webEmbedding is an MCP server published by io.github.jongko54, hosted at webembedding-jongkos-mcp.vercel.app. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 6 tools, including detect_runtime_capabilities, inspect_url, discover_embed_candidates, classify_clone_mode, generate_embed_snippet.
Clone any web page from a URL into a verified offline HTML copy, embed, or rebuild.
93 connections through 5 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
Report hosted Apps SDK readiness, read-only runtime capabilities, unsupported capture behavior, and the local stdio command.
No parameters.
{
"name": "detect_runtime_capabilities",
"title": "Detect Hosted Runtime Capabilities",
"description": "Report hosted Apps SDK readiness, read-only runtime capabilities, unsupported capture behavior, and the local stdio command.",
"inputSchema": {
"type": "object",
"properties": {}
},
"outputSchema": {
"type": "object",
"additionalProperties": true
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Fetch a public or user-authorized URL and inspect title, metadata, frame policy, and likely source/embed candidates. Does not capture screenshots or persist artifacts.
| Parameter | Type | Description |
|---|---|---|
| url * | string | Public or user-authorized http(s) URL of the page to inspect. |
| timeout_seconds | integer | Timeout in seconds for fetching the page (1-30). |
{
"name": "inspect_url",
"title": "Inspect URL Reuse Route",
"description": "Fetch a public or user-authorized URL and inspect title, metadata, frame policy, and likely source/embed candidates. Does not capture screenshots or persist artifacts.",
"inputSchema": {
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "Public or user-authorized http(s) URL of the page to inspect."
},
"timeout_seconds": {
"type": "integer",
"maximum": 30,
"minimum": 1,
"description": "Timeout in seconds for fetching the page (1-30)."
}
}
},
"outputSchema": {
"type": "object",
"additionalProperties": true
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Extract likely embed, preview, viewer, remix, and source URLs from a public or user-authorized page.
| Parameter | Type | Description |
|---|---|---|
| url * | string | Public or user-authorized http(s) URL of the page to inspect. |
| timeout_seconds | integer | Timeout in seconds for fetching the page (1-30). |
{
"name": "discover_embed_candidates",
"title": "Discover Embed Candidates",
"description": "Extract likely embed, preview, viewer, remix, and source URLs from a public or user-authorized page.",
"inputSchema": {
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "Public or user-authorized http(s) URL of the page to inspect."
},
"timeout_seconds": {
"type": "integer",
"maximum": 30,
"minimum": 1,
"description": "Timeout in seconds for fetching the page (1-30)."
}
}
},
"outputSchema": {
"type": "object",
"additionalProperties": true
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Decide whether a reference should be embedded, sourced, locally captured, bounded-rebuilt, or blocked before reproduction.
| Parameter | Type | Description |
|---|---|---|
| candidates | array | Embed/source candidates as returned by discover_embed_candidates (objects with kind and url). |
| license_text | string | License or permission text that allows reusing the page, from the user or the site; informs the reuse/rebuild policy. |
| site_profile | object | The site_profile object returned by inspect_url. |
| source_signals | array | Extra hints about the page's origin, e.g. ["framer", "spline", "export"]; merged with signals detected from the page. |
| exact_requested | boolean | True (default) when the user wants an exact, faithful clone; false when an approximate rebuild is acceptable. |
{
"name": "classify_clone_mode",
"title": "Classify Clone Mode",
"description": "Decide whether a reference should be embedded, sourced, locally captured, bounded-rebuilt, or blocked before reproduction.",
"inputSchema": {
"type": "object",
"properties": {
"candidates": {
"type": "array",
"items": {
"type": "object"
},
"description": "Embed/source candidates as returned by discover_embed_candidates (objects with kind and url)."
},
"license_text": {
"type": "string",
"description": "License or permission text that allows reusing the page, from the user or the site; informs the reuse/rebuild policy."
},
"site_profile": {
"type": "object",
"description": "The site_profile object returned by inspect_url."
},
"source_signals": {
"type": "array",
"items": {
"type": "string"
},
"description": "Extra hints about the page's origin, e.g. [\"framer\", \"spline\", \"export\"]; merged with signals detected from the page."
},
"exact_requested": {
"type": "boolean",
"description": "True (default) when the user wants an exact, faithful clone; false when an approximate rebuild is acceptable."
}
}
},
"outputSchema": {
"type": "object",
"additionalProperties": true
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Generate an iframe snippet for a known frameable and authorized URL. Does not verify frameability by itself.
| Parameter | Type | Description |
|---|---|---|
| url * | string | URL to embed. It must allow framing; check with inspect_url first. |
| title | string | Accessible title attribute for the iframe. |
| framework | string | Snippet flavor: html (plain iframe) or nextjs (React component). |
{
"name": "generate_embed_snippet",
"title": "Generate Embed Snippet",
"description": "Generate an iframe snippet for a known frameable and authorized URL. Does not verify frameability by itself.",
"inputSchema": {
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "URL to embed. It must allow framing; check with inspect_url first."
},
"title": {
"type": "string",
"description": "Accessible title attribute for the iframe."
},
"framework": {
"enum": [
"html",
"nextjs"
],
"type": "string",
"description": "Snippet flavor: html (plain iframe) or nextjs (React component)."
}
}
},
"outputSchema": {
"type": "object",
"additionalProperties": true
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Create a source-first plan that separates exact embed/source reuse from local capture and bounded rebuild work.
| Parameter | Type | Description |
|---|---|---|
| candidates | array | Embed/source candidates as returned by discover_embed_candidates (objects with kind and url). |
| license_text | string | License or permission text that allows reusing the page, from the user or the site; informs the reuse/rebuild policy. |
| site_profile | object | The site_profile object returned by inspect_url. |
| capture_bundle | object | Capture bundle from the local MCP's capture_reference_bundle, if one exists. |
| source_signals | array | Extra hints about the page's origin, e.g. ["framer", "spline", "export"]; merged with signals detected from the page. |
| exact_requested | boolean | True (default) when the user wants an exact, faithful clone; false when an approximate rebuild is acceptable. |
{
"name": "plan_reproduction_path",
"title": "Plan Reproduction Path",
"description": "Create a source-first plan that separates exact embed/source reuse from local capture and bounded rebuild work.",
"inputSchema": {
"type": "object",
"properties": {
"candidates": {
"type": "array",
"items": {
"type": "object"
},
"description": "Embed/source candidates as returned by discover_embed_candidates (objects with kind and url)."
},
"license_text": {
"type": "string",
"description": "License or permission text that allows reusing the page, from the user or the site; informs the reuse/rebuild policy."
},
"site_profile": {
"type": "object",
"description": "The site_profile object returned by inspect_url."
},
"capture_bundle": {
"type": "object",
"description": "Capture bundle from the local MCP's capture_reference_bundle, if one exists."
},
"source_signals": {
"type": "array",
"items": {
"type": "string"
},
"description": "Extra hints about the page's origin, e.g. [\"framer\", \"spline\", \"export\"]; merged with signals detected from the page."
},
"exact_requested": {
"type": "boolean",
"description": "True (default) when the user wants an exact, faithful clone; false when an approximate rebuild is acceptable."
}
}
},
"outputSchema": {
"type": "object",
"additionalProperties": true
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}webEmbedding hosted intake: read-only checks for cloning or embedding a web page from its URL. Use when the user gives a URL and wants it cloned, copied, recreated, embedded, or checked for whether it can be framed. Start with inspect_url (frame policy, platform, reuse route) and discover_embed_candidates; use generate_embed_snippet when the page allows framing. Full browser capture, offline HTML snapshots, rebuilds, and fidelity verification run in the local MCP: `npx web-embedding mcp` (tool clone_reference_url). Do not use for scraping/summarizing content or bypassing logins, paywalls, captchas, or licenses.
Names, descriptions and schemas were written by the server and are shown as data.
Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators.