Skip to main content
Glama
pavelpikta

lampa-mcp-server

by pavelpikta
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Validate Lampa plugin, grep, i18n, or build

validate_code
Read-onlyIdempotent

Run code quality checks and hints to detect common pitfalls, scan for TODOs, debug logs, hardcoded strings, evaluate translation coverage, and suggest build commands without executing them.

Instructions

Run checks and hints, not catalogs (list_catalog) and not edit plans (plan_change). mode=plugin scores a plugin against official pitfalls; grep scans the snapshot for TODOs/console.log/undefined/lang/hardcoded HTML (not a shell); i18n looks up key or, if omitted, coverage vs en.js; build returns the npm/gulp command for a goal — it does not run it. checks only for mode=grep (default all); show_missing only for i18n coverage (ignored when key is set); goal only for mode=build; target is required for mode=plugin (folder or JS path); missing plugin → error listing folders.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
keyNoFor mode=i18n: specific translation key. Omit for coverage report.
goalNoFor mode=build: which command to hint (does not execute). Default build.
modeYesplugin=convention score; grep=snapshot quality scans (not a shell); i18n=keys/coverage; build=command hint (does not run npm/gulp).
checksNoFor mode=grep: which checks. Defaults to all.
targetNoRequired for mode=plugin: plugin folder name or repo-relative JS path. Missing plugin → error listing folders.
show_missingNoFor mode=i18n coverage: include missing/extra key lists. Default true.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
markdownYesHuman-readable markdown report. Always present, including empty-result cases. Does not write files.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv1.7.0
    • changedInput schema / properties / goal / description
      Previous value: -"For mode=build: which command to hint. Default build."New value: +"For mode=build: which command to hint (does not execute). Default build."
    • changedInput schema / properties / mode / description
      Previous value: -"plugin=convention score; grep=quality scans; i18n=keys/coverage; build=command hint."New value: +"plugin=convention score; grep=snapshot quality scans (not a shell); i18n=keys/coverage; build=command hint (does not run npm/gulp)."
    • changedInput schema / properties / target / description
      Previous value: -"For mode=plugin: plugin folder or repo-relative JS path."New value: +"Required for mode=plugin: plugin folder name or repo-relative JS path. Missing plugin → error listing folders."
  2. Addedv1.6.0

TDQS

A5/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, and the description adds important behavioral details beyond those: build does not execute, grep is not a shell, missing plugin errors list folders, and show_missing is ignored when key is set. These disclosures fully inform the agent of side effects and failure modes.

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?

The description is dense but every sentence adds value, with exclusions front-loaded and mode details organized by mode. There is no filler or repetition of schema content; the structure efficiently communicates complex conditional behavior.

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

Completeness5/5

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

For a multi-mode tool with six parameters, the description covers every mode, every parameter's applicability, error behavior, and exclusions. The presence of an output schema means return-value details need not be explained, so nothing essential is missing for correct invocation.

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

Parameters5/5

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

Schema coverage is 100%, but the description still adds crucial mode-to-parameter mappings: checks only for grep, show_missing only for i18n coverage, goal only for build, and target required for plugin. It also explains conditional behaviors like default checks and ignored show_missing, which go beyond the raw schema descriptions.

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?

The description opens with a specific verb ('Run checks and hints') and defines four concrete modes with distinct outcomes: plugin scoring, grep snapshot scans, i18n key/coverage lookup, and build command hints. It explicitly excludes sibling tools like list_catalog and plan_change, making the tool's scope unmistakable.

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

Usage Guidelines5/5

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

The description provides explicit when-to-use guidance per mode, including exclusions ('not a shell', 'does not run it') and alternative tools it is not. Mode-specific parameter constraints further clarify which arguments apply in each scenario, so an agent can choose correctly without guessing.

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

Deploy Server

Other Tools