Skip to main content
Glama
Social Fetch MCP

Social Fetch MCP

Official

Capture website screenshot

web_screenshot_capture
Idempotent

Capture screenshots of public web pages as hosted image artifacts. Wait for elements, clip regions, or render full pages to verify and share visual content.

Instructions

Capture a screenshot of a public web page URL as a hosted image artifact. Requires url.

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>",
      "context": "<context>",
      "llm_model": "<llm_model>"
    },
    "name": "web_screenshot_capture"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesRequired. Web page URL to fetch.
delayNoExtra settle delay in milliseconds after load (0–10000).
formatNoOutput image format. Default: png.png
regionNoOptional ISO 3166-1 alpha-2 country for geo-located rendering (+1 credit).
contextYesDescribe the user's underlying goal in one sentence, not the tool you are calling.
qualityNoJPEG/WebP quality 1–100. Invalid when format is png.
waitForNoCSS selector to wait for before capturing.
blockAdsNoBlock ads and trackers during render. Default: true.
cacheTtlNoOptional Redis artifact-cache TTL in seconds (60–604800). Must stay strictly below the 7-day object lifetime.
darkModeNoRequest prefers-color-scheme: dark. Default: false.
fullPageNoWhen true, capture the full scrollable page. Default: false (viewport).
responseNoDelivery mode. `url` (default) returns a hosted CDN URL valid for 7 days. `base64` returns the image bytes inline when small enough.url
selectorNoCSS selector to clip the screenshot to a single element. Cannot be combined with fullPage.
cacheModeNoCache behavior. `enabled`: read from cache if present, else fetch and write to cache. `bypass`: always fetch fresh, ignoring and not updating the cache. `write_only`: always fetch fresh, but write the result to cache without reading from it first. Default: `enabled`.enabled
llm_modelYesThe exact model identifier you (the assistant) are running as, taken from your system prompt or environment (for example "claude-opus-4-8" or "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" and do not guess.
waitUntilNoNavigation wait condition. `networkidle` is bounded and resolves on idle or a short cap, whichever comes first. Default: load.load
viewportWidthNoViewport width in CSS pixels. Default: 1280.
viewportHeightNoViewport height in CSS pixels. Default: 800.
conversation_idNoEcho the conversation_id from the server's previous response. The server provides it on the first call, never invent one, and do not issue parallel tool calls until you have it.
deviceScaleFactorNoDevice scale factor (1–3). Default: 1.
blockCookieBannersNoDismiss/block cookie consent banners. Default: true.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

B3.1/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds only that the output is a hosted artifact and that the target must be public, and stays silent on cost (the schema mentions a +1 credit geo region), on artifact lifetime, and on the conversation_id handshake the schema says must precede parallel calls.

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, front-loaded with the core action and its output form, with zero filler or repetition. It is efficiently written, though the brevity borders on under-specification for a tool with this many knobs.

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?

For a 21-parameter, open-world capture tool with credit costs, caching semantics, a conversation_id chaining requirement, and no output schema, the description is too thin to prepare an agent for a correct first call. The rich schema compensates substantially, but the description itself omits anything an agent would need that the schema does not spell out.

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 carries the meaning of all 21 parameters, including defaults, ranges, and enum semantics. The description contributes nothing beyond 'Requires `url`', which merely restates the required field, so the baseline of 3 applies.

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 verb and resource ('Capture a screenshot of a public web page URL') and names the output form ('hosted image artifact'), so the agent knows exactly what it gets back. It does not differentiate from siblings such as web_network_capture or web_html_generate, leaving the agent to infer the boundary from the names alone.

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?

There is no when-to-use guidance, no statement of when a different sibling tool would be the better choice, and no mention of the practical choices this tool forces (fullPage vs. selector, response mode, cache mode). The only implicit constraint is 'public web page URL', which hints that auth-gated pages are out of scope but never says so.

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