How to Use the Equixly MCP in LangChain

Q: How do I make a LangChain agent trigger a scan on a new API with Equixly?

Your agent needs to call the tools in sequence. First, use createservice with the API's name and base URL. Then, use the returned service ID with uploadapispec and triggerscan to start the pentest.

Q: Can I build a LangChain agent that only reports on critical vulnerabilities from an Equixly scan?

Yes. After a scan completes, have your agent call getscanfindings. You can then add logic within your chain to filter the results, only processing findings where the severity is 'critical'.

Build security automation chains for LangChain that find and report API vulnerabilities before they hit production.

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 LangChain

Create your Vinkius account to connect Equixly to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Scans into Your CI/CD Pipeline

Connect your CI/CD process directly to Equixly. Your agent can use `list_services` to find the right API, `upload_api_spec` with the latest OpenAPI definition from your build, and then immediately call `trigger_scan`. It's a straight line from code commit to security scan. The agent doesn't just fire and forget. It can poll the `get_scan` tool until the status is 'completed'. If `get_scan_findings` returns any critical issues, the agent can fail the build or open a Jira ticket. You build the logic, the agent executes it.

Automate Vulnerability Triage with LangChain

Stop manually digging through scan reports. Create a ReAct agent that pulls results using `get_scan_findings`, then categorizes each vulnerability. Is it a BOLA issue? An IDOR? The agent can reason about the findings. From there, the chain can route the issue. High-severity findings from a production service (identified via `get_service`) might trigger a PagerDuty alert. Low-severity findings can be logged to a Slack channel. You're building an automated security analyst.

Manage Your Attack Surface with this MCP Server

Your infrastructure changes, and your security posture needs to keep up. Use an agent to periodically sync your service registry with Equixly. The agent can `list_services` and compare that against your internal records. If a new service is found, the agent can automatically run `create_service` to register it. If a service is decommissioned, it calls `delete_service` to clean up. This MCP approach keeps your automated pentesting perfectly aligned with your actual deployed APIs.

Setup guide

Set up Equixly MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Equixly tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "equixly-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Equixly transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Your agent needs to call the tools in sequence. First, use `create_service` with the API's name and base URL. Then, use the returned service ID with `upload_api_spec` and `trigger_scan` to start the pentest.

Yes. After a scan completes, have your agent call `get_scan_findings`. You can then add logic within your chain to filter the results, only processing findings where the `severity` is 'critical'.

The most direct way is to create an agent that runs on every deployment. It should use `upload_api_spec` to provide the latest API definition and `trigger_scan`. Your agent can then use `get_scan_findings` to decide whether to pass or fail the pipeline stage based on the vulnerabilities found.

LangSmith gives you a full trace of the agent's execution. You can see the exact inputs and outputs for every tool call, like the spec content sent to `upload_api_spec` or the JSON returned by `get_scan_findings`. This makes debugging your security automation chains much faster.

The server processes API specifications you upload and the detailed scan findings it generates. Vinkius ensures this data is isolated in an ephemeral sandbox for each request. Your API specs and vulnerability reports are never stored long-term or mixed with other users' data.

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