Brightflag Connects to Claude, ChatGPT, and Any MCP-Compatible AI Workspace
According to the 2026 FTI Consulting and Relativity General Counsel Report, 87% of general counsel now report using AI within their teams, nearly double from a year ago. Claude, ChatGPT, legal-specific tools, all of it. The adoption is real.
The tools are remarkable. But they’re working in the dark, because the real intelligence in a legal department doesn’t live in a chat window or the internet. It lives in your systems of record.
Brightflag has been working on something that brings these two worlds together.
The technology behind the breakthrough
MCP — the Model Context Protocol — is the technology that makes this possible. Think of it as a universal plug for AI: instead of every tool needing a custom, fragile connection to every platform, MCP gives them a shared language. Build one MCP server, and any compatible AI can connect to your data instantly.
Brightflag is one of the first systems of record in legal to build on MCP. We believed it was going to become the standard for how AI connects to enterprise data and we built accordingly.
With legal professionals being amongst the most engaged users of general purpose AI, the industry is building toward the future we anticipated. Brightflag is already there.
Introducing Brightflag + MCP
Brightflag’s system of record for matters, vendors, and spend connects natively to Claude, ChatGPT, and any MCP-compatible AI workspace.
We are one of the first systems of record in legal to build on MCP. We built on it early because we knew it would become the standard for how AI connects to enterprise data.
What your team can do with it
The practical shift is straightforward. Questions that used to require pulling a report or navigating dashboards can be asked directly in the AI workspace your team already uses.
- A legal ops manager can ask which outside counsel firms are billing above their agreed rates across all active matters.
- A legal ops team heading into outside counsel review season can surface performance trends across the full portfolio before a single call is scheduled.
- A legal ops manager prepping a GC for a board meeting can pull a breakdown of legal spend by business unit, with variance against budget, in the same conversation.
- A team evaluating outside counsel can ask how different firms have been resourcing similar matters, which timekeepers are doing the work, and whether staffing patterns have shifted year over year.
The answers come from your actual Brightflag data, not estimates, not model-generated approximations.
Get connected safely and on your terms
But we know what the next question is. “If AI can access our Brightflag data, who controls what it can see?”
The answer is simple: the same people who always have.
Because MCP connects directly to the Brightflag system of record, it doesn’t create a new permission layer — it inherits the one you already have. Every role, every access restriction, every data boundary you’ve configured in Brightflag applies automatically in the AI workspace or agent.
This is what governed AI actually looks like. Not a new security model to configure and maintain — just your existing controls, extending naturally into every AI tool your team uses
Want to see what Brightflag + MCP can do your in-house legal team?
Join our webinar on August 4 at 12 PM ET where our Head of Community, Anna Richards, will be doing a walkthrough of what MCP is (and is not), why it fundamentally changes how your team works with AI, and what it actually looks like in practice.
Share:
