Skip to main content
Glama
reeinharddd

snapmcp

by reeinharddd
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

capture_browser

Capture page screenshots from a URL using headless Chromium, with full-page or viewport options and Chrome profile for authenticated sessions. SSRF protection blocks private IPs and localhost.

Instructions

Take a screenshot of a URL using headless Chromium. Uses system Chrome profile when available (set SNAPMCP_CHROME_PROFILE) for authenticated sessions, cookies, and extensions. SSRF protection is enabled by default (SNAPMCP_SSRF_PROTECTION=true) - blocks private IPs, localhost, and DNS-rebounding attacks. Supports full-page or viewport captures.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesURL to capture (http/https). Must pass SSRF validation: no private IPs (10/8, 172.16/12, 192.168/16, fc00::/7), no localhost variants, no DNS-rebinding. Redirects are also validated.
widthNoViewport width in pixels (320-3840). Ignored if fullPage=true.
heightNoViewport height in pixels (240-4096). Ignored if fullPage=true.
outputNoOutput filename (default: auto-generated as 'browser-<timestamp>.png' or '.jpeg' based on SNAPMCP_FORMAT). Include extension to override format.
fullPageNoCapture full scrollable page (true) or just the viewport (false). Full page may take longer and use more memory.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv2.3.4
    • changedInput schema / properties / fullPage / description
      Previous value: -"Capture full scrollable page"New value: +"Capture full scrollable page (true) or just the viewport (false). Full page may take longer and use more memory."
    • changedInput schema / properties / height / description
      Previous value: -"Viewport height (px)"New value: +"Viewport height in pixels (240-4096). Ignored if fullPage=true."
    • changedInput schema / properties / output / description
      Previous value: -"Output filename (default: auto-generated)"New value: +"Output filename (default: auto-generated as 'browser-<timestamp>.png' or '.jpeg' based on SNAPMCP_FORMAT). Include extension to override format."
    • changedInput schema / properties / url / description
      Previous value: -"URL to capture"New value: +"URL to capture (http/https). Must pass SSRF validation: no private IPs (10/8, 172.16/12, 192.168/16, fc00::/7), no localhost variants, no DNS-rebinding. Redirects are also validated."
    • changedInput schema / properties / width / description
      Previous value: -"Viewport width (px)"New value: +"Viewport width in pixels (320-3840). Ignored if fullPage=true."
  2. First observedv2.3.2

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses headless Chromium, optional Chrome-profile use, and SSRF protections including blocked IP ranges and DNS-rebinding defense. It does not fully describe the return value or post-capture behavior, such as whether a file path is returned, so a 5 is not justified.

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?

Four short sentences, each carrying distinct information: core action, authentication/profile behavior, SSRF safeguards, and capture modes. The most important facts are front-loaded 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 5-parameter tool with no annotations and no output schema, the description plus schema is nearly sufficient: it covers purpose, security behavior, profile behavior, and all parameters. The main gap is that the result format is not described, and there is no explicit guidance distinguishing this tool from its many capture_* siblings.

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 thoroughly documents url, width, height, output, and fullPage. The description adds useful environment-variable context (SNAPMCP_CHROME_PROFILE, SNAPMCP_SSRF_PROTECTION) but no additional parameter-level meaning, matching the high-coverage baseline of 3.

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: 'Take a screenshot of a URL using headless Chromium.' This immediately distinguishes capture_browser from siblings like capture_pdf or capture_html by anchoring on URL and screenshot behavior. The full-page/viewport detail further clarifies scope.

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 usage context: it is for URL screenshots and explicitly mentions when the Chrome profile is relevant for authenticated sessions, cookies, and extensions. It does not explicitly name alternative tools or state when not to use this tool, so it falls short of a 5.

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