How to Use the Beagle Security MCP in LlamaIndex

Q: How can LlamaIndex index data from Beagle Security?

You configure a LlamaIndex agent to call gettestresult, and then you pipe that JSON output into your normal indexing workflow. The MCP Server provides the tools to get the data; LlamaIndex handles embedding and storing it.

Q: What's the process for a LlamaIndex agent to start a new Beagle Security scan?

Your agent simply calls the starttest tool, specifying the application ID. You can design your RAG system to trigger this automatically if it can't find recent-enough data in its existing index to answer a user's query.

Turn your Beagle Security scan data into a queryable knowledge base with LlamaIndex.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Beagle Security MCP to LlamaIndex

Create your Vinkius account to connect Beagle Security to LlamaIndex and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Beagle Security with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Your Security Findings

This MCP toolset connects Beagle Security directly to your LlamaIndex data pipelines. When your agent calls `get_test_result`, the raw JSON of vulnerabilities and findings can be automatically chunked, embedded, and indexed into a vector store. Instead of just getting a one-off report, you're building a historical record. Your agents can now perform semantic searches across all past security scans. Ask questions like 'Show me all SQL injection vulnerabilities from Q2' and get answers grounded in actual test data from this MCP Server.

Augment Queries with Live Data

LlamaIndex agents can use these tools for Retrieval-Augmented Generation (RAG). When you ask a question about your security posture, the agent can first `list_applications` to get current context, then query its indexed knowledge base of past `get_test_result` outputs. This combines real-time awareness with historical depth. Your agent isn't just hallucinating; it's synthesizing information from past scans and current application states to give you a complete picture. It can even `start_test` on an app if it finds no recent data in its index.

Build a Security Research Agent with LlamaIndex

Don't just ask questions—get your agent to perform research. You can build a LlamaIndex agent that's tasked with investigating a potential threat. It can start by listing current `get_running_tests` to avoid duplication. If no relevant test is active, it can `start_test` on the target application, wait for completion by checking `get_test_status`, and then analyze the `get_test_result` to form its conclusion. The entire process becomes a dynamic RAG pipeline powered by these MCP tools.

Setup guide

Set up Beagle Security MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Beagle Security MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Beagle Security tools.",
)
response = await agent.run("List recent Beagle Security data")

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Beagle Security. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Beagle Security now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Beagle Security MCP in LlamaIndex

You configure a LlamaIndex agent to call `get_test_result`, and then you pipe that JSON output into your normal indexing workflow. The MCP Server provides the tools to get the data; LlamaIndex handles embedding and storing it.

Yes, that's the core idea. Once your past test results are indexed, you can ask natural language questions about them. For instance, 'What were the most common vulnerabilities in the checkout app last year?'

Your agent simply calls the `start_test` tool, specifying the application ID. You can design your RAG system to trigger this automatically if it can't find recent-enough data in its existing index to answer a user's query.

Yes. This server is completely agnostic to your data layer. It just provides the tools for LlamaIndex to get data. You can index that data into Pinecone, Weaviate, Chroma, or any other vector store LlamaIndex supports.

The server handles your application names, project IDs, and the JSON data from your test results. Each connection is isolated and authenticated with a unique token. The server itself is ephemeral, meaning none of your Beagle Security data persists here.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript