and GraphQL guides), operations (configuration, CLI, installation, performance)
limitNoMax results (default 5, max 20)
queryYesKeywords to look for in the official Adobe Commerce docs (e.g. "plugin around method", "declarative schema foreign key", "message queue consumer", "full page cache private content")

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile needs no restating. The description adds genuinely new context: the corpus is bundled offline (so no network freshness or live-doc assumptions), results are excerpts carrying title, public URL and source path, and read-doc is the drill-down path. It doesn't discuss ranking or relevance behavior, which is the only meaningful gap.

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

Conciseness5/5

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

Three compact sentences in a clear order: what it searches, when to use it, what comes back and what to do next. The topic enumeration is dense but every item is a real retrieval cue; nothing is filler.

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?

With no output schema, the description correctly compensates by saying results are excerpts with title, URL and source path, plus the read-doc follow-up, which is what an agent needs to chain calls. Only minor omissions remain, such as result ordering or whether excerpts are truncated.

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?

Schema coverage is 100%, so query, area, and limit are already fully documented with examples, enum meanings and the default/max. The description's recital of the four doc areas roughly mirrors the area enum without adding format or query-syntax guidance beyond the schema. Baseline 3 is appropriate when the schema carries the load.

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

Purpose5/5

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

States a specific verb (Search) and a precisely scoped resource: the official Adobe Commerce/Magento developer documentation bundled offline, broken down into PHP extensions, frontend core, Web APIs and operations. It also names read-doc as the follow-up tool, so an agent can separate it from siblings like lookup-webapi or lookup-cli-command without opening a schema.

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?

"Use it first for any 'how do I' question" is an explicit routing directive that prioritizes this tool over siblings, and the enumerated topic list (modules, plugins, DI, events, declarative schema, layouts, caching, indexers, queues, configuration) gives concrete triggers. It stops short of saying when to prefer lookup-webapi or lookup-cli-command instead, so the exclusions are implied rather than stated.

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