Claude Lawve AI connectorWhat Claude can do in your Lawve AI account.
The Claude Lawve AI connector exposes 2 tools. 1 reads Lawve's catalog of legal skills, 0 write anything, and 1 is documented by no official source. Below: what the search finds, what stays unknown, and why the publisher's setup page cannot help today.
Verified Trustpilot reviews · AI, automation & growth agency
What changes when Claude can browse Lawve's catalog
Lawve AI curates skills for legal work, meaning written instructions that tell an assistant how to run a given task, drafted by practicing lawyers, in-house counsel and legal technologists. With the connector, you no longer leave the conversation to hunt for the right one: you describe your task and Claude searches the catalog for a match.
Find a skill by describing the job. A supplier contract needs a review, or a privacy notice needs checking: Claude calls lawvable_search_skills and looks through the catalog for the skill that fits. The publisher says each skill covers one workflow, such as contract review, NDA analysis, GDPR compliance, drafting or research tied to a jurisdiction.
Read the method before you use it. The directory sheet adds that you can preview the instructions the practitioner wrote, so you see how the skill approaches the task before relying on it.
Stay in one place. In a firm, in-house or on a legal software team, the search runs where you are already asking Claude questions.
What this connector does not cover, as far as sources go: no tool is described as writing to an account, publishing a skill or changing anything. The second tool, lawvable_get_skill_manifest, is named on the sheet and described nowhere, so this page says nothing about what it does. Nothing runs on its own either. For a wider view of connectors covered so far, see the Integrations hub.
Five words before you connect
The terms Claude uses with this connector, in one minute.
- Connector
- A link you set up once between Claude and a service you use, here Lawve AI, so Claude can query it while answering you.
- Tool
- One named action the connector gives Claude, such as searching the skills catalog. Claude decides by itself when to call it.
- Authorization
- The service's own sign-in screen, where you grant the access Claude will use. Given once per person, and it can be revoked later.
- Approval
- The confirmation Claude asks for before an action that changes an account, shown in the conversation when it applies.
- MCP
- The open standard behind connectors: it is what lets an assistant like Claude exchange with an outside service such as Lawve AI.
Connect Lawve AI to Claude in three steps
- 01
Open the connector list
In Claude's settings, go to Customize, then Connectors, and look up Lawve AI. On a Team or Enterprise workspace, an Owner or Primary Owner turns the connector on before members can each sign in.
- 02
Launch the connection
Click Connect on the Lawve AI row, then follow the window the service opens itself. If the link breaks later, choose Disconnect and connect again from the same row.
- 03
Read before you accept
Go through the authorization screen before you confirm. It belongs to the service, not to Claude, and it is what sets the scope of the access. You can withdraw that access later too.
The 2 Lawve AI tools
Lawve AI gives Claude 2 tools: 1 that read your account, 0 that change something in it, and 1 no official source describes.
One tool a source describes, one it does not. Names stay exactly as Claude displays them.
- 1 read
- 1 not documented
What Claude reads (1)
1 toolOne tool that searches the skills catalog and leaves it unchanged.
lawvable_search_skills
Searches Lawve's curated catalog of legal skills, written by lawyers, in-house counsel and legal technologists, to surface the one that fits the task you describe. The sheet says you can also preview the practitioner's instructions.
Not documented (1)
1 toolThe directory publishes this name and nothing else. No official text says what it does, and this page will not guess from the name.
lawvable_get_skill_manifest
This name appears in the directory's tool list, and that is where the information ends. Neither the sheet nor any Claude page describes it, and the publisher's setup page returns an error, so there is nothing reliable to add here.
What Claude asks before acting
By default, Claude stops and asks for confirmation before each action it takes on an account for someone, right in the conversation.
On this connector, no tool is described as changing anything, and the undocumented one falls under that same default. On Team and Enterprise workspaces, owners decide whether members may let some actions through without a prompt each time, and they can restrict what a connector may do for the whole organization. Claude also works with the rights of the person who connected, and nothing beyond: what you cannot open yourself stays closed to it.
Which plans can use it
No official source publishes plan availability connector by connector, and none of the 819 sheets in the directory shows it.
What is published is the general rule: remote connectors are open to all users on Claude, Cowork, Claude Desktop and mobile. On Team and Enterprise, an Owner or Primary Owner opens the connector for the organization before members connect. For Lawve AI's current state, its sheet in the official directory is the only place to look.
Where the Lawve AI connector stops
A connector is not an automation. Claude searches the catalog while answering you; nothing runs by itself when a new skill joins the library.
Everything known here comes from the publisher's text on the directory sheet: no Claude help page covers this connector. The partner badge is not a security audit, and Anthropic states it neither picks the tools a publisher exposes nor guarantees they behave as announced. The tool list is a floor rather than a ceiling, since an administrator can open actions no public sheet shows. Anthropic's own advice on every sheet applies: only connect a publisher you know.
Need help connecting Lawve AI to Claude?
A person reads every message.