Skip to main content
Glama
andresolbach

nodriver-mcp-server

by andresolbach
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Take heap snapshot

take_memory_snapshot

Capture a V8 heap snapshot to a file for memory-leak debugging. Take snapshots before and after a suspect interaction, then compare retained objects in Chrome DevTools.

Instructions

Capture a V8 heap snapshot of the page, for memory-leak debugging.

Writes the raw .heapsnapshot file for Chrome DevTools -> Memory -> Load. The usual workflow is two snapshots taken around a suspect interaction, then comparing retained objects between them.

On a heavy page a snapshot can be hundreds of megabytes and take several seconds; the response reports the resulting file size.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
browserNoWhich browser to act on. Each name is an independent Chrome, created on first use. Omit for the shared default; parallel agents each need their own name.default
file_pathYesLocal path to write the .heapsnapshot file to. Open it in DevTools -> Memory -> Load profile.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.5.0
    • addedInput schema / properties / browser
      Added value: +{
+  "default": "default",
+  "description": "Which browser to act on. Each name is an independent Chrome, created on first use. Omit for the shared default; parallel agents each need their own name.",
+  "type": "string"
+}
  2. First observedv1.7.2

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only indicate non-read-only and non-idempotent; the description adds that it writes a raw .heapsnapshot file, can be hundreds of MB, take several seconds, and reports file size. This meaningfully informs an agent of side effects and cost beyond structured annotations.

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 paragraphs each add distinct value: purpose, workflow/format, and cost/response. All sentences are informative and front-loaded, with no filler.

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?

With an output schema present, the description needn't define return values. It explains purpose, workflow, file output, scale, and latency—everything an agent needs to invoke and interpret the tool correctly is present.

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?

Input schema covers both parameters with detailed descriptions, including the browser naming semantics. The description doesn't add parameter-specific detail, but the high schema coverage makes that acceptable; baseline 3 is appropriate.

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 ('Capture'), resource ('V8 heap snapshot of the page'), and use case ('memory-leak debugging'). The .heapsnapshot format and DevTools destination distinguish it clearly from sibling snapshot/navigation/perf tools.

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 description gives a concrete workflow: take two snapshots around a suspect interaction and compare retained objects. This implies when to use it (memory-leak debugging) and frames it as a comparative diagnostic operation, though it doesn't explicitly name alternatives or exclusions.

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