agentsafe-sdk 0.1.0

# AgentSafe Python SDK

Real-time URL trust scoring for AI agents. Block phishing, scam sites, and malicious redirects before your agent interacts with them.

## Installation

````pip install agentsafe```

## Quick Start

from agentsafe import AgentSafe



client = AgentSafe(api\_key="your\_api\_key")



result = client.check("https://example.com", action="payment")

print(result.score)        # 0-100

print(result.recommendation)  # TRUSTED or RISKY

print(result.blocked)      # True or False

## Raise on Block

from agentsafe import AgentSafe



client = AgentSafe(api\_key="your\_api\_key")



\# Raises exception if URL is blocked

client.check\_or\_raise("https://example.com", action="payment")

## Environment Variable

import os

from agentsafe import check



os.environ\["AGENTSAFE\_API\_KEY"] = "your\_api\_key"

result = check("https://example.com", action="payment")

## LangChain Integration

from agentsafe import AgentSafe



safe = AgentSafe(api\_key="your\_api\_key")



def safe\_browse(url: str) -> str:

    safe.check\_or\_raise(url, action="browse")

    # proceed with browsing...

    return "Safe to proceed"

## Actions

- browse — general browsing

- payment — making a payment

- login — logging into a site

- download — downloading a file

## Get an API Key

Visit [agentsafe.app](https://agentsafe.app) to get your API key.

## License

MIT

Save it. 👊