# WebExtract MCP server

> Convert any public web page to clean Markdown or fixed-schema JSON with product, price, table and article metadata.

- Listing: https://mcp.tc/i/webextract
- Connect: use the server's own URL `https://api.webextract.dev/mcp` (no sign-in); clients connect to it directly. The listing link is a page, not an MCP endpoint.
- Type: remote (Streamable HTTP)
- Auth: none
- Category: [Search & Web Data](https://mcp.tc/c/search-web)
- Vendor: WebExtract
- Homepage: <https://webextract.dev/>

## About

WebExtract fetches a public web page (robots.txt respected) and returns its main content as clean Markdown. It can also return fixed-schema JSON with article metadata, product and price details, and tables. It suits AI agents and RAG pipelines.

It runs as a hosted streamable HTTP endpoint. No sign-in or API key is needed for the free tier of 20 calls per day per IP. Beyond that, send an Authorization: Bearer header with a prepaid credit key. Pages are fetched as raw HTML, so content built by JavaScript in the browser may come back thin.

## What it can do

- Convert any public URL to clean Markdown
- Extract product name, price, currency and availability
- Pull tables as headers and rows
- Get article metadata such as authors, dates and canonical URL
- Pick the cheaper Markdown-only tool when structure is not needed

## Tools (2)

- `extract_url`: Fetch a public page and return Markdown plus JSON with article metadata, product/price and tables. (read-only)
- `page_markdown`: Fetch a public page and return clean Markdown only, at a lower credit cost. (read-only)

## Example prompts

- "Convert https://example.com/blog/post to Markdown"
- "What does the product at https://web-scraping.dev/product/1 cost?"
- "Extract the tables from this page as structured data"
- "Get the author and publish date of this article URL"

## Install

### Claude Code

1. Run this in a terminal, in your project folder:

```bash
claude mcp add --transport http webextract https://api.webextract.dev/mcp
```

2. Start Claude Code and type `/mcp`. **webextract** should show as connected.

Add `--scope user` to make it available in every project, not just this one.

### Claude Desktop

1. Open **Customize → Connectors**, click **+ Add**, then **Add custom connector**.

2. Name it **WebExtract** and paste this URL:

```url
https://api.webextract.dev/mcp
```

3. Click **Add**. Its tools appear in the chat’s tools menu.

Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.

### claude.ai

1. Open the connector form on claude.ai. This button fills in the name and URL for you:

[Add to claude.ai](<https://claude.ai/customize/connectors?modal=add-custom-connector&connectorName=WebExtract&connectorUrl=https%3A%2F%2Fapi.webextract.dev%2Fmcp>) (opens connector settings)

2. Check that the URL reads `https://api.webextract.dev/mcp` and click **Add**.

3. Turn it on in a chat from the tools menu.

Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**.

### ChatGPT

1. On chatgpt.com, go to **Plugins**, select **+**, then **Add custom MCP server**.

2. Enter a name for the server.

3. Under **Connection**, paste `https://api.webextract.dev/mcp` as the server URL, then for authentication choose **No authentication**.

4. Check **I understand and want to continue**, then select **Create as a plugin**.

Whether you can add a custom MCP server depends on your ChatGPT plan and your workspace permissions (in Business workspaces, admins and owners can).

### Cursor

[Add to Cursor](<https://cursor.com/install-mcp?name=webextract&config=eyJ1cmwiOiJodHRwczovL2FwaS53ZWJleHRyYWN0LmRldi9tY3AifQ%3D%3D>) (opens Cursor)

Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project):

`mcp.json`:

```json
{
  "mcpServers": {
    "webextract": {
      "url": "https://api.webextract.dev/mcp"
    }
  }
}
```

### VS Code

[Install in VS Code](<https://vscode.dev/redirect/mcp/install?name=webextract&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fapi.webextract.dev%2Fmcp%22%7D>) (opens VS Code)

Or from a terminal:

```bash
code --add-mcp '{"name":"webextract","type":"http","url":"https://api.webextract.dev/mcp"}'
```

Or commit it to the repo in `.vscode/mcp.json`:

`.vscode/mcp.json`:

```json
{
  "servers": {
    "webextract": {
      "type": "http",
      "url": "https://api.webextract.dev/mcp"
    }
  }
}
```

### Devin Desktop

1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows):

`mcp_config.json`:

```json
{
  "mcpServers": {
    "webextract": {
      "serverUrl": "https://api.webextract.dev/mcp"
    }
  }
}
```

2. Refresh the MCP server list in Cascade.

Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers.

### Codex

```bash
codex mcp add webextract --url https://api.webextract.dev/mcp
```

Or edit `~/.codex/config.toml` directly:

`config.toml`:

```toml
[mcp_servers.webextract]
url = "https://api.webextract.dev/mcp"
```

### Gemini CLI

```bash
gemini mcp add --transport http webextract https://api.webextract.dev/mcp
```

This adds it to the current project. Add `-s user` to use it everywhere.

### Any client

Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file.

```json
{
  "mcpServers": {
    "webextract": {
      "type": "http",
      "url": "https://api.webextract.dev/mcp"
    }
  }
}
```

Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE.

Client only starts local servers? Bridge it with `npx -y mcp-remote https://api.webextract.dev/mcp`.

## Recent changes

- 2026-10-30 08:46 UTC: 2 tools changed. Source: automatic check. Changed: extract\_url, page\_markdown.
- 2026-10-29 14:43 UTC: Server instructions changed. Source: automatic check. Worth a look: new server instructions.
- 2026-10-25 23:38 UTC: Server instructions changed. Source: automatic check. Worth a look: new server instructions.
- 2026-10-25 08:20 UTC: Tracking started: 2 tools read. Source: automatic check.

More on the History tab, with descriptions before and after for the newest entries: https://mcp.tc/i/webextract#history (Atom feed: https://mcp.tc/i/webextract/history.xml). It records what mcp.tc's anonymous checks saw, every 3 hours where the tool list can be read without sign-in; it is not a security review.

## Details

- Server version: 1.1.0
- MCP protocol version: 2025-06-18
- Last checked: 2026-11-18 (reachable)
- Listed: 2026-10-25
- Updated: 2026-10-30

---
Source: https://mcp.tc/i/webextract (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report
