mcp-bastion-anthropic 2.0.0

MCP-Bastion security middleware for Anthropic Claude — prompt injection, PII, and rate-limit protection for AI agents

mcp-bastion-anthropic

Security middleware for Anthropic Claude powered by MCP-Bastion.

Protects your Claude API calls from prompt injection, PII leakage, and resource exhaustion.

Install

pip install mcp-bastion-anthropic

Usage

from mcp_bastion_anthropic import SecureClaude

client = SecureClaude()  # uses ANTHROPIC_API_KEY from env
response = client.chat("What is MCP?")
print(response)

Features

• Content filtering on all prompts
• Rate limiting per caller
• Prompt injection detection
• PII redaction

License

Same terms as the MCP-Bastion project: see LICENSE. Non-commercial use is free with required citation/attribution; copyright terms apply. Commercial use as defined in the License may need a separate agreement (COMMERCIAL_LICENSE.md).