Bring Court Records
to OpenAI Agents SDK
Learn how to connect UniCourt to OpenAI Agents SDK and start using 27 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
GDPR Free for SubscribersCompatible with every major AI agent and IDE
Gemini
What is the UniCourt MCP Server?
Connect your UniCourt account to any AI agent to streamline legal research and litigation tracking through natural language.
What you can do
- Case Search — Search across millions of court cases using keyword expressions and filters
- Automated Tracking — Use
track_caseto monitor specific litigation and receive updates on a schedule - Normalized Data — Access structured profiles for attorneys, law firms, judges, and parties to perform deep background checks
- Document Management — Order court documents and export case data directly into your workflow
- Legal Analytics — Retrieve case counts and analytics to understand litigation trends
How it works
- Subscribe to this server
- Enter your UniCourt Access Token
- Start querying legal records from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Legal Professionals — automate case monitoring and perform quick conflict checks
- Researchers — gather large-scale litigation data for market analysis
- Insurance & Finance — assess legal risks by inspecting party histories and active court cases
Built-in capabilities (27)
Delete PACER account credentials
Generate a new UniCourt access token
Get details for a specific case
Get case count analytics by case type
Get the file URL for a completed case export
Check the status of a requested case update
Get the file URL for a completed document order
Get analytics and details for a normalized attorney
Get analytics and details for a normalized judge
Get analytics and details for a normalized law firm
Get analytics and details for a normalized party
Retrieve current PACER account credentials status
High-priority case import
Import a case not in UniCourt via PACER
Order a court document
Request an export of case data as a ZIP file
Request an asynchronous update for a case
g., caseName:pfizer). Search for court cases
Search for normalized attorneys
Search for normalized judges
Search for normalized law firms
Search for normalized parties
Search PACER directly via Case Locator
Automatically update cases on a schedule
Schedule recurring bar source refreshes for an attorney
Schedule recurring source refreshes for a law firm
Manage PACER account credentials
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 27 tools from UniCourt through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries UniCourt, another analyzes results, and a third generates reports, all orchestrated through Vinkius.
- —
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
UniCourt in OpenAI Agents SDK
UniCourt and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect UniCourt to OpenAI Agents SDK through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for UniCourt in OpenAI Agents SDK
The UniCourt 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. All 27 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in OpenAI Agents SDK only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* 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
How Vinkius secures
UniCourt for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the UniCourt MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How can I search for court cases involving a specific company?
Use the search_cases tool with a query like caseName:"Company Name". The agent will return a list of matching cases with their UniCourt IDs and basic details.
Can the AI automatically track a case for new updates?
Yes! By using the track_case tool with a specific caseId, you can set up automated monitoring. You can even specify a refreshWindow like '1d' for daily updates.
Is it possible to get professional background data for an attorney?
Absolutely. Use search_norm_attorney to find the attorney and then get_norm_attorney with their ID to retrieve detailed analytics and professional history.
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.
Can I use multiple MCP servers in one agent?
Yes. Pass a list of MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.
Does the SDK support streaming responses?
Yes. The SDK supports SSE and Streamable HTTP transports, both of which work natively with Vinkius.
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.
Explore More MCP Servers
View all →
LinearB
7 toolsExport software delivery metrics, manage deployments, and report incidents via the LinearB API.
Plunk Email Marketing
8 toolsAutomate your email marketing via Plunk — send transactional emails, track events, and manage contacts.
Random Facts API
2 toolsAccess thousands of interesting facts — audit random data via AI.
Daily.co
50 toolsManage video calls and WebRTC infrastructure via Daily.co — create rooms, track participants, and control meeting sessions directly from your AI.