Skip to main content
Glama
andresolbach

nodriver-mcp-server

by andresolbach
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Take screenshot

take_screenshot
Read-only

Capture the page, viewport, or a specific element as an image for layout and styling checks, visual regression, or extracting text embedded in images.

Instructions

Capture the page, the viewport or a single element as an image.

Do NOT use this to read a page. take_snapshot gives you the same content as searchable text, is dramatically smaller, and yields the uids every interaction tool needs. Use a screenshot only when you genuinely need pixels: layout and styling checks, visual regression, or text that exists only inside an image.

Element capture needs a uid from the current snapshot. Without file_path the image is returned inline as a base64 data URL.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
uidNoCapture just this element, using a uid from the most recent take_snapshot. Cannot be combined with full_page. Empty string captures the page.
formatNoImage format. "png" is lossless and the default; "jpeg" or "webp" with a quality setting are far smaller, which matters for full-page captures.png
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
qualityNoCompression quality from 1 to 100, for jpeg and webp only. Ignored for png. 0 leaves Chrome's default.
file_pathNoWrite the image to this local path. Omit to get a base64 data URL inline in the response — that is expensive, so prefer a file for full-page or high-DPR captures.
full_pageNoCapture the whole scrollable page rather than just the visible viewport. Cannot be combined with `uid`.

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

A4.3/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description does not contradict them. It adds some context by noting the inline base64 data URL behavior when file_path is omitted and the uid requirement for element capture, but these points are also present in the schema and there is no deeper behavioral disclosure such as side effects, permissions, or performance limits.

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 compact and well-structured: the core capability comes first, followed by an explicit anti-pattern with alternative, and a final caveat about element capture and output format. Every sentence earns its place, with no wasted words.

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 all six parameters documented in the schema and an output schema provided, the description covers the remaining cross-cutting concerns: what screenshots are for versus text snapshots, the uid prerequisite, and the inline-vs-file output mode. Nothing an agent needs to invoke this tool correctly is missing.

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 baseline is 3. The description restates the uid-from-current-snapshot requirement and the inline-vs-file_path behavior, both already documented in the parameter descriptions, without adding new parameter-specific meaning.

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 precise verb-plus-resource statement: 'Capture the page, the viewport or a single element as an image.' It then explicitly contrasts itself with take_snapshot, so an agent can immediately distinguish pixel capture from text extraction.

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?

It says when not to use the tool ('Do NOT use this to read a page'), names the alternative (take_snapshot), and gives the exact condition for using screenshots ('only when you genuinely need pixels: layout and styling checks, visual regression, or text that exists only inside an image'). It also states the prerequisite for element capture (a uid from the current snapshot).

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