Law Firms Face a Critical Choice on AI Connectivity
Most law firms now run multiple generative AI tools in production. Harvey, Legora, iManage, and NetDocuments are all pushing forward with new capabilities. But beneath the announcements, a fundamental problem remains unsolved: the AI can't actually connect to the systems where legal work happens.
The Model Context Protocol (MCP) is designed to fix that. Whether firms engage with it deliberately or react later has become a real strategic question.
Two gaps are holding back AI progress
The first is the context gap. An AI tool can summarize a document or draft a clause, but it often can't see the precedents, correspondence, or deal-specific instructions sitting elsewhere in the firm's systems. Lawyers spend time pulling that context together by hand.
The second is the action gap. Even when AI produces something useful, it usually can't act on it where the work actually happens. It can draft a status update but not post it into the deal room. It can flag a missing condition but not update the closing checklist. The lawyer becomes the messenger.
These two gaps explain why many AI pilots stall at "useful, but not transformative." The model isn't the bottleneck. The connectivity is.
What MCP actually does
MCP is an open standard that lets AI applications connect to other systems through a common interface. Think of it as HTTP for AI-to-system integration. Instead of every AI tool needing a custom integration with every legal system, everyone connects to the same standard.
An MCP server makes a system's data and actions available in a standardized way. An MCP client is an AI application that uses what those servers expose. A firm with an MCP-enabled document management system can plug it into any MCP-enabled AI tool.
The legal stack is now starting to enable this. iManage launched its MCP server on May 14. NetDocuments is following. Harvey and Legora are building workflows that depend on exactly this kind of connectivity. Vendors without it will soon face hard questions from their largest customers.
Five concrete use cases
Document and matter context: Pull the full matter picture into the AI session, not just the document on screen, so summaries and drafting are grounded in the actual deal.
Transaction management and cross-party coordination: Let AI assistants see live status across deals, write back updates, and surface bottlenecks without lawyers translating between systems.
Due diligence and data room: Connect AI directly to the data room and review platform so issues flow into the report and the report flows back into the workstream.
Knowledge and precedent: Make firm precedents and prior advice available to the AI in a structured way so drafting starts from the firm's best work rather than a generic template.
Client reporting: Pull status, financials, and key risks together into a client-facing update without the partner compiling them manually.
None of these are theoretical. All depend on the AI being able to read from and write to the systems where the work actually lives. None work at scale through copy and paste.
The decision in front of firms
There is a temptation to treat MCP as IT plumbing-interesting to technical teams, irrelevant to strategy. That view is becoming harder to defend.
MCP is now a procurement question. The systems a firm buys, renews, and decommissions over the next 18 months will either be MCP-enabled or they won't. The AI tools put in front of lawyers will either be able to act across the stack or they won't.
It is also a positioning question. Firms that move deliberately on MCP-identifying their first high-value integration, taking a view on vendor support, and briefing partners on what changes when the AI can actually do the work-will be the ones using AI credibly in front of clients in 18 months. Firms that don't will still have AI. It just won't have access to anything that matters.
The question for most firms isn't whether to take MCP seriously. It's whether to do so now, while the market is still forming, or later, after others have set the pace.
For more on how MCP applies to legal work, see MCP Courses and AI for Legal.
Your membership also unlocks:
