News

Two ways we use MCP, and how each is governed.

, updated

The Model Context Protocol (MCP) is an open standard that allows an AI model to use tools provided by another system. Lynctera now uses it in two directions. Our own agents use it to draw on outside data services, and Claude, Anthropic's assistant, can use it to work with Lynctera on a person's behalf. The two directions carry different risks, so each is governed in its own way.

MCP in two directions Claude sends a request to Lynctera and gets back the outcome, not the archive, through a checkpoint on the way out and an access check on the way in. Inside Lynctera, the firm's mail, documents and precedents stay in its own workspace, where our agents do the work. Our agents send outside data services short identifiers only, and what comes back is fenced as outside content, through tools that are pinned, read-only and fenced. Claude where you work Lynctera your firm's own workspace Mail, documents, precedents Our agents do the confidential work Outside data prices, transcripts Your request The outcome, not the archive Short identifiers only Data, fenced as outside content Checkpoint out, access check in Pinned, read-only, fenced a remote control a tool MCP in two directions Claude sends a request to Lynctera and gets back the outcome, not the archive, through a checkpoint on the way out and an access check on the way in. Inside Lynctera, the firm's mail, documents and precedents stay in its own workspace, where our agents do the work. Our agents send outside data services short identifiers only, and what comes back is fenced as outside content, through tools that are pinned, read-only and fenced. Claude where you work Your request The outcome, not the archive Checkpoint out, access check in a remote control Lynctera your firm's own workspace Mail, documents, precedents Our agents do the confidential work Short identifiers only Data, fenced as outside content Pinned, read-only, fenced a tool Outside data prices, transcripts
Claude works with Lynctera on one side, and our agents draw on outside services on the other. Confidential material remains within the firm's own workspace throughout.

Using Lynctera from Claude

For people who already use Claude in their daily work, the Lynctera connector makes the platform available from there. They can see what has changed on their cases, open a case, start a research run, approve a step that is awaiting them, or have a reply drafted in their own voice and saved to Outlook.

Claude directs the work, while the handling of confidential material stays within Lynctera. Our agents work inside each client's own isolated workspace, and Claude receives the outcome rather than the archive: a status, a draft, or a link to the relevant step in the portal. Email bodies, the passages of a precedent library and the full text of documents are not available to Claude under any setting, and the connector has no means of sending anything.

Every request carries the person's own Microsoft sign-in and is limited to what that person could see in the portal. Each answer is checked before it leaves Lynctera, so that text written by someone outside the firm is withheld, and every request is written to the firm's own audit record.

The firm's decision

Whether anything reaches Claude is a decision for the firm. The connector is switched off by default, and a firm that wishes to use it switches it on one area at a time, from a consent page that sets out what each area shares and where it goes. Before doing so, the firm confirms that its people use Claude through an organisation account and that it has considered its confidentiality obligations to its own clients. Drafting and cases can be switched on today, and precedents, email and market data will follow.

Every change is recorded. The firm can see who has connected and disconnect anyone, and people can see and end their own connections from their Lynctera settings. Switching an area off stops new requests at once, although it cannot recall information already returned to Claude.

Anything Claude receives, and anything typed into Claude, is held by Anthropic under the firm's own agreement with it, outside our platform and outside the regions in which we host the firm's data. For that reason the connector sends no more than each task requires.

The connector is in use on our own workspace. Client workspaces will be able to connect once sign-in from the client's own Microsoft directory is in place, and we will post here when they can.

Outside services used by our agents

Our agents also use MCP to draw on outside data, such as market prices and earnings call transcripts. Because the operator of a service can change its tools at any time, we approve each tool individually and record its exact definition. If the vendor changes it, the tool is switched off automatically until a person has reviewed the change. Every tool connected today is read-only, and whatever it returns is treated as outside content rather than as instructions.

  1. A person approves the tool
  2. Its definition is pinned
  3. Agents use it, results fenced
  4. The vendor changes it
  5. Switched off automatically
  6. A person reviews and re-approves
A change made by the vendor is held back from our agents until we have reviewed it.

Governance

MCP does not change the rules that govern the rest of the platform. Approvals given through Claude are the person's own, actions taken through Claude enter the same decision record as those taken in the portal, and each agent's AI impact assessment lists the outside tools it holds. These rules are described on Governance.

If your risk or compliance team would like to go through the detail, we would be glad to arrange it.

Where this shows up in the work.

Try it on a sample of your work.

Send us a few emails or documents. We will show you what it does with them, and why. Then a short fixed-fee pilot.

Try it on a sample