Skip to main content
Glama
andresolbach

nodriver-mcp-server

by andresolbach
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Set browser launch flags

set_browser_flags
Destructive

Change Chrome's launch flags at runtime and view current ones. Apply immediately by restarting Chrome or defer to next start.

Instructions

Change Chrome's launch flags at runtime, and show the current ones.

Call with no arguments at all to just read the effective configuration — that form changes nothing.

These are launch-time flags, so applying them restarts Chrome and closes every open page; on an ephemeral profile that also drops its cookies. Values set here override the NODRIVER_ENABLE_* environment variables.

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
restartNoRestart Chrome now so the flags take effect, closing all open pages. Default true; false defers them to the next browser start.
translateNoTrue allows Chrome's Google Translate popup, false suppresses it. Omit to leave unchanged. Suppressed by default, because the popup covers page content and swallows clicks.
extensionsNoTrue allows externally-installed Chrome extensions, false blocks them. Omit to leave unchanged. Blocked by default, so no "an extension requires your attention" prompt appears. manage_extensions offers the same switch plus listing and loading.
extra_argsNoReplace the set of extra Chrome launch flags with this list, e.g. ["--lang=de-DE", "--window-size=1280,800"]. A leading "--" is added if missing. Pass [] to clear them, omit to leave unchanged. This replaces the list rather than appending to it.

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

A4.7/5.0
Behavior5/5

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

Despite annotations already marking destructiveHint=true, the description adds valuable specifics: applying flags restarts Chrome, closes every open page, and drops cookies on ephemeral profiles. It also clearly states that the no-argument form changes nothing, which is important behavioral nuance beyond the 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 short paragraphs each carry essential information: the tool's dual purpose, the safe read-only call form, and the destructive side effects plus env-var precedence. No filler or redundant restatement of the schema.

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?

The description covers the read path, the destructive restart path, cookie loss, and environment variable override. The input schema documents all parameters in depth, an output schema exists, and annotations cover the danger profile, 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.

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3. The description adds meaningful global semantics beyond the schema: no arguments means read-only, and values set here override environment variables. These details help agents reason about the effective configuration without duplicating per-parameter docs.

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 and resource: 'Change Chrome's launch flags at runtime, and show the current ones.' This states both the mutation and read modes, making the tool's purpose unmistakable and distinguishing it from sibling tools like manage_extensions.

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 clear context for when to call with no arguments to read vs. with arguments to change flags, and explains precedence over NODRIVER_ENABLE_* environment variables. It does not explicitly name alternative tools or state when not to use this tool, but the guidance is sufficient for most calls.

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