webcap MCP

A remote MCP server that turns any URL into a screenshot (PNG/JPEG/PDF) or structured text/JSON. It supports paid per-call web capture via USDC over x402 micropayments, offering features like visual analysis, SEO auditing, and site mapping with no API keys required for basic usage.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Community listingStreamable HTTPNo sign-inEndpoint checked 2026-11-07Published by shoutsid-lab

MCP endpoint (Streamable HTTP)

https://webcap.shoutsid.fyi/mcp

Vendor documentation

What its tools do

8 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Not annotated (8)

webcap_service_catalog
webcap_preview
webcap_og
webcap_capture
webcap_extract
webcap_audit
webcap_map_lite
webcap_analyze

8 of 8 have a description · 0 of 8 declare behavior hints · 7 of 7 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

Passed Endpoint answered the live check · Nov 7, 2026, 3:32 AM UTC
Availability 1 of 1 checks passed in 30 days

What you can do with it

Capture screenshots of any URL as PNG, JPEG, or PDF
Extract structured content like headings and links from web pages
Perform SEO audits and Open Graph metadata checks
Analyze page visuals for accessibility and layout issues

Source and maintenance

Community listingRegistry 0.1.0

mcp-registry: io.github.shoutsid-lab/webcap@0.1.0 Source repository Project website

Maintenance checked: Nov 7, 2026, 12:20 AM UTC

Protocol and capabilities

Server: webcap 0.1.0
MCP protocol negotiated in check: 2025-11-25
Tools: 8 advertised
Resources: Not advertised
Resource templates: Not advertised
Prompts: Not advertised

Server-advertised capabilities

{
  "tools": {}
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

webcap turns a URL into a screenshot, structured JSON, or a page audit, paid per call in USDC over x402. Free tools need nothing; paid tools return a 402 challenge (price, network, payTo) when no wallet is wired. Call webcap_service_catalog to see every endpoint and price.

Tools

8 advertised

webcap_service_catalog

Advertised by the server during the last successful anonymous check.

Free service catalog (no payment): every paid endpoint with its exact price in USDC, the settlement network, USDC asset, payTo address, facilitator and the step-by-step x402 how-to-pay flow, plus the free allowance this caller has left. Call this first to learn what webcap sells and what it costs.

webcap_service_catalog input schema

{
  "type": "object",
  "properties": {}
}

webcap_preview

Advertised by the server during the last successful anonymous check.

Free bounded preview of a page: title, description, headings, links, word count and a truncated markdown slice. Use it to peek before the full extract. Rate-limited per IP. This is a teaser, not the product: the real products are free too inside the rolling per-IP allowance.

webcap_preview input schema

{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "format": "uri",
      "description": "Absolute http(s) URL of the page to process, e.g. https://example.com/"
    }
  }
}

webcap_og

Advertised by the server during the last successful anonymous check.

Free Open Graph metadata for a URL: title, description, image, icon. No payment.

webcap_og input schema

{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "format": "uri",
      "description": "Absolute http(s) URL of the page to process, e.g. https://example.com/"
    }
  }
}

webcap_capture

Advertised by the server during the last successful anonymous check.

PAID ($0.001 image/PDF, $0.005 video): turn a URL into a persistent public artifact. png/jpeg/pdf are a screenshot or PDF and include free OG metadata; mp4/webm scroll-record the page as WebM/VP8 (mp4 is a legacy alias). Settles gasless USDC over x402 — but an unpaid call runs free while the rolling per-IP allowance lasts, so just call it.

webcap_capture input schema

{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "format": "uri",
      "description": "Absolute http(s) URL of the page to process, e.g. https://example.com/"
    },
    "format": {
      "enum": [
        "png",
        "jpeg",
        "pdf",
        "mp4",
        "webm"
      ],
      "type": "string",
      "default": "png",
      "description": "Artifact format, default png. png/jpeg/pdf = screenshot/PDF at $0.001 (POST /v1/x402/capture); mp4/webm = scroll video at $0.005 (POST /v1/x402/video), always recorded as WebM/VP8. The 402 challenge states the exact price for the format you chose."
    },
    "fullPage": {
      "type": "boolean",
      "default": false,
      "description": "Image/PDF only. true captures the whole scrollable page (default false: viewport only)."
    },
    "durationMs": {
      "type": "integer",
      "default": 5000,
      "maximum": 30000,
      "minimum": 1,
      "description": "Video formats only. Scroll duration in milliseconds, 1-30000; default 5000."
    }
  }
}

webcap_extract

Advertised by the server during the last successful anonymous check.

PAID ($0.01, one payment covers a batch of up to 50 URLs): structured content as JSON — title, headings, paragraphs, links, images, document-order markdown. Provide exactly one of "url" (a single page) or "urls" (a batch); "url" is shorthand for a one-item "urls".

webcap_extract input schema

{
  "type": "object",
  "oneOf": [
    {
      "required": [
        "url"
      ]
    },
    {
      "required": [
        "urls"
      ]
    }
  ],
  "properties": {
    "url": {
      "type": "string",
      "format": "uri",
      "description": "A single page to extract, e.g. https://example.com/. Shorthand for \"urls\": [\"<url>\"]. Mutually exclusive with \"urls\" — sending both is an error."
    },
    "urls": {
      "type": "array",
      "items": {
        "type": "string",
        "format": "uri"
      },
      "maxItems": 50,
      "description": "Batch of pages for one payment, at most 50 items; a batch of one is allowed. Mutually exclusive with \"url\" — sending both is an error."
    },
    "schema": {
      "type": "string",
      "description": "Optional natural-language description of the JSON to extract. Omit it to get the default page structure."
    }
  }
}

webcap_audit

Advertised by the server during the last successful anonymous check.

PAID ($0.002): SEO basics plus link and Open Graph health for one URL in a single call. Returns issues with severity, not just raw tags.

webcap_audit input schema

{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "format": "uri",
      "description": "Absolute http(s) URL of the page to process, e.g. https://example.com/"
    }
  }
}

webcap_map_lite

Advertised by the server during the last successful anonymous check.

PAID ($0.002): discover a site's URLs from its sitemap and robots.txt plus a 1-hop same-host crawl, and return them as a JSON list. Cheaper than crawling each page with webcap_extract.

webcap_map_lite input schema

{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "format": "uri",
      "description": "Absolute http(s) URL of the page to process, e.g. https://example.com/"
    },
    "maxUrls": {
      "type": "integer",
      "default": 20,
      "maximum": 50,
      "minimum": 1,
      "description": "Maximum number of URLs to return. Integer 1-50; default 20 when omitted."
    }
  }
}

webcap_analyze

Advertised by the server during the last successful anonymous check.

PAID ($0.01): AI analysis of one URL. Pick the task that matches the question you are answering.

webcap_analyze input schema

{
  "type": "object",
  "required": [
    "url",
    "task"
  ],
  "properties": {
    "url": {
      "type": "string",
      "format": "uri",
      "description": "Absolute http(s) URL of the page to process, e.g. https://example.com/"
    },
    "task": {
      "enum": [
        "classification",
        "accessibility",
        "layout",
        "entities",
        "sentiment"
      ],
      "type": "string",
      "description": "What to analyze (required, no default): classification = page type, accessibility = a11y issues, layout = structure and regions, entities = named entities and facts, sentiment = tone."
    }
  }
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks: 1 of 1 (100%)
Average latency: 1167 ms
95th percentile latency: 1167 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

Nov 7, 2026, 3:32 AM UTC · probe · passed · 1167 ms · metadata changed · 8 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

claude mcp add --transport http webcap-mcp https://webcap.shoutsid.fyi/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add webcap-mcp --url https://webcap.shoutsid.fyi/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable webcap-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "webcap-mcp": {
      "url": "https://webcap.shoutsid.fyi/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).

Cline configuration

{
  "mcpServers": {
    "webcap-mcp": {
      "type": "streamableHttp",
      "url": "https://webcap.shoutsid.fyi/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start webcap-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "webcap-mcp": {
      "type": "http",
      "url": "https://webcap.shoutsid.fyi/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

gemini mcp add --transport http webcap-mcp https://webcap.shoutsid.fyi/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.

Claude Desktop configuration

https://webcap.shoutsid.fyi/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "webcap-mcp": {
      "serverUrl": "https://webcap.shoutsid.fyi/mcp"
    }
  }
}

Let your agent find its tools

Find servers like webcap MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows