# Geonode Scraper API MCP server

> Extract web pages as Markdown or HTML, with crawl, map, search and batch jobs available using a Geonode API key.

- Listing: https://mcp.tc/i/geonode-scraper-api
- Connect: use the server's own URL `https://scraper.geonode.io/mcp` (sign-in optional); clients connect to it directly. The listing link is a page, not an MCP endpoint.
- Type: remote (Streamable HTTP)
- Auth: optional (works without sign-in)
- Category: [Search & Web Data](https://mcp.tc/c/search-web)
- Vendor: Geonode
- Homepage: <https://docs.geonode.com/docs/scraper-api/guides/mcp/00_overview>

## About

Connects an assistant to Geonode's Scraper API. The extract tool fetches a web page and returns Markdown or HTML, with options for JavaScript rendering, proxy geo-targeting, custom headers and browser wait controls. With an API key, the server also exposes crawl, map, search, batch and job history tools.

Runs as a hosted streamable HTTP endpoint at https://scraper.geonode.io/mcp. No sign-in or API key is needed to use extract anonymously, which is synchronous only, has no JavaScript rendering and has a small per-client rate and daily limit. A Geonode API key sent in the X-Api-Key header removes these limits and unlocks the other tools.

## What it can do

- Extract page content as Markdown or HTML
- Render JavaScript-heavy pages with a headless browser (API key)
- Geo-target requests through proxies (API key)
- Crawl and map websites (API key)
- Search the web and run batch jobs (API key)
- Poll asynchronous job status (API key)

## Tools (16)

- `extract`: Extract a web page as HTML or Markdown, with optional JS rendering, geo-targeting and custom… (read-only)
- `job`: Retrieve the result of an asynchronous extraction job by its job ID. (read-only)
- `jobs`: List extraction jobs with optional filters. (read-only)
- `statistics`: Retrieve aggregated extraction statistics for the authenticated user. (read-only)
- `batch`: Start an asynchronous batch extraction job from an explicit list of URLs.
- `batch_status`: Retrieve the status and paginated results of a batch extraction job by its job ID. (read-only)
- `cancel_batch`: Cancel a batch job by its job ID. (can modify or delete data)
- `crawl`: Start a website crawl job from a seed URL.
- `crawl_status`: Retrieve the status and results of a crawl job by its job ID. (read-only)
- `cancel_crawl`: Cancel a crawl job by its job ID. (can modify or delete data)
- `map`: Discover all URLs under a base URL by combining sitemap parsing with HTML link extraction from the seed page. (read-only)
- `map_jobs`: List map jobs for the authenticated user with optional filters. (read-only)
- `map_job`: Retrieve the full details and discovered links for a map job by its job ID. (read-only)
- `search`: Run a web search and return ranked results. (read-only)
- `search_jobs`: List search jobs for the authenticated user with optional filters. (read-only)
- `search_job`: Retrieve the full details and results for a search job by its job ID. (read-only)

## Example prompts

- "Extract the content of this product page as Markdown."
- "Fetch https://example.com/docs and summarize the page."
- "Crawl the official React documentation and list its main sections."
- "Check whether my extraction job has finished."

## Install

### Claude Code

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

```bash
claude mcp add --transport http geonode-scraper-api https://scraper.geonode.io/mcp
```

2. Start Claude Code and type `/mcp`. **geonode-scraper-api** should show as connected. To sign in for more access, pick it and choose **Authenticate**.

Add `--scope user` to make it available in every project, not just this one. Works without a key. An API key from Geonode raises the limits: send it as `X-Api-Key: <YOUR_API_KEY>`.

### Claude Desktop

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

2. Name it **Geonode Scraper API** and paste this URL:

```url
https://scraper.geonode.io/mcp
```

3. Click **Add**, then **Connect**. Signing in to Geonode is optional.

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=Geonode%20Scraper%20API&connectorUrl=https%3A%2F%2Fscraper.geonode.io%2Fmcp>) (opens connector settings)

2. Check that the URL reads `https://scraper.geonode.io/mcp` and click **Add**.

3. Click **Connect**. Signing in to Geonode is optional.

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://scraper.geonode.io/mcp` as the server URL, then for authentication choose **No authentication**, or **OAuth** to sign in to Geonode for more access.

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=geonode-scraper-api&config=eyJ1cmwiOiJodHRwczovL3NjcmFwZXIuZ2Vvbm9kZS5pby9tY3AifQ%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": {
    "geonode-scraper-api": {
      "url": "https://scraper.geonode.io/mcp"
    }
  }
}
```

Works without a key. An API key from Geonode raises the limits: send it as `X-Api-Key: <YOUR_API_KEY>`.

### VS Code

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

Or from a terminal:

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

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

`.vscode/mcp.json`:

```json
{
  "servers": {
    "geonode-scraper-api": {
      "type": "http",
      "url": "https://scraper.geonode.io/mcp"
    }
  }
}
```

Works without a key. An API key from Geonode raises the limits: send it as `X-Api-Key: <YOUR_API_KEY>`.

### 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": {
    "geonode-scraper-api": {
      "serverUrl": "https://scraper.geonode.io/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. Works without a key. An API key from Geonode raises the limits: send it as `X-Api-Key: <YOUR_API_KEY>`.

### Codex

```bash
codex mcp add geonode-scraper-api --url https://scraper.geonode.io/mcp
```

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

`config.toml`:

```toml
[mcp_servers.geonode-scraper-api]
url = "https://scraper.geonode.io/mcp"
```

Works without a key. An API key from Geonode raises the limits: send it as `X-Api-Key: <YOUR_API_KEY>`.

### Gemini CLI

```bash
gemini mcp add --transport http geonode-scraper-api https://scraper.geonode.io/mcp
```

Then, inside Gemini CLI, run `/mcp auth geonode-scraper-api` to sign in (optional).

This adds it to the current project. Add `-s user` to use it everywhere. Works without a key. An API key from Geonode raises the limits: send it as `X-Api-Key: <YOUR_API_KEY>`.

### 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": {
    "geonode-scraper-api": {
      "type": "http",
      "url": "https://scraper.geonode.io/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://scraper.geonode.io/mcp`.

Works without a key. An API key from Geonode raises the limits: send it as `X-Api-Key: <YOUR_API_KEY>`.

## Recent changes

- 2026-11-13 11:53 UTC: 1 tool changed. Source: automatic check. Changed: search.
- 2026-11-09 08:52 UTC: 3 tools changed. Source: automatic check. Changed: jobs, map\_jobs, search\_jobs.
- 2026-11-05 11:52 UTC: 1 tool changed. Source: automatic check. Changed: search.
- 2026-10-27 17:58 UTC: New version 1.0.1 (was 0.1.0), reported by the server. Source: automatic check.
- 2026-10-27 08:42 UTC: 15 tools added. Server instructions changed. Source: automatic check. Worth a look: a new tool is marked destructive and new server instructions. Added: batch, batch\_status, cancel\_batch, cancel\_crawl, crawl, crawl\_status, job, jobs, map, map\_job, map\_jobs, search, search\_job, search\_jobs, statistics.

More on the History tab, with descriptions before and after for the newest entries: https://mcp.tc/i/geonode-scraper-api#history (Atom feed: https://mcp.tc/i/geonode-scraper-api/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: 1.0.1
- MCP protocol version: 2026-07-28
- Last checked: 2026-11-18 (reachable)
- Listed: 2026-10-19
- Updated: 2026-11-09

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