qa-mcp-server

Overview Schema Source Related Servers Discussions Admin

logcat

Read-only

Dump Android device logs non-blocking with size limits, filtered by app package, tag, minimum level, or timestamp to inspect app behavior during QA.

Instructions

Read the logcat buffer (non-blocking dump), size-capped.

    Filters: package (running process), tag, minimum level and since.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "logcat"
  }
}

Input Schema

Name	Required	Description	Default
`tag`	No
`level`	No	Minimum priority: V < D < I < W < E < F.	V
`since`	No	Only lines at or after '[YYYY-]MM-DD HH:MM:SS[.mmm]' (device time).
`serial`	No
`package`	No	Only lines from this app's running process.
`max_lines`	No

Output Schema

Name	Required	Description	Default
`note`	No
`serial`	Yes
`entries`	Yes
`scanned`	Yes
`returned`	Yes
`truncated`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 13, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Annotations already declare readOnly/non-destructive/openWorld=false, so the description's added value is exactly what it delivers: 'non-blocking' (won't hang the session waiting for new log lines) and 'size-capped' (output is truncated). Those are operational traits the annotations do not express.

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?

One sentence for the operation plus a one-line filter summary; front-loaded, no redundancy, and the non-blocking/size-cap caveats appear before the filter list where they matter most.

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 an output schema present and safety annotations supplied, the description covers the core semantics; remaining gaps are the undocumented serial and max_lines parameters and default buffer scope. Acceptable for a 6-parameter all-optional read tool but not exhaustive.

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

Parameters4/5

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

Schema coverage is only 50% (tag and max_lines carry no schema description), yet the description enumerates the meaningful filters and clarifies that package scopes to the app's running process and level sets a minimum priority. It leaves serial and max_lines unmentioned, so it does not fully compensate for the coverage gap.

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?

Names a specific verb and resource ('Read the logcat buffer') and immediately qualifies the mode ('non-blocking dump'), which cleanly separates it from UI-inspection siblings like dump_ui and screenshot. An agent knows exactly what this returns without opening the schema.

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

Usage Guidelines3/5

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

The filter list ('package (running process), tag, minimum level and since') implies when the tool is the right choice for log inspection, but there is no explicit when-to-use or when-not guidance and no reference to alternatives for overlapping needs. Usage is inferable rather than stated.

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

Deploy Server