BrowserSolver MCP Server

Official

by browsersolver

Overview Schema Source Related Servers Discussions Admin

TypeScript

Hybrid

Website Screenshot

website_screenshot

Read-only

Capture any public URL as a PNG, JPEG, WebP, or PDF via BrowserSolver, avoiding local Chromium management.

Instructions

Website Screenshot. Turn any public URL into a PNG, JPEG, WebP, or PDF asset rendered by BrowserSolver. No local Chromium fleet to operate. Credit cost: 2 credits per call.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "<url>"
    },
    "name": "website_screenshot"
  }
}

Input Schema

Name	Required	Description
`url`	Yes	Page address to render into an image or PDF. Must include a protocol.
`cache`	No	Serve a stored capture on repeat requests when caching is enabled. Default: false.
`delay`	No	Additional settle time in seconds after the readiness event. Default: 0.
`proxy`	No	Route the browser through an intermediate proxy.
`device`	No	Swap the desktop viewport for a preset handset or tablet fingerprint. Allowed values: galaxy_fold4, galaxy_s23, galaxy_s23_ultra, galaxy_s8, huawei_mate_50_pro, huawei_p60_pro, ipad, iphone_12, iphone_13_mini, iphone_13_pro_max, iphone_14_pro, iphone_14_pro_max, iphone_x, pixel_5, pixel_6a, pixel_7_pro, redmi_note_11, redmi_note_12_pro.
`fields`	No	Comma-separated list of fields to keep in the response, with dot notation for nested fields (e.g. name,location.city). Does not change the credit cost.
`format`	No	File type returned in the response body. Allowed values: jpeg, jpg, pdf, png, webp. Default: "png".
`s3_url`	No	Upload the binary and include the public object URL in the API response. Default: false.
`selector`	No	Limit the shot to one DOM node matched by this CSS selector.
`cache_ttl`	No	Lifetime of cached captures in seconds. Default: 2592000.
`full_page`	No	Extend the capture beyond the viewport so the entire scrollable document is included. Default: false.
`s3_bucket`	No	Destination bucket for the binary asset.
`s3_region`	No	Cloud region of the bucket.
`block_urls`	No	Substring patterns that should never be fetched (example: analytics,tracking,advertisement). Hosts, paths, or fragments such as .example.com/ work.
`remove_ads`	No	Best-effort stripping of ad slots before capture. Default: false.
`wait_until`	No	Which browser lifecycle event marks the page ready. Allowed values: domcontentloaded, load, networkidle0, networkidle2.
`scale_factor`	No	Pixel density multiplier. Raise it for retina-quality output; files grow accordingly. Default: 1.
`image_quality`	No	Lossy compression level for soft formats. Default: "80".
`s3_object_key`	No	Key under which the object is stored (generated automatically if blank).
`s3_secret_key`	No	Secret key used to authenticate uploads.
`viewport_width`	No	Width of the synthetic desktop window, in pixels. Default: 1280.
`block_resources`	No	Resource kinds to discard during load, as a comma list (example: image,stylesheet,font). Allowed values: document, eventsource, fetch, font, image, manifest, media, other, script, stylesheet, texttrack, websocket, xhr.
`viewport_height`	No	Height of the synthetic desktop window, in pixels. Default: 1024.
`full_page_scroll`	No	Drive a scroll pass first so deferred content mounts before a tall capture. Default: false.
`remove_selectors`	No	Hide matching CSS selectors (modals, promo bars, etc.) before shooting.
`s3_access_key_id`	No	Access key used to authenticate uploads.
`storage_endpoint`	No	Override the default AWS endpoint for S3-compatible backends. Leave blank for AWS. R2 example: https://<accountId>.r2.cloudflarestorage.com.
`wait_for_selector`	No	Hold capture until this CSS node is present.
`remove_cookie_banners`	No	Best-effort removal of cookie consent layers before capture. Default: false.
`full_page_scroll_duration`	No	Milliseconds spent scrolling prior to a full-height capture. Default: 400.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 7, 2026

TDQS

B3.2/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true, openWorldHint=true, and destructiveHint=false, so the safety profile is covered. The description adds useful context by stating the external rendering service and the credit cost of 2 credits per call, but it leaves out return format details and any rate-limit or timeout behavior.

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?

The description is front-loaded and brief, with three short sentences. 'Website Screenshot.' is redundant with the tool name and title, and 'No local Chromium fleet to operate' is slightly promotional, but the core message remains efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 30-parameter tool with no output schema, the description is quite thin. It explains the rendering source and credit cost but does not clarify whether the response is a binary image, a JSON envelope, or a URL, which matters for invoking the tool correctly.

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 every parameter is already documented in the input schema. The description only restates the supported output formats and does not add syntax or behavioral meaning beyond what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific transformation: 'Turn any public URL into a PNG, JPEG, WebP, or PDF asset rendered by BrowserSolver.' That makes the verb and resource clear and distinguishes it from siblings like website_crawler and website_rendering, though it does not explicitly name those alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no explicit guidance on when to use this tool versus sibling tools such as website_rendering or website_crawler. It also does not mention prerequisites, rate limits, or conditions where a screenshot might fail.

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

Deploy Server