Connect Lever to Claude Code

Make Claude advance candidates and add notes in Lever. From the terminal, inside the sessions where you already work.

How do you connect Lever to Claude Code?

Claude Code reaches outside tools through MCP servers. To connect Lever, you add a Lever MCP server: a small hosted service that exposes Lever's data and actions over the Model Context Protocol. With a custom connector we build for you, that is one command in the terminal, then an OAuth sign-in with your own Lever account. No API keys pasted into config files.

claude mcp add --transport http lever https://your-connector-url/mcp

Then run /mcp inside a Claude Code session to sign in. Add it with --scope project and the connector is checked into the repo for your whole team.

What can Claude Code do in Lever once connected?

Full read-write Lever access lets Claude move a candidate to the next pipeline stage, add interview notes and feedback to a profile, apply or remove tags, archive candidates with a reason, and create or update job postings, all after you approve. The pipeline upkeep that used to mean clicking through Lever happens where the work already lives.

Advance a candidate to the next stage in a posting's pipeline
Add a note or interview feedback to a candidate profile
Apply or remove tags to organize candidates
Archive a candidate with a documented reason
Create or update a job posting and its details
Add a candidate to a posting after you confirm

One connector, every Claude surface

The connector we build is a remote MCP server, which is the same standard claude.ai and Claude Desktop use. Add it once and the same Lever access works in Claude Code for you, in claude.ai for the rest of the team, and in Claude Desktop. One build, one set of permissions, one monthly plan covering all of them.

Build it yourself, or have it built?

If you live in the terminal, you can absolutely write your own MCP server against the Lever API. The protocol is open. What you take on is everything around the happy path: OAuth token refresh, hosting, monitoring, keeping up when Lever changes its API and when the MCP spec itself moves, and scoping write actions so an agent can never do more than you intended. We build Lever connectors with separated read and write tools and approval gates on destructive actions, then host and maintain them so they keep working while you work.

Frequently asked questions

Does the same Lever connector work in claude.ai and Claude Code?

Yes. It is one remote MCP server. Claude Code adds it with a single "claude mcp add" command; claude.ai and Claude Desktop add it as a custom connector in Settings. Each person signs in with their own Lever account, so access always matches what that person can already see and do.

Do I need to host or maintain anything myself?

No. The connector runs as a hosted service we operate: we handle uptime, token health, API changes on Lever's side, and MCP spec migrations under the monthly plan. Your side is one command in the terminal and an OAuth sign-in.

Is it safe to give a coding agent write access to Lever?

Write access is scoped, not blanket. Read tools and write tools are separated, destructive actions like deleting or sending are gated behind your explicit approval, and the connector can never exceed the permissions of the Lever account it signs in with. Revoking access is one click in Lever.

More on the Lever connector

Lever connector for claude.ai Deel + Claude Code Justworks + Claude Code Paychex + Claude Code

Tell us what you run. We'll build the connector.

Pick your tool, choose what Claude should do, and get an instant scope and price. No call required.

Build my connector Talk to us