Skip to main content
Glama
Rendershot

@rendershot/mcp-server

Official
by Rendershot

take_screenshot

Capture screenshots of web pages or HTML content, returning base64-encoded PNG or JPEG images. Supports custom viewport size, full page capture, and cookie injection.

Instructions

Capture a screenshot of a web page or HTML content. Returns a base64-encoded PNG or JPEG image.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlNoURL of the page to screenshot. Exactly one of url or html is required.
htmlNoRaw HTML to render. Exactly one of url or html is required.
formatNoImage format.png
qualityNoJPEG quality (1–100). Ignored for PNG.
viewport_widthNoViewport width in pixels.
viewport_heightNoViewport height in pixels.
full_pageNoCapture the full scrollable page.
wait_forNoWhen to consider the page loaded: load | dom_content_loaded | network_idle | commit | CSS selector.dom_content_loaded
delay_msNoExtra delay in milliseconds after page load before capturing.
ai_cleanupNoRemove cookie banners/popups before capture. 'fast' uses JS heuristics (1 credit). 'thorough' adds an LLM pass (3 credits; requires Anthropic key on the server).
headersNoCustom HTTP headers to send with the render request. Use for Bearer tokens, X-Tenant-Id, etc. Host / Cookie / Content-Length / Sec-* / Connection are rejected server-side. Max 30 headers, values ≤ 2 KB.
cookiesNoSession cookies to inject before page navigation. Each cookie needs either 'domain' or 'url'. Max 50 per request.
basic_authNoHTTP Basic auth credentials. Forwarded to the headless browser on a 401 challenge.
output_pathNoAbsolute or relative path to save the image file (e.g. /tmp/shot.png). If omitted, the image is returned as base64 in the response.
Behavior2/5

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

No annotations provided, so description must disclose behavioral traits. It doesn't mention non-destructiveness, credit consumption, or failure modes. Only states basic function.

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?

Two sentences with key information front-loaded. No fluff, but could be slightly more structured.

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

Completeness2/5

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

Description omits crucial context like requirement for exactly one of url or html, optional save to file, and cookie handling. Given 14 parameters and no output schema, more context is needed.

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 coverage is 100% with detailed descriptions; description adds nothing beyond stating the return format. 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?

Description clearly states verb 'capture' and resource 'screenshot of a web page or HTML content', and mentions return format. Distinguishes from siblings by specifying both URL and HTML content options.

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?

No explicit guidance on when to use this tool vs alternatives like bulk_render or generate_pdf. The description does not compare or contrast with siblings.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Rendershot/rendershot-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server