# ai.extract

Fetch a URL and extract typed data from its content per a user-supplied JSON Schema. Use when you need a structured payload conforming to your own shape.

Agent View of the PolicyLayer registry record for `ai.extract`. HTML page: https://policylayer.com/tools/io-github-2s-io-mcp/ai.extract

## Facts

- Tool: `ai.extract`
- Server: Mcp (`@2sio/mcp`) — https://policylayer.com/tools/io-github-2s-io-mcp.md
- Install: `npx -y @2sio/mcp`
- Homepage: https://github.com/2s-io/sdk
- Risk category: Read (Low risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Allowed

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "ai.extract",
    "arguments": {}
  }
}
```

## Why ai.extract is rated Low

This tool retrieves and parses content from a URL and structures it according to a schema, but does not modify, delete, or execute code. The operation is purely informational (Read category). Severity is low because the primary risk is exposure of sensitive data at the fetched URL or misuse of the schema definition; the tool itself has no destructive, financial, or code-execution capabilities.

From the tool's own definition: "Tool description states 'Fetch a URL and extract typed data from its content' — fetching and extracting are read-only operations with no modification, deletion, or code execution."

## Use case

AI agents call ai.extract to retrieve information from Mcp without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Mcp:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "ai.extract": {}
  }
}
```

## Other tools on Mcp (571)

- `queue.ack` — Destructive — https://policylayer.com/tools/io-github-2s-io-mcp/queue.ack.md
- `store.blob-delete` — Destructive — https://policylayer.com/tools/io-github-2s-io-mcp/store.blob-delete.md
- `store.doc-delete` — Destructive — https://policylayer.com/tools/io-github-2s-io-mcp/store.doc-delete.md
- `store.kv-delete` — Destructive — https://policylayer.com/tools/io-github-2s-io-mcp/store.kv-delete.md
- `store.vector-delete` — Destructive — https://policylayer.com/tools/io-github-2s-io-mcp/store.vector-delete.md
- `watchers.cancel` — Destructive — https://policylayer.com/tools/io-github-2s-io-mcp/watchers.cancel.md
- `ai.council` — Execute — https://policylayer.com/tools/io-github-2s-io-mcp/ai.council.md
- `ai.screenshot` — Execute — https://policylayer.com/tools/io-github-2s-io-mcp/ai.screenshot.md
- `batch.run` — Execute — https://policylayer.com/tools/io-github-2s-io-mcp/batch.run.md
- `dev.preflight` — Execute — https://policylayer.com/tools/io-github-2s-io-mcp/dev.preflight.md
- `dev.regex-test` — Execute — https://policylayer.com/tools/io-github-2s-io-mcp/dev.regex-test.md
- `hash.compute` — Execute — https://policylayer.com/tools/io-github-2s-io-mcp/hash.compute.md
- `pubsub.subscribe` — Execute — https://policylayer.com/tools/io-github-2s-io-mcp/pubsub.subscribe.md
- `queue.lease` — Execute — https://policylayer.com/tools/io-github-2s-io-mcp/queue.lease.md
- `search.crawl` — Execute — https://policylayer.com/tools/io-github-2s-io-mcp/search.crawl.md
- `url.render` — Execute — https://policylayer.com/tools/io-github-2s-io-mcp/url.render.md
- `watchers.crypto-address-activity` — Execute — https://policylayer.com/tools/io-github-2s-io-mcp/watchers.crypto-address-activity.md
- `watchers.earthquake` — Execute — https://policylayer.com/tools/io-github-2s-io-mcp/watchers.earthquake.md
- `predict.crypto-updown` — Financial — https://policylayer.com/tools/io-github-2s-io-mcp/predict.crypto-updown.md
- `predict.wallet` — Financial — https://policylayer.com/tools/io-github-2s-io-mcp/predict.wallet.md
- `watchers.fear-greed` — Financial — https://policylayer.com/tools/io-github-2s-io-mcp/watchers.fear-greed.md
- `watchers.fx-rate` — Financial — https://policylayer.com/tools/io-github-2s-io-mcp/watchers.fx-rate.md
- `agent.knowledge-delta` — Other — https://policylayer.com/tools/io-github-2s-io-mcp/agent.knowledge-delta.md
- `agriculture.drought` — Read — https://policylayer.com/tools/io-github-2s-io-mcp/agriculture.drought.md
- `agriculture.stats` — Read — https://policylayer.com/tools/io-github-2s-io-mcp/agriculture.stats.md
- `ai.chat` — Read — https://policylayer.com/tools/io-github-2s-io-mcp/ai.chat.md
- `ai.classify` — Read — https://policylayer.com/tools/io-github-2s-io-mcp/ai.classify.md
- `ai.describe-image` — Read — https://policylayer.com/tools/io-github-2s-io-mcp/ai.describe-image.md
- `ai.entities` — Read — https://policylayer.com/tools/io-github-2s-io-mcp/ai.entities.md
- `ai.image` — Read — https://policylayer.com/tools/io-github-2s-io-mcp/ai.image.md
- …and 541 more: https://policylayer.com/tools/io-github-2s-io-mcp.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=io-github-2s-io-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/io-github-2s-io-mcp