What features of CloudLex are available through this API?

The API provides access to: Cases/Matters (CRUD operations), Contacts/Clients (create and list), Documents (list by case), Tasks (list by case), Medical Records (list by case), Liens (list by case), Communications (list by case), and Expenses (list by case). You can search cases by keyword, filter by status and practice area, and view all cases for a specific client.

How do I get a CloudLex API key?

Log in to your CloudLex account at cloudlex.com, navigate to Settings → Integrations or API Settings, and generate an API key. The key gives you access to your firm's case data, client information, documents, medical records, and expenses. Contact CloudLex support if you don't see the API option in your account.

Can I create new cases and clients through the API?

Yes! You can create new cases with case name, client assignment, status, practice area, and incident date. You can also create new contacts with first name, last name, email, phone, and contact type (Client, Opposing Party, Witness, Medical Provider, Expert). Use `create_cloudlex_case` and `create_cloudlex_client` tools for these operations.

What types of contacts can I manage in CloudLex?

CloudLex supports multiple contact types essential for personal injury practice: Clients (injured parties), Opposing Parties (defendants, insurance adjusters), Witnesses (eyewitnesses, expert witnesses), Medical Providers (doctors, hospitals, physical therapists), and Experts (medical experts, accident reconstructionists, economists). Each contact type can be linked to specific cases and communications.

CloudLex Legal MCP Server for OpenAI Agents SDK 15 tools — connect in under 2 minutes

Name: CloudLex Legal
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 15 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect CloudLex Legal through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="CloudLex Legal Assistant",
            instructions=(
                "You help users interact with CloudLex Legal. "
                "You have access to 15 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from CloudLex Legal"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About CloudLex Legal MCP Server

Connect to CloudLex Legal case management platform and manage your entire personal injury practice from any AI agent. Access cases, clients, documents, medical records, liens, tasks, communications, and expenses—all through a unified API designed for plaintiff personal injury law firms.

The OpenAI Agents SDK auto-discovers all 15 tools from CloudLex Legal through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries CloudLex Legal, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Cases/Matters — List, search, create, and update personal injury cases with status, client, and practice area
Clients/Contacts — Manage your client database including individuals, opposing parties, witnesses, medical providers, and experts
Client Portfolio — View all cases associated with a specific client
Documents — Access case documents including pleadings, correspondence, evidence, and settlement documents
Tasks — View and manage tasks associated with cases including due dates and assigned attorneys
Medical Records — Access medical treatment records, bills, provider information, and medical summaries
Liens — Track medical liens, insurance liens, and other claims against settlements
Communications — View emails, phone calls, letters, and notes with clients, opposing counsel, and other parties
Expenses — Track case-related expenses including court costs, expert witness fees, and medical record retrieval costs

The CloudLex Legal MCP Server exposes 15 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect CloudLex Legal to OpenAI Agents SDK via MCP

Follow these steps to integrate the CloudLex Legal MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 15 tools from CloudLex Legal

Why Use OpenAI Agents SDK with the CloudLex Legal MCP Server

OpenAI Agents SDK provides unique advantages when paired with CloudLex Legal through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

CloudLex Legal + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the CloudLex Legal MCP Server delivers measurable value.

Automated workflows: build agents that query CloudLex Legal, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries CloudLex Legal, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through CloudLex Legal tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query CloudLex Legal to resolve tickets, look up records, and update statuses without human intervention

CloudLex Legal MCP Tools for OpenAI Agents SDK (15)

These 15 tools become available when you connect CloudLex Legal to OpenAI Agents SDK via MCP:

create_cloudlex_case

USE WHEN: - User wants to open a new legal case - User needs to create a new matter for a client - User asks to "create a new case" or "open a matter" PARAMETERS: - case_name (REQUIRED): Case/matter name - client_id (OPTIONAL): ID of the client this case belongs to - status (OPTIONAL): Initial status — "Open" (default), "Closed", "Pending", "Settled" - practice_area (OPTIONAL): Practice area (e.g. "Personal Injury", "Mass Tort", "Auto Accident") - description (OPTIONAL): Case description/notes - incident_date (OPTIONAL): Date of the incident (YYYY-MM-DD) EXAMPLES: - "Create a new case called 'Smith Auto Accident'" → call with case_name="Smith Auto Accident" - "Open a new personal injury matter for client 456" → call with case_name="State v. Johnson", client_id="456", practice_area="Personal Injury" Create a new case/matter in CloudLex Legal

create_cloudlex_client

USE WHEN: - User wants to add a new client - User needs to create a new contact record - User asks to "add a new client" or "create a contact" PARAMETERS: - first_name (REQUIRED): Client's first name - last_name (REQUIRED): Client's last name - email (OPTIONAL): Client's email address - phone (OPTIONAL): Client's phone number - type (OPTIONAL): Contact type — "Client" (default), "Opposing Party", "Witness", "Medical Provider", "Expert" EXAMPLES: - "Add a new client John Smith" → call with first_name="John", last_name="Smith" - "Create contact for opposing party Jane Doe, jane@example.com" → call with first_name="Jane", last_name="Doe", email="jane@example.com", type="Opposing Party" Create a new client/contact in CloudLex Legal

get_client_cloudlex_cases

Useful for understanding a client's full legal portfolio and case history. Get all cases/matters for a specific client/contact

get_cloudlex_case

Get detailed information for a specific case/matter

get_cloudlex_client

Get detailed information for a specific client/contact

list_cloudlex_cases

Supports filtering by status, practice area, client, and date range for flexible queries. USE WHEN: - User wants to see all their legal cases/matters - User needs to find cases by status, client, or practice area - User is exploring their law firm's caseload - User asks "what cases do I have" or "list my open cases" PARAMETERS: - status (OPTIONAL): Filter by case status (e.g. "Open", "Closed", "Pending", "Settled") - practice_area (OPTIONAL): Filter by practice area (e.g. "Personal Injury", "Mass Tort", "Auto Accident") - client_id (OPTIONAL): Filter by specific client ID - page (OPTIONAL): Page number for pagination - page_size (OPTIONAL): Results per page (default: 25, max: 100) EXAMPLES: - "List all my open cases" → call with status="Open" - "Show my personal injury matters" → call with practice_area="Personal Injury" - "List all cases" → call with no params List all cases/matters in CloudLex Legal

list_cloudlex_clients

USE WHEN: - User wants to see all their clients and contacts - User needs to find a client by name or email - User is exploring their contact database - User asks "list my clients" or "show all contacts" PARAMETERS: - page (OPTIONAL): Page number for pagination - page_size (OPTIONAL): Results per page (default: 25, max: 100) EXAMPLES: - "List all my clients" → call with no params - "Show my contacts" → call with no params - "List clients page 2" → call with page="2" List all clients/contacts in CloudLex Legal

list_cloudlex_communications

List communications for a specific case

list_cloudlex_documents

List documents for a specific case/matter

list_cloudlex_expenses

List expenses for a specific case

list_cloudlex_liens

List liens for a specific case

list_cloudlex_medical_records

List medical records for a specific case

list_cloudlex_tasks

List tasks for a specific case/matter

search_cloudlex_cases

Search cases/matters by keyword query

update_cloudlex_case

Update an existing case/matter in CloudLex Legal

Example Prompts for CloudLex Legal in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with CloudLex Legal immediately.

"List all my open personal injury cases in CloudLex."

"Show me all medical records for the Smith Auto Accident case."

"Create a new case for client John Smith called 'Smith v. ABC Corporation - Workplace Injury'."

Troubleshooting CloudLex Legal MCP Server with OpenAI Agents SDK

Common issues when connecting CloudLex Legal to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

CloudLex Legal + OpenAI Agents SDK FAQ

Common questions about integrating CloudLex Legal MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.