# AIHackr

> Read public webpages, extract structured data, discover links, and run bounded crawls.

- name: io.github.biserd/aihackr
- version: 0.8.1
- connection class: R0 (autonomous)
- trust: 96/100
- quality: 94/100 (new)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.biserd%2Faihackr
- tools: https://api.protogrid.dev/v1/servers/io.github.biserd%2Faihackr/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "aihackr": {
      "type": "http",
      "url": "https://aihackr.com/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 97
- freshness: 100
- provenance: 90
- drivers: +repository +namespace-matches-repo +website +reachable +uptime-92% +updated-1d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 94/100 (new)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 9 of 9 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 1,314 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump
- pass `tools.hidden_text`: no hidden text in tool names, descriptions, schemas or annotations

### stability: n/a (weight 15)

- n/a `stability.changes`, `stability.rug_pull`, `stability.new_links`: tool history recorded for 1 of the 7 days needed

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 9, about 1,314 tokens to load them all
- tool set hash: e15c112c4b515c97ee3360966d932681
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.biserd/aihackr.svg)](https://protogrid.dev/servers/io.github.biserd/aihackr)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://aihackr.com/mcp (streamable-http, auth none, reachable true, uptime30d 0.9166667)

## Packages

_none_

## Tools (9)

- `cancel_crawl`: Cancel a running crawl job No additional credits; final crawl settlement includes partial successful pages.
- `get_account`: Identify the connected AIHackr account.
- `get_crawl_result`: Get the status and records of a crawl job started with start_crawl No additional credits; final crawl settlement includes partial successful pages.
- `get_url_html_content`: Get page HTML content Costs 1 credit per successful request.
- `get_url_json`: Extract structured JSON from a page using AI. Provide a prompt and/or a response_format JSON schema to guide extraction. Costs 5 credits per successful extraction.
- `get_url_links`: Get the list of links on a page Costs 1 credit per successful request.
- `get_url_markdown`: Get page converted into Markdown Costs 1 credit per successful request.
- `scrape_url_elements`: Scrape elements from a page by CSS selector Costs 1 credit per successful request.
- `start_crawl`: Start an asynchronous crawl of a website. Returns a job_id — poll get_crawl_result to retrieve records. Workspace maximum: 100 pages and depth 5. Reserves the page limit; charges 1 credit per successful page.