The Legatics MCP (Model Context Protocol) server connects AI assistants directly to your live Legatics data. Instead of an AI assistant working from general knowledge alone, the MCP server gives it accurate, real-time context from your matters, lists, and transactions.
Note: The MCP server is included for all Legatics customers at no additional cost.
Overview
What MCP is
MCP stands for Model Context Protocol. It is an emerging standard, introduced by Anthropic, that defines how AI language models connect to external data sources and tools. The protocol is now widely supported across the AI industry.
In practical terms, MCP is the mechanism by which an AI assistant can ask Legatics a question e.g. "what's the current status of the conditions list on this matter?" and receive a live, accurate answer, rather than relying on information it was trained on or that you've pasted into a prompt.
How it works
When an AI assistant is connected to the Legatics MCP server, it can query your Legatics data in real time during a conversation. The flow works like this:
You ask your AI assistant a question about a transaction or matter
The assistant recognises that it needs live Legatics data to answer
It queries the Legatics MCP server using your authorised credentials
The MCP server returns the relevant data from your Legatics environment
The assistant uses that data to form its response
Access is controlled through connected apps and OAuth 2.0, the same authorisation model used by the Legatics API. Your system admin controls which AI tools are authorised to query Legatics data, and what data they can access.
What the MCP server enables
The MCP server can read your Legatics data and, where the connected app allows it, write to it too:
Reads: answer questions, summarise the state of a transaction, and flag outstanding items or conditions
Writes: update statuses and owners, add rows or parties, create lists, and mark documents for signing
Note: Write access is optional. System admins control it through scopes, and can add the read_only scope to keep a connected app read-only regardless of its other scopes.
Setting up the MCP connection
Setting up the MCP connection involves a few different people at your firm. Work through the steps below in order.
1. Check the prerequisites
Who: IT/developer
Your AI tool supports MCP and you have an AI tool admin who can add connectors or integrations to it
You have a system admin in Legatics who can create connected apps
You know your MCP URL. Read Finding your Legatics API and MCP URLs
2. Allowlist the Legatics authentication address
Who: IT/developer
Make sure api.app.legatics.com is allowlisted on your firm's network and by your AI provider. This is the address Legatics uses for authentication, so the connection can't complete if it's blocked.
3. Get the redirect URL from your AI tool
Who: AI tool admin
Your AI tool provides a redirect (callback) URL when you add a new MCP connector. Copy it and send it to your system admin. Legatics enforces an exact match, so copy it exactly.
4. Create the connected app
Who: System admin
Create a connected app in the Administration System using the redirect URL from step 3. Select the legatics_mcp scope, plus any other scopes the AI tool needs, and choose Public client only if your AI tool requires it. Read Create and manage connected apps.
5. Configure the AI tool
Who: AI tool admin or IT/developer
Enter the MCP URL, client ID and, if issued, client secret into the AI tool. Treat the client secret like a password: it's only needed by the person configuring the AI tool, not by members. For tool-specific steps, read Claude, Harvey or Legora.
6. Sign in
Who: Member
Each member connects from within the AI tool and signs in with their Legatics credentials to authorise access to their data. Read Using AI assistants with Legatics.
7. Test the connection
Who: Member
Ask the AI assistant a simple question about a matter you have access to, for example "Summarise the current status of [matter name]." If it can't connect, follow the troubleshooting checklist in Using AI assistants with Legatics.
Security
How access is controlled
The MCP server uses the same access model as the Legatics API. All connections are:
Authorised through a connected app created by a system admin
Governed by a three-layer permission model: the connected app's scopes, the member's own consent (they can narrow but never widen what the app requested), and the member's existing Legatics permissions
Protected by short-lived OAuth 2.0 tokens
Revocable at any time from the Administration System
The AI assistant does not store your Legatics data. An AI assistant can never do more in Legatics than the member could do themselves.
Note: The behaviour of the AI assistant with respect to data retention is governed by the AI tool's own privacy policy, not Legatics. Check with your AI provider if you have data retention requirements.
User permissions are always enforced
The MCP server respects your existing Legatics permissions in full. It can only ever return or change data that the authenticated member is already permitted to see and edit within Legatics.
If a member does not have access to a matter, list, or document in Legatics, the MCP server will not return or change that data for the AI assistant, regardless of how the question is phrased. Connecting an AI tool does not grant any elevated or additional access beyond what the member already has.
Note: User permissions are enforced automatically. There is no additional configuration required to restrict what the AI assistant can see or change, it inherits the same access controls as the member it is acting on behalf of.
Supported AI tools
The MCP server can be used with any AI tool that supports the Model Context Protocol. This includes Harvey, Copilot, Claude, and other MCP-compatible AI assistants.
Tip: If you're not sure whether your firm's AI tool supports MCP, ask your AI tool admin or IT/developer.
Next step: Using AI assistants with Legatics