webEmbedding
Server Details
Clone any web page from a URL into a verified offline HTML copy, embed, or rebuild.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-03-26
- URL
- Repository
- jongko54/webEmbedding
- GitHub Stars
- 14
- Server Listing
- webEmbedding
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 6 tools
Most tools target distinct steps, but inspect_url overlaps with discover_embed_candidates by also returning embed/source candidates, and classify_clone_mode overlaps with plan_reproduction_path around choosing reproduction strategy. Descriptions help clarify the boundaries, but an agent could still plausibly misselect between these pairs.
All tool names use a consistent snake_case verb_noun pattern: classify_clone_mode, detect_runtime_capabilities, discover_embed_candidates, generate_embed_snippet, inspect_url, and plan_reproduction_path. The convention is predictable throughout.
Six tools is well-scoped for a web embedding/reproduction planning server. Each tool maps to a recognizable stage: runtime capability detection, URL inspection, candidate discovery, mode classification, path planning, and snippet generation.
The surface covers inspection, discovery, classification, planning, and snippet generation, which is a coherent lifecycle for the stated purpose. The main gap is that generate_embed_snippet explicitly does not verify frameability and there is no dedicated validation tool, though inspect_url partly compensates by checking frame policy.
Available Tools
6 toolsclassify_clone_modeClassify Clone ModeBRead-onlyIdempotentInspect
Decide whether a reference should be embedded, sourced, locally captured, bounded-rebuilt, or blocked before reproduction.
Inputs: candidates, license_text, site_profile, source_signals, +1 more. Returns: object
detect_runtime_capabilitiesDetect Hosted Runtime CapabilitiesBRead-onlyIdempotentInspect
Report hosted Apps SDK readiness, read-only runtime capabilities, unsupported capture behavior, and the local stdio command.
Inputs: no named parameters. Returns: object
discover_embed_candidatesDiscover Embed CandidatesBRead-onlyIdempotentInspect
Extract likely embed, preview, viewer, remix, and source URLs from a public or user-authorized page.
Inputs: url (required), timeout_seconds. Returns: object
generate_embed_snippetGenerate Embed SnippetARead-onlyIdempotentInspect
Generate an iframe snippet for a known frameable and authorized URL. Does not verify frameability by itself.
Inputs: url (required), title, framework. Returns: object
inspect_urlInspect URL Reuse RouteARead-onlyIdempotentInspect
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.
Inputs: url (required), timeout_seconds. Returns: object
plan_reproduction_pathPlan Reproduction PathBRead-onlyIdempotentInspect
Create a source-first plan that separates exact embed/source reuse from local capture and bounded rebuild work.
Inputs: candidates, license_text, site_profile, capture_bundle, +2 more. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Capture web pages as cryptographically signed, tamper-evident evidence with WACZ archives.
Preserve public web pages as signed, timestamped evidence packages, then verify them, compare versions and monitor pages for changes.
Download files from URL lists or every file linked on a page (images, PDFs, media); ZIP.
Read, screenshot, diff, verify and audit any URL: SEO, links, sitemaps, schema, a11y.
Related MCP Servers
- FlicenseBqualityDmaintenanceProvides a tool to download entire websites using wget. It preserves the website structure and converts links to work locally.1157-
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to clone entire websites, download files, manage authentication sessions, and analyze site information with support for JavaScript-heavy SPAs and dynamic content.11Apache 2.0
- FlicenseNot gradedqualityCmaintenanceArchives live web pages for offline replay with full interactivity, enabling AI agents to analyze page structure and behavior.1-
- FlicenseNot gradedqualityAmaintenanceFetches web content locally, removes clutter, and converts pages to clean Markdown for efficient LLM consumption, with optional crawling and caching.-
Glama MCP Gateway
Add one secure layer between your agents and this server.