Skip to main content
Glama
CrossPad

crosspad-mcp-server

by CrossPad

crosspad_log

Read-only

Capture consolidated logs from either a built PC simulator binary or a connected ESP32-S3 device over serial, filtering lines and controlling capture duration and line limits with a single tool.

Instructions

[PC | ESP HW] Capture logs (consolidated; replaces crosspad_log_pc and crosspad_log_idf in v6). • target='pc' → spawn the built sim binary, capture stdout/stderr, then kill it. Fields used: timeout_seconds (default 5), max_lines (default 200). port and filter MUST be omitted. • target='idf' → read serial from a connected ESP32-S3 via pyserial (no TTY needed). Fields used: port (auto-detected if omitted), timeout_seconds (default 10), max_lines (default 500), filter (substring, case-insensitive).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
portNoidf only. Serial port path. Auto-detected if omitted; required when multiple devices connected. MUST be omitted for target=pc.
filterNoidf only. Case-insensitive substring filter — only matching lines returned. MUST be omitted for target=pc.
targetYes'pc' = run+capture sim binary (uses timeout_seconds?,max_lines? — port/filter MUST be omitted); 'idf' = read serial from connected ESP device (uses port?,timeout_seconds?,max_lines?,filter?,reset_to_boot?).
max_linesNoMax output lines. Defaults: 200 (pc), 500 (idf).
reset_to_bootNoidf only. Pulse the device reset (esptool DTR/RTS sequence, works through the STM bridge) before capturing, so the log starts at boot t=0. Use for boot-time profiling. Default false (passive read of the running device).
timeout_secondsNoCapture duration in seconds. Defaults: 5 (pc), 10 (idf).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
portNo
errorNo
linesNo
stderrNo
stdoutNo
successYes
exe_pathNo
exit_codeNo
truncatedNo
line_countNo
duration_secondsNo
Behavior3/5

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

Annotations provide readOnlyHint=true, so the safety profile is already covered. The description adds useful behavioral detail (spawn+kill sim binary, pyserial read without TTY, reset_to_boot DTR/RTS pulse sequence through STM bridge). However, it doesn't disclose return format or pagination/truncation behavior beyond max_lines.

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?

Reasonably compact with clear bullet-style per-mode breakdown that front-loads the main purpose. Slightly dense, but each sentence carries content about mode-specific behavior, defaults, and constraints with no 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?

For a dual-mode tool with 6 params, the description does substantial work: names both target modes, enumerates which fields apply to each, gives defaults, and explains the reset_to_boot behavior thoroughly. An output schema exists, so return format explanation isn't required. Minor gap: no explicit naming of sibling alternatives beyond the consolidation note.

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 description coverage is 100%, so the schema already documents all 6 parameters well. The description adds value by specifying mode-specific defaults and the MUST-omit constraints for pc mode, but this mostly reinforces what the schema already conveys.

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 clearly states it captures logs with a specific verb+resource ('Capture logs'). It distinguishes between two modes (pc sim binary and idf serial) and explicitly notes it consolidates/replaces crosspad_log_pc and crosspad_log_idf, differentiating it from siblings like crosspad_trace.

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?

Explicitly describes when to use each target mode, which fields are used in each mode, and which fields MUST be omitted for target='pc'. Provides defaults (timeout_seconds, max_lines) and explains auto-detection for port. The [PC | ESP HW] prefix frames hardware context.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/CrossPad/crosspad-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server