Model Context Protocol (MCP) Server

We are developing an MCP server that will enable AI assistants to access CourtListener's legal data.

Coming Soon: This feature is currently in development. The information on this page describes our planned implementation and may change as development progresses.

The Model Context Protocol (MCP) server will allow AI tools like Claude, ChatGPT, and other large language models to seamlessly access CourtListener's extensive legal databases. This will enable AI assistants to provide more accurate and comprehensive answers to legal research questions by giving them direct access to case law, PACER data, judge information, and more.

What is the Model Context Protocol?

The Model Context Protocol is an open standard that allows AI applications to connect to external data sources and tools. Instead of relying solely on their training data, AI assistants using MCP can query live databases and APIs to retrieve current, accurate information.

When you use an AI assistant that has CourtListener's MCP server installed, the assistant will be able to:

Search for case law across hundreds of jurisdictions
Look up specific court opinions by citation
Access PACER docket information from the RECAP Archive
Find judge profiles and their authored opinions
Retrieve oral argument recordings and transcripts

Planned Features

Our MCP server will provide tools that map to CourtListener's comprehensive REST APIs, giving AI assistants the same powerful search and data access capabilities available to developers.

We want to build an MCP server that meets your needs. If you have ideas for features, use cases, or specific tools you would like to see, please share them in our GitHub discussion. You can also vote on existing suggestions to help us prioritize development. The MCP server and its underlying Python SDK are being developed at courtlistener-api-client.

Search Tools

AI assistants will be able to perform sophisticated searches across our databases:

Case Law Search: Search millions of court opinions using keywords, citations, dates, courts, and judges. Supports the same advanced query syntax available on the website.
RECAP Search: Search federal court dockets and filings from our RECAP Archive, which contains millions of PACER documents.
Citation Lookup: Look up cases by their legal citation using our Citation Lookup API.
Oral Arguments: Search oral argument recordings and transcripts from appellate courts.

Data Access

Beyond search, AI assistants will be able to retrieve detailed information about specific items:

Opinion Details: Full text of court opinions, metadata, and citation information.
Docket Information: Complete docket sheets including all filings and parties.
Judge Profiles: Biographical information about judges, their positions, and authored opinions.
Court Information: Details about courts, their jurisdictions, and coverage in our database.

Getting Started

When the MCP server launches, you will be able to install it in compatible AI applications. The installation process will vary depending on the AI tool you use.

For local MCP servers (like those used with Claude Desktop), installation will involve adding a configuration to your AI application that references the CourtListener MCP package:

{
  "mcpServers": {
    "courtlistener": {
      "command": "uvx",
      "args": ["--from", "courtlistener", "courtlistener-mcp"],
      "env": {
        "COURTLISTENER_API_TOKEN": "your-api-token"
      }
    }
  }
}

Note: This configuration is subject to change. Final installation instructions will be provided when the MCP server is released.

Authentication

The MCP server will use CourtListener API tokens for authentication. This means:

You will need a CourtListener API account to use the MCP server.
Your existing API token will work with the MCP server.
API rate limits and usage policies will apply to MCP requests just as they do to direct API calls.
Organizations with commercial API agreements can use MCP under the same terms.

If you do not yet have a CourtListener account, you can create one for free. API tokens are available in your profile settings after registration.

Stay Informed

We will announce the MCP server launch through our usual channels:

The Free Law Project blog
Our Bluesky account
The Free Law Project announcement mailing list

If you have questions about the MCP server or would like to be notified when it launches, please contact us.

Please Support Open Legal Data

These services are sponsored by Free Law Project and users like you. We provide these services in furtherance of our mission to make the legal sector more innovative and equitable.

We have provided these services for over a decade, and we need your contributions to continue curating and enhancing them.

Will you support us today by becoming a member?

Join FLP

Back to Help