# Olostep MCP Server (npm · olostep-mcp)

Search, scrape, and crawl the web for AI agents. Batch scraping and answers with citations.

- Trust score: 57/100 (low)
- Change this week: +20
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `olostep-mcp`: 57/100 (this document), [markdown](https://verifymcp.io/servers/olostep-olostep-mcp-server/olostep-mcp.md), [page](https://verifymcp.io/servers/olostep-olostep-mcp-server/olostep-mcp)

## Channel facts

- Registry: `npm`
- Package: `olostep-mcp`
- Version: `1.0.17`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (102 of 103), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (102 of 103), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 19/100
  - Repository check failed: no source repository is declared.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (ISC).
  - Actively maintained (last published 31 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 60/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1838 tokens (~183/item across 10 items; 10 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add olostep-olostep-mcp-server -- npx -y olostep-mcp
```

### Codex

```bash
codex mcp add olostep-olostep-mcp-server -- npx -y olostep-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "olostep-olostep-mcp-server": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "olostep-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add olostep-olostep-mcp-server --command npx --arg -y --arg olostep-mcp
```

### Hermes

```yaml
mcp_servers:
  olostep-olostep-mcp-server:
    command: "npx"
    args: ["-y", "olostep-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "olostep-olostep-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "olostep-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 57, +44)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional regression] Security disclosure: unverified → fail
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Schema quality: unverified → good
- [functional] Licence: ISC

### 2026-08-01 (score 13, +13)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-31 (score 0, −19)

- [security regression] Malware scan: pass → unverified
- [functional regression] Dependency health: partial → unverified

### 2026-07-29 (score 19, −18)

- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] Dependency health: unverified → partial
- [functional] First check of Schema quality: unverified

### 2026-07-27 (score 37)

First indexed and scored.

## MCP tools (10)

### `create_map` (~206 tokens)

Get a LIST of URLs on a website (URL discovery only — does NOT scrape content). Use when the user wants a list of links: 'show me all URLs on this site', 'map this website', or when you want to surface candidate URLs to the user before scraping a subset. Prefer `create_crawl` if the goal is to scrape the whole site — it discovers AND scrapes in one workflow. Use this only when the URL list itself is the deliverable.

Input parameters:

- `exclude_url_patterns` (array): Optional glob patterns to exclude (e.g., "/admin/**").
- `include_url_patterns` (array): Optional glob patterns to include (e.g., "/blog/**").
- `search_query` (string): Optional search query to filter URLs (e.g., "blog").
- `top_n` (integer): Optional limit for number of URLs returned.
- `url` (string): Website URL to extract links from.
- `website_url` (string): Alias for `url`.

### `create_crawl` (~270 tokens)

\**PREFERRED tool for crawling a website.** Use this whenever the user says 'crawl', 'scrape the whole site', 'get all pages from a site', or wants multiple pages from a single domain. This is the CORRECT tool for any whole-site scraping task. **Do NOT use `batch_scrape_urls` for crawling** - that tool is only for when you already have a specific list of unrelated URLs from different domains. Starts an ASYNC crawl that autonomously discovers and scrapes pages by following links from a start URL. Returns a crawl_id - the crawl runs in the background. You MUST then call `get_crawl_results` with the returned crawl_id to poll status and retrieve the scraped pages. Do NOT call `get_batch_results` with a crawl_id - crawls and batches are separate resources.

Input parameters:

- `country` (string): Optional country code for location-specific crawling.
- `max_pages` (integer): Maximum number of pages to crawl. Set to 1 to scrape only the start URL.
- `output_format` (string): Format for scraped content. Default: "markdown".
- `parser` (string): Optional parser ID for specialized content extraction.
- `start_url` (string): Alias for `url`.
- `url` (string): Starting URL for the crawl.

### `get_crawl_results` (~207 tokens)

Retrieve the status and scraped pages for a crawl job. Pass the crawl_id returned by create_crawl. If the crawl is still in_progress, returns the current status so you can call again later (poll every ~10 seconds). Once completed, returns the list of discovered pages with their scraped content in the requested formats. This is the REQUIRED companion to create_crawl — create_crawl only kicks off the async job, this tool is how you actually get the content.

Input parameters:

- `crawl_id` (string, required): The crawl_id (or id) returned from create_crawl.
- `cursor` (integer): Pagination cursor for list-pages. Default: 0 (first page).
- `formats` (array): Content formats to retrieve per page. Default: ["markdown"].
- `items_limit` (integer): Max number of pages to retrieve content for (1-100). Default: 20.
- `search_query` (string): Optional filter to rank/select pages by relevance to a query.

### `batch_scrape_urls` (~334 tokens)

Scrape a SPECIFIC, KNOWN list of URLs (typically from different domains). **Do NOT use this for crawling a website** - if the user wants to scrape a whole site or 'crawl' a domain, use `create_crawl` instead. Use this only when you already have an explicit list of URLs to scrape (e.g., user provides a CSV of URLs, or you need to scrape unrelated pages). Returns a batch_id immediately. Use `get_batch_results` with the batch_id to fetch the scraped content once the batch completes (~5–8 min). Set `wait_for_completion_seconds` to poll automatically.

Input parameters:

- `country` (string): Optional country code for location-specific scraping.
- `output_format` (string): Choose format for all URLs. Default: "markdown".
- `parser` (string): Optional parser ID for specialized extraction (e.g. @olostep/google-search).
- `urls` (array): Array of URLs to scrape — plain URL strings, or objects with "url" and optional "custom_id".
- `urls_to_scrape` (array): Alias for `urls`.
- `wait_before_scraping` (integer): Wait time in milliseconds before scraping each URL.
- `wait_for_completion_seconds` (integer): Seconds to wait for batch completion. If >0, polls every 10s until done or timeout, then returns status. Use 0 to return immediately with batch_id (then call get_batch_results later). Recommended: 60…

### `get_batch_results` (~126 tokens)

Retrieve the status and scraped content for a batch job. Pass the batch_id returned by batch_scrape_urls. If the batch is completed, returns the scraped content for each URL. If still in_progress, returns the current status so you can call again later.

Input parameters:

- `batch_id` (string, required): The batch_id (or id) returned from batch_scrape_urls.
- `formats` (array): Content formats to retrieve per URL. Default: ["markdown"].
- `items_limit` (integer): Max number of items to retrieve content for (1-100). Default: 20.

### `answers` (~168 tokens)

Answer a factual question using web search, optionally shaped into a flat JSON object of fields (returned with sources and citations). Best for a bounded, factual answer (e.g. a company's founding year, a product's current price). It is NOT reliable for enumerating a live list from a page (e.g. 'the latest N blog posts with titles and dates'). For that, use create_map or get_webpage_content on the page and read the results instead.

Input parameters:

- `json`: Optional shape for the answer: a flat JSON object of the fields you want. Example: { "book_title": "", "author": "", "release_date": "" }. Keep it flat. Deeply nested shapes or long lists are unrelia…
- `task` (string, required): Question or task to answer using web data.

### `search_web` (~56 tokens)

Search the web for a given query and return structured results (non-AI, parser-based).

Input parameters:

- `country` (string): Optional country code for localized results (e.g., US, GB).
- `query` (string, required): Search query

### `scrape_website` (~274 tokens)

Extract content from a single URL. Supports multiple formats and JavaScript rendering.

Input parameters:

- `country` (string): Optional country code (e.g., US, GB, CA) for location-specific scraping.
- `llm_extract` (object): Defines what to pull when output_format is "json". Provide a `schema` (a JSON-schema object of the fields you want, e.g. { "type": "object", "properties": { "title": { "type": "string" } } }) and/or…
- `output_format` (string): Output format. "markdown" (default), "html", and "text" need no extra config. "json" returns STRUCTURED data and requires either a `parser` OR an `llm_extract` schema describing the fields to pull. D…
- `parser` (string): Optional parser ID for specialized extraction (e.g., "@olostep/amazon-product").
- `url` (string): The URL of the website you want to scrape.
- `url_to_scrape` (string): Alias for `url`.
- `wait_before_scraping` (integer): Wait time in milliseconds before scraping (0-10000). Useful for dynamic content.

### `get_webpage_content` (~90 tokens)

Retrieve content of a webpage in markdown

Input parameters:

- `country` (string): Residential country to load the request from (e.g., US, CA, GB). Optional.
- `url` (string): The URL of the webpage to scrape.
- `url_to_scrape` (string): Alias for `url`.
- `wait_before_scraping` (integer): Time to wait in milliseconds before starting the scrape.

### `get_website_urls` (~107 tokens)

Search and retrieve relevant URLs from a website (URL discovery only - does NOT scrape content). Use this only when the user wants a *filtered list of links* matching a search query. **Do NOT use this as a precursor to scraping** - if the user wants to scrape/crawl a site, use `create_crawl` directly.

Input parameters:

- `search_query` (string, required): The search query to sort URLs by.
- `url` (string, required): The URL of the website to map.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/olostep-olostep-mcp-server/olostep-mcp#diagnostics

## Score history

- 2026-08-03: 57
- 2026-08-02: 57
- 2026-08-01: 13
- 2026-07-31: 0
- 2026-07-29: 19
- 2026-07-28: 37
- 2026-07-27: 37

## Links

- npm package: https://www.npmjs.com/package/olostep-mcp
- Socket report: https://socket.dev/npm/package/olostep-mcp
- Changelog RSS feed: https://verifymcp.io/servers/olostep-olostep-mcp-server/olostep-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/olostep-olostep-mcp-server/olostep-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/olostep-olostep-mcp-server/olostep-mcp