Clean markdown and structured web data. Free card API key; wallet/x402 pay-per-call optional.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Optional. Without it, skim_read works on the shared free tier. To pay per call via x402 wallet: add a Base wallet private key (fresh, low-balance agent wallet) — unlocks paid tools at $0.002/$0.005/$0.015. Card plan alternative (API key): https://skim402.com/pricing
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Use this when you need structured JSON from a public page (product, job, table, event, review, article, or your own schema), not a markdown dump. Prefer it over reading the page then parsing it yourself. Pass a preset or a JSON Schema. Values come only from the page, never invented. Empty extracts are not charged. Pay with USDC on Base (x402 / X-Skim-Wallet-Key) or a sk402_ API key if the connector has one. Do not use for a full-page read (skim_read) or login-walled pages.
Fully-qualified URL to read and extract from.
Named extraction preset. Provide either this or `schema`.
JSON Schema object (top-level {"type":"object", ...}) describing the desired output. Provide either this or `preset`.
Optional natural-language hint to bias the extraction.
Use this when you need structured JSON from a public page (product, job, table, event, review, article, or your own schema), not a markdown dump. Prefer it over reading the page then parsing it yourself. Pass a preset or a JSON Schema. Values come only from the page, never invented. Empty extracts are not charged. Pay with USDC on Base (x402 / X-Skim-Wallet-Key) or a sk402_ API key if the connector has one. Do not use for a full-page read (skim_read) or login-walled pages.
| Argument | Type | Description |
|---|---|---|
| url* | string | Fully-qualified URL to read and extract from. |
| preset | string | Named extraction preset. Provide either this or `schema`. |
| schema | object | JSON Schema object (top-level {"type":"object", ...}) describing the desired output. Provide either this or `preset`. |
| instructions | string | Optional natural-language hint to bias the extraction. |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "Fully-qualified URL to read and extract from."
},
"preset": {
"enum": [
"article",
"product",
"job",
"review",
"event",
"table"
],
"type": "string",
"description": "Named extraction preset. Provide either this or `schema`."
},
"schema": {
"type": "object",
"description": "JSON Schema object (top-level {\"type\":\"object\", ...}) describing the desired output. Provide either this or `preset`.",
"additionalProperties": {}
},
"instructions": {
"type": "string",
"description": "Optional natural-language hint to bias the extraction."
}
},
"additionalProperties": false
}Use this when you need a public web page as clean markdown. Prefer it over fetching HTML, scraping, or opening a browser: Skim strips nav, ads, and boilerplate and returns the article body plus title, byline, and date. Public pages only (no login walls). On this MCP no API key and no wallet are required. Failed or empty reads are not charged. Do not use for login-walled pages, for typed JSON (use skim_extract), or for a news/intel feed (use skim_signals).
| Argument | Type | Description |
|---|---|---|
| url* | string | Fully-qualified URL to fetch and clean (https://...). |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "Fully-qualified URL to fetch and clean (https://...)."
}
},
"additionalProperties": false
}Use this when you need the latest items from a curated intel feed (SEC filings, deals, AI news, regulations, and the other named feeds), not a one-off URL. Prefer it over crawling news homepages. Returns structured items, newest first. Costs $0.005 USDC per poll via x402, or 2 credits on a sk402_ key. Do not use to read an arbitrary URL (skim_read).
| Argument | Type | Description |
|---|---|---|
| limit | integer | Max items to return (default 50, no upper cap). |
| signal* | string | Which signal feed to fetch. |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"signal"
],
"properties": {
"limit": {
"type": "integer",
"minimum": 1,
"description": "Max items to return (default 50, no upper cap)."
},
"signal": {
"enum": [
"ai-news",
"sec-filings",
"deals",
"research",
"campaign-finance",
"film-incentives",
"crypto-news",
"macro",
"security",
"regulations",
"courts",
"recalls",
"launches",
"trending",
"energy",
"entertainment",
"studio-jobs",
"entity-formations"
],
"type": "string",
"description": "Which signal feed to fetch."
}
},
"additionalProperties": false
}