WebExtract MCP
A remote MCP server that extracts web page content into clean Markdown and structured JSON, including product details, pricing, tables, and article metadata. It supports AI agents and RAG pipelines by providing consistent data shapes across different websites, respecting robots.txt, and offering both free tier and prepaid credit options.
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.
MCP endpoint (Streamable HTTP)
https://api.webextract.dev/mcpWhat you can do with it
- Extract main content as clean Markdown from any URL
- Retrieve structured product data including name, price, and SKU
- Parse HTML tables into GFM format with header and row data
- Get article metadata such as title, authors, and publication dates
Source and maintenance
Vendor evidenceRegistry 1.0.3
Protocol and capabilities
- Server
- webextract 1.1.0
- MCP protocol
- 2025-06-18
- Tools
- 2 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.
Tools
2 advertised
extract_url — Extract web page
Advertised read-onlyOpen-world
Fetch a public web page (robots.txt respected) and return clean Markdown plus fixed-schema JSON: article metadata, product/price, tables. HTML only, no JS execution, no PDF. Free 20 calls/day per IP; pass 'Authorization: Bearer <key>' for prepaid credits.
extract_url input schema
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "Public http(s) URL"
}
}
}extract_url output schema
{
"type": "object",
"required": [
"url",
"final_url",
"fetched_at",
"schema_version",
"markdown",
"metadata",
"product",
"tables"
],
"properties": {
"url": {
"type": "string"
},
"tables": {
"type": "array",
"items": {
"type": "object",
"properties": {
"rows": {
"type": "array",
"items": {
"type": "array",
"items": {
"type": "string"
}
}
},
"index": {
"type": "integer"
},
"checks": {
"type": "object",
"properties": {
"row_count": {
"type": "integer"
},
"column_count": {
"type": "integer"
},
"consistent_width": {
"type": "boolean"
}
}
},
"caption": {
"type": [
"string",
"null"
]
},
"headers": {
"type": "array",
"items": {
"type": "string"
}
}
}
}
},
"product": {
"type": [
"object",
"null"
],
"properties": {
"sku": {
"type": [
"string",
"null"
]
},
"gtin": {
"type": [
"string",
"null"
]
},
"name": {
"type": [
"string",
"null"
]
},
"brand": {
"type": [
"string",
"null"
]
},
"image": {
"type": [
"string",
"null"
]
},
"price": {
"type": [
"number",
"null"
]
},
"rating": {
"type": [
"object",
"null"
]
},
"source": {
"enum": [
"json-ld",
"opengraph",
"microdata",
"heuristic",
null
],
"type": [
"string",
"null"
],
"description": "Extraction method for the flat fields (not the content source; see content_source)"
},
"currency": {
"type": [
"string",
"null"
]
},
"price_high": {
"type": [
"number",
"null"
]
},
"description": {
"type": [
"string",
"null"
]
},
"availability": {
"type": [
"string",
"null"
]
},
"price_detail": {
"type": "object",
"required": [
"status",
"prices"
],
"properties": {
"range": {
"type": [
"object",
"null"
],
"properties": {
"low": {
"type": "number"
},
"high": {
"type": [
"number",
"null"
]
},
"basis": {
"enum": [
"aggregate_offer",
"offers",
"product_group_variants"
],
"type": "string"
},
"currency": {
"type": [
"string",
"null"
]
},
"offer_count": {
"type": [
"integer",
"null"
]
}
}
},
"prices": {
"type": "array",
"items": {
"type": "object",
"required": [
"type",
"amount",
"currency"
],
"properties": {
"type": {
"enum": [
"list",
"sale",
"installment",
"current"
],
"type": "string",
"description": "current = the only price shown, no discount information; sale = current price with a higher list price on the page"
},
"amount": {
"type": "number",
"exclusiveMinimum": 0
},
"method": {
"enum": [
"json-ld",
"opengraph",
"microdata",
"heuristic",
"dom",
"shopify_meta"
],
"type": "string"
},
"variant": {
"type": [
"object",
"null"
],
"properties": {
"id": {
"type": [
"string",
"null"
]
},
"sku": {
"type": [
"string",
"null"
]
},
"url": {
"type": [
"string",
"null"
]
},
"name": {
"type": [
"string",
"null"
]
},
"match": {
"enum": [
"offer_url",
"offer_sku",
"shopify_variant_id",
"url_param+dom_selected",
"dom_selected"
],
"type": "string"
},
"attributes": {
"type": [
"object",
"null"
]
}
}
},
"currency": {
"type": [
"string",
"null"
]
},
"evidence": {
"type": [
"string",
"null"
]
},
"amount_high": {
"type": [
"number",
"null"
]
},
"installment": {
"type": [
"object",
"null"
]
}
}
}
},
"status": {
"enum": [
"resolved",
"partial",
"unresolved"
],
"type": "string"
},
"currency": {
"type": [
"string",
"null"
]
},
"variants": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": [
"string",
"null"
]
},
"sku": {
"type": [
"string",
"null"
]
},
"url": {
"type": [
"string",
"null"
]
},
"name": {
"type": [
"string",
"null"
]
},
"amount": {
"type": [
"number",
"null"
]
},
"source": {
"type": [
"string",
"null"
]
},
"currency": {
"type": [
"string",
"null"
]
},
"evidence": {
"type": [
"string",
"null"
]
},
"attributes": {
"type": [
"object",
"null"
]
},
"availability": {
"type": [
"string",
"null"
]
}
}
},
"maxItems": 100
},
"warnings": {
"type": "array",
"items": {
"type": "string"
}
},
"unresolved": {
"type": [
"object",
"null"
],
"required": [
"reason"
],
"properties": {
"detail": {
"type": [
"string",
"null"
]
},
"reason": {
"enum": [
"no_offer_in_structured_data",
"price_not_numeric",
"zero_price",
"js_rendered_suspected",
"template_placeholder",
"no_price_found",
"variant_not_matched",
"listing_page",
"no_product_markup",
"not_html"
],
"type": "string"
}
}
},
"currency_basis": {
"enum": [
"declared",
"symbol",
null
],
"type": [
"string",
"null"
]
},
"selected_variant": {
"type": [
"object",
"null"
],
"properties": {
"id": {
"type": [
"string",
"null"
]
},
"sku": {
"type": [
"string",
"null"
]
},
"url": {
"type": [
"string",
"null"
]
},
"name": {
"type": [
"string",
"null"
]
},
"match": {
"enum": [
"offer_url",
"offer_sku",
"shopify_variant_id",
"url_param+dom_selected",
"dom_selected"
],
"type": "string"
},
"attributes": {
"type": [
"object",
"null"
]
}
}
}
},
"description": "Preferred price field. Never contains 0. status=unresolved always comes with unresolved.reason."
}
}
},
"markdown": {
"type": "string"
},
"metadata": {
"type": "object",
"properties": {
"type": {
"type": [
"string",
"null"
]
},
"image": {
"type": [
"string",
"null"
]
},
"title": {
"type": [
"string",
"null"
]
},
"authors": {
"type": "array",
"items": {
"type": "string"
}
},
"language": {
"type": [
"string",
"null"
]
},
"site_name": {
"type": [
"string",
"null"
]
},
"description": {
"type": [
"string",
"null"
]
},
"modified_at": {
"type": [
"string",
"null"
]
},
"published_at": {
"type": [
"string",
"null"
]
},
"canonical_url": {
"type": [
"string",
"null"
]
}
}
},
"final_url": {
"type": "string"
},
"fetched_at": {
"type": "string"
},
"word_count": {
"type": "integer"
},
"content_source": {
"enum": [
"raw_html",
"rendered"
],
"type": "string",
"description": "Where the content came from: raw_html = the HTTP response body, no JavaScript executed (current behaviour); rendered = after headless rendering (not offered yet)"
},
"schema_version": {
"type": "string"
},
"markdown_truncated": {
"type": "boolean"
},
"product_unresolved": {
"type": [
"object",
"null"
],
"required": [
"reason"
],
"properties": {
"detail": {
"type": [
"string",
"null"
]
},
"reason": {
"enum": [
"no_offer_in_structured_data",
"price_not_numeric",
"zero_price",
"js_rendered_suspected",
"template_placeholder",
"no_price_found",
"variant_not_matched",
"listing_page",
"no_product_markup",
"not_html"
],
"type": "string"
}
},
"description": "Only when product is null: why no product was extracted (e.g. listing_page)"
}
}
}extract_url annotations
{
"title": "Extract web page",
"readOnlyHint": true,
"openWorldHint": true,
"destructiveHint": false
}page_markdown — Web page to Markdown
Advertised read-onlyOpen-world
Fetch a public web page (robots.txt respected) and return clean Markdown only. HTML only, no JS execution, no PDF. Cheaper than extract_url (0.4 credit). Free 20 calls/day per IP; pass 'Authorization: Bearer <key>' for prepaid credits.
page_markdown input schema
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "Public http(s) URL"
}
}
}page_markdown output schema
{
"type": "object",
"required": [
"url",
"final_url",
"markdown"
],
"properties": {
"url": {
"type": "string"
},
"title": {
"type": [
"string",
"null"
]
},
"markdown": {
"type": "string"
},
"final_url": {
"type": "string"
},
"fetched_at": {
"type": "string"
},
"word_count": {
"type": "integer"
},
"content_source": {
"enum": [
"raw_html",
"rendered"
],
"type": "string",
"description": "Where the content came from: raw_html = the HTTP response body, no JavaScript executed (current behaviour); rendered = after headless rendering (not offered yet)"
},
"markdown_truncated": {
"type": "boolean"
}
}
}page_markdown annotations
{
"title": "Web page to Markdown",
"readOnlyHint": true,
"openWorldHint": true,
"destructiveHint": false
}Prompts
Not advertised
Resources
Not advertised
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
- 1495 ms
- 95th percentile latency
- 1495 ms
Maintenance history
Public check and source-refresh events. Editorial and ownership records remain private.
- · probe · passed · 1495 ms · metadata changed · 2 tool(s)
Connect from your client
Each snippet registers the same endpoint; pick the client you use.
Claude Code
Claude Code configuration
claude mcp add --transport http webextract-mcp https://api.webextract.dev/mcpCodex
Codex configuration
codex mcp add webextract-mcp --url https://api.webextract.dev/mcpCursor
Cursor configuration
{
"mcpServers": {
"webextract-mcp": {
"url": "https://api.webextract.dev/mcp"
}
}
}Cline
Cline configuration
{
"mcpServers": {
"webextract-mcp": {
"type": "streamableHttp",
"url": "https://api.webextract.dev/mcp",
"disabled": false
}
}
}VS Code
VS Code configuration
{
"servers": {
"webextract-mcp": {
"type": "http",
"url": "https://api.webextract.dev/mcp"
}
}
}Gemini CLI
Gemini CLI configuration
gemini mcp add --transport http webextract-mcp https://api.webextract.dev/mcpClaude Desktop
Claude Desktop configuration
{
"mcpServers": {
"webextract-mcp": {
"url": "https://api.webextract.dev/mcp"
}
}
}Windsurf
Windsurf configuration
{
"mcpServers": {
"webextract-mcp": {
"serverUrl": "https://api.webextract.dev/mcp"
}
}
}Let your agent find its tools
Find servers like WebExtract MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.
Other developer tools servers
Do you run WebExtract MCP?
Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.