mcp-bastion-langchain 3.3.0

MCP-Bastion security middleware integration for LangChain - prompt injection, PII, and rate-limit protection for LLM agents

mcp-bastion-langchain

Security middleware for LangChain powered by MCP-Bastion.

Protects your LangChain agents from prompt injection, PII leakage, and resource exhaustion.

Install

pip install mcp-bastion-langchain

Usage

Callback (automatic protection)

from langchain_openai import ChatOpenAI
from mcp_bastion_langchain import BastionSecurityCallback

llm = ChatOpenAI(callbacks=[BastionSecurityCallback()])
llm.invoke("Hello, what is MCP?")

Tool decorator

from mcp_bastion_langchain import secure_tool

@secure_tool
def my_tool(query: str) -> str:
    return f"Result for {query}"

Features

• Content filtering on all LLM prompts and tool inputs
• 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).