How to Use the Equixly MCP in LlamaIndex

Q: How can I use LlamaIndex to find all past Equixly scans for a specific API?

First, use the listservices tool to get the ID for your target API. Then, create a query engine over an agent that uses the listscans tool, filtering by that service ID. This gives you a complete, queryable history.

Q: Can a LlamaIndex agent compare two Equixly scans to see if a vulnerability was fixed?

Yes. You'd have the agent run getscanfindings for both the old and new scan IDs. After indexing both sets of results, you can ask the query engine to identify vulnerabilities present in the first scan but absent in the second.

Q: What about the privacy of my API specifications when using Equixly with LlamaIndex?

Your API specifications, which you provide via uploadapispec, are handled within a zero-trust environment on Vinkius. Each tool call is processed in an isolated sandbox that is destroyed after execution. The raw spec content is used for the scan and then discarded.

Turn Equixly scan results into a searchable knowledge base with LlamaIndex and find security answers grounded in real data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Equixly MCP to LlamaIndex

Create your Vinkius account to connect Equixly 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 Equixly with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build a RAG App on Your Security Posture

Don't just run scans, learn from them. Use the McpToolSpec to wrap the Equixly tools. Your LlamaIndex agent can periodically call `list_services`, then iterate through them to run `list_scans` and `get_scan_findings` for each one. The real power comes next: index all those findings into a vector store. Now you can ask natural language questions like, "Have we ever had an IDOR vulnerability on the payments API?" and get answers based on actual historical scan data. This is how you build institutional knowledge.

Ground Your LlamaIndex Agent in Live Data

LlamaIndex agents can make decisions based on fresh data from your security tools. Before answering a question about a service's health, the agent can call `get_service` to check its configuration and `get_scan` on the latest run to see a summary. This prevents your RAG application from giving stale answers. When someone asks, "Is the new checkout API secure enough to deploy?", the agent can `trigger_scan` on the spot, wait, index the results from `get_scan_findings`, and then give an answer based on what Equixly found minutes ago.

Query API Specs with a LlamaIndex MCP Server

Your agent can use `list_api_specs` to fetch all the OpenAPI definitions you've uploaded for a service. By indexing this content, you create a queryable library of your API's structure over time. This lets you ask complex questions that cross-reference structure and security. For example: "Show me all endpoints that accept user IDs as path parameters and have had a BOLA vulnerability in the last 3 months." Your agent queries the indexed specs and the indexed findings from `get_scan_findings` to get the answer.

Setup guide

Set up Equixly 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 Equixly 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 Equixly tools.",
)
response = await agent.run("List recent Equixly 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 Equixly. 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 Equixly 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 Equixly MCP in LlamaIndex

First, use the `list_services` tool to get the ID for your target API. Then, create a query engine over an agent that uses the `list_scans` tool, filtering by that service ID. This gives you a complete, queryable history.

Yes. You'd have the agent run `get_scan_findings` for both the old and new scan IDs. After indexing both sets of results, you can ask the query engine to identify vulnerabilities present in the first scan but absent in the second.

The key difference is memory. LlamaIndex excels at building a searchable knowledge base from your Equixly scan data. This lets you ask complex, historical questions about your security posture that a simple agent couldn't answer.

Build a simple ingestion pipeline. Have an agent run on a schedule to call `list_services`, loop through them calling `list_scans`, and then fetch new results with `get_scan_findings` to update your vector index.

Your API specifications, which you provide via `upload_api_spec`, are handled within a zero-trust environment on Vinkius. Each tool call is processed in an isolated sandbox that is destroyed after execution. The raw spec content is used for the scan and then discarded.

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