Docket Alarm MCP. Access 732M+ Legal Records from Chat.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Docket Alarm connects your AI agent to 732 million legal records and court filings across PACER and state courts. Use specific tools like `get_docket` to pull full case dockets, or run `smart_search` to convert natural language questions into complex boolean searches.
Extract judgments with `extract_judgment`, summarize complaints using `get_complaint_summary`, and set up automated alerts for new activity on any docket using `track_case`.
Stop manually checking court websites.
What your AI agents can do
Ask docket
Answers natural language questions about a specific court docket record.
Extract judgment
Pulls out final judgments and outcomes from legal case filings.
Get cause of action
Identifies the primary causes of action and relevant statutes cited in a complaint.
Query the massive Docket Alarm database using complex boolean searches via the search tool.
Directly search federal court records through the search_pacer tool, which fetches live litigation data.
Retrieve a complete, up-to-date list of all filings and events for a specific case using get_docket.
Extract detailed summaries of initial complaints or analyze complex documents with tools like get_complaint_summary.
Determine the primary causes of action and relevant legal statutes using the get_cause_of_action tool.
Set up automated alerts for new filings or activity on a case docket using the track_case function.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Docket Alarm: 13 Tools for Litigation Research
These tools allow you to query vast databases of court filings, extract specific case data points, monitor dockets, and summarize complex legal documents.
019ea5e7ask docket
Answers natural language questions about a specific court docket record.
019ea5e7extract judgment
Pulls out final judgments and outcomes from legal case filings.
019ea5e7get cause of action
Identifies the primary causes of action and relevant statutes cited in a complaint.
019ea5e7get complaint summary
Extracts detailed short or long summaries from initial complaints filed in court.
019ea5e7get docket
Retrieves the full, live docket history for a specified case number from the court system.
019ea5e7get search direct args
Lists and retrieves required arguments needed to perform a direct search on state or agency courts.
019ea5e7list search direct courts
Provides a list of all supported state and agency courts for direct searching.
019ea5e7match case
Finds specific cases using partial or limited identifying information (like names or dates).
019ea5e7search
Runs general boolean searches across the entire Docket Alarm database of records.
019ea5e7search direct
Searches state and agency court dockets directly using specific parameters.
019ea5e7search pacer
Directly searches federal PACER/court records, incurring a fee per page of results.
019ea5e7smart search
Generates complex and accurate search queries from simple natural language instructions.
019ea5e7track case
Sets up automated monitoring alerts for new activity on a specific case docket.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Docket Alarm, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
Docket Alarm connects your AI agent straight into 732 million legal records and court filings from PACER and state courts. You're done manually checking dusty court websites; you just tell your agent what you need, and it pulls the data.
Searching Records:
To start digging, you can run a general boolean search across the entire Docket Alarm database using search. If you need to query federal court filings live, use search_pacer, which fetches current litigation data (just remember that's billed per page of results). For specialized state or agency courts, first check out list_search_direct_courts to see what systems are supported.
Then, grab the required arguments you need using get_search_direct_args before executing a direct search via search_direct. If you're just trying to locate a specific case—maybe you only have names or dates—you can use match_case to pinpoint records. For complex research questions that are worded naturally, let smart_search convert those simple instructions into accurate, detailed boolean queries.
Getting Full Docket History:
You need the full story on a case? Run get_docket; this retrieves a complete, live history of every filing and event tied to a specific case number directly from the court system. You can also use get_search_direct_args to list required arguments for direct searches.
Analyzing Legal Filings:
Don't waste time reading thousands of pages of legalese. Extracting key information is what you want. Use get_complaint_summary to pull detailed short or long summaries from the initial complaints filed in court. Want to know what the final word was? Run extract_judgment; this tool isolates the final outcomes and judgments from legal filings.
If you're reviewing a specific case file, ask_docket lets your agent answer natural language questions about that particular docket record. To figure out the core legal issues, use get_cause_of_action, which identifies the primary causes of action and all relevant statutes cited in a complaint.
Monitoring Cases:
Don't wait for stale updates. You can set up automated alerts using track_case. This function monitors a specific case docket and lets you know immediately when new activity or filings drop on that record.
How Docket Alarm MCP Works
- 1 First, tell your AI agent what kind of information you need. Do you need to find cases by partial info? Use the
match_casetool. - 2 Next, if it's a federal case, use
search_pacer. If it's state/agency level, runget_search_direct_argsfirst to get required parameters forsearch_direct. - 3 Finally, feed the resulting docket number into
get_docketorask_docketso your agent can pull the full history and answer specific questions about it.
The bottom line is that you move from a vague legal question to actionable, structured data points without leaving your AI client environment.
Who Is Docket Alarm MCP For?
This server serves litigators and corporate counsel who are tired of spending hours manually navigating jurisdictional court websites. It's for the legal researcher needing deep-dive boolean searches across millions of records, or the attorney who needs to synthesize a quick narrative from complex dockets.
Tracks opposing counsel’s filings across multiple courts and uses get_docket to build timelines for depositions.
Performs complex searches using the search tool or runs smart_search on vague criteria to nail down relevant case law quickly.
Monitors litigation trends and uses track_case to receive real-time alerts on cases that might affect the company.
What Changes When You Connect
- Stop reading filings cover-to-cover. Use
get_complaint_summaryto pull instant, deep summaries of complaints, saving hours of manual document review. - Pinpoint case details instantly. The
ask_dockettool lets you ask natural language questions about a docket—no need for legal jargon or database syntax. - Cover every jurisdiction. Use the dedicated tools (
get_search_direct_args,list_search_direct_courts) to handle specialized state and agency courts that standard searches miss. - Automate monitoring. Instead of checking court websites daily, use
track_caseto set up alerts. Your agent tells you immediately when a relevant filing drops. - Improve search accuracy. Don't just run
search. Usesmart_searchfirst; it converts your vague questions into precise boolean query language for better results.
Real-World Use Cases
Need to track an opposing counsel’s filing schedule.
The paralegal needs to know if the opposition filed a motion last week. Instead of checking the court website, they run get_docket with the case number. The agent pulls the full history and reports back: 'Motion filed on Tuesday.' This is faster than any manual check.
Unsure how to search a specialized state court.
The attorney needs records from a specific county agency but doesn't know the required parameters. They first call list_search_direct_courts and then use get_search_direct_args to get the exact structure needed, finally running search_direct for clean results.
Need a quick overview of complex case law.
The corporate counsel gets a new docket number and needs context immediately. They run get_complaint_summary to get the core allegations, then use get_cause_of_action to see what statutes were cited. This provides instant risk assessment.
Searching across multiple jurisdictions for precedents.
The researcher needs case law involving '3M' in different districts. They run a broad search query, but then refine it by calling match_case to filter the results down to only those with specific filing dates or parties.
The Tradeoffs
Running simple 'Search' queries.
The user just runs search('3M'). This returns thousands of unfiltered, irrelevant results because the query lacks specific date ranges or court limitations.
→
Don’t run a broad search. First, use match_case to narrow down records by partial info like '3M' AND 'District of Delaware'. Then, use that result set with get_docket for focused data.
Asking the agent everything at once.
The user prompts: 'Find all things about 3M and tell me the judgment.' The agent gets confused or only runs a general search, missing structured data points.
→
Use a multi-step workflow. First, match_case to find the case ID. Second, run get_docket using that ID. Finally, use extract_judgment on the resulting docket structure.
Assuming PACER data is always free.
The user expects a simple search query and gets frustrated when they realize there's an additional fee for accessing federal records via search_pacer.
→
Always remember that search_pacer incurs a $0.10 fee per page of results unless you are running a test query.
When It Fits, When It Doesn't
Use this server if your research requires querying official court filings (PACER, state/agency dockets) and synthesizing data from millions of records. You need to know what happened in the case, not just that it exists.
Don't use this if you simply need general legal definitions or quick summaries from public law articles—a standard search engine works better. Also, don't run search_pacer unless you understand its fee structure. If your query is highly specific and technical (e.g., 'What were the arguments in a motion filed on X date?'), use that tool directly rather than relying on a general smart_search.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Docket Alarm. 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.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 13 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Manually checking court websites for updates is a time sink.
Right now, tracking a case means logging into the PACER portal, searching by docket number, and manually clicking through dozens of pages. You copy dates, cross-reference filing types (motion vs. order), and try to determine if the new document is critical—all while juggling multiple tabs and fighting website load times.
With this MCP server, you just give your agent the case ID. It uses `get_docket` and pulls the full history instantly. You get a clean, structured list of every filing, letting you see exactly what changed without leaving your chat interface.
Docket Alarm MCP Server: Getting actionable legal insight.
Before this server, summarizing a complaint meant reading through pages of dense legalese and manually cross-referencing the primary statute. If you needed to know if there was an outcome, you were left hoping the last few filings contained enough information.
Now, run `get_complaint_summary` or `extract_judgment`. Your agent handles the analysis, giving you a clean summary of allegations and outcomes right away. It’s that simple.
Common Questions About Docket Alarm MCP
How do I search for cases using vague criteria with smart_search? +
The smart_search tool converts your plain language into a complex query. Just ask it: 'Find all copyright suits involving 3M in California.' It builds the necessary boolean logic for you.
Is `get_docket` better than `search`? +
get_docket is better because you feed it a specific, known docket number and get its full history. The general search tool requires much more input to narrow down records.
Can I set up an alert for new filings? Use track_case. +
Yes, the track_case function lets you monitor a case docket automatically. You tell it the ID and the event type, and your agent sends you an alert when activity is logged.
What's the difference between `search_pacer` and `search_direct`? +
search_pacer targets federal PACER records (and has a fee). search_direct handles state or agency courts, which require you to first use list_search_direct_courts.
If I have a massive legal document, how do I summarize it using `get_complaint_summary`? +
It generates a concise overview of the complaint's core allegations. You just pass the docket ID to your agent; it returns a summary that cuts through the jargon and gives you the main claims.
Before I run `search_direct`, how do I know which state courts are supported by the server? +
You need to use the list_search_direct_courts tool. This runs immediately and provides a definitive list of all the state and agency court identifiers you can target for your research.
What arguments must I provide when using `get_search_direct_args`? +
Running get_search_direct_args first tells you the exact parameters. This confirms which fields—like judge name or case type—you need to include for a successful direct court search.
I only have partial information, not a docket number. Can I still find the case using `match_case`? +
Yes, that's exactly what match_case does. You input details—like names and dates—and it searches records to locate potential docket matches across various jurisdictions.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Metabase (Business Intelligence & Analytics)
Manage your BI environment via Metabase — list dashboards, retrieve visual questions (cards), and search data entities.
Currents
Access real-time global news and search millions of articles directly from your AI agent using the Currents API.
Legal Fees Apportionment Engine
Split judicial awards and attorney fees across multiple parties with exact, auditable proportional math.
You might also like
Greenhouse Alternative
Manage your recruiting pipeline via Greenhouse — list applications, track candidate activity, and manage job board posts directly from any AI agent.
BILL (Bill.com)
Manage financial operations via BILL — list vendors, customers, bills, and invoices directly from any AI agent.
ECB Monetary — Money Supply, Yield Curves & Banknotes
Eurozone monetary data: M1, M2, and M3 money supply aggregates, government bond yield curves from 3 months to 30 years, full yield curve snapshots, and euro banknotes in circulation statistics from the European Central Bank.