MCP Gateway · Claude Code
Connect Cube to Claude Code
Cube gives agents a way to explore analytics data and generate SQL queries. Developers can bring that into Claude Code through the Speakeasy MCP Gateway, which puts Cube behind one governed URL with sign-in through the company identity provider. Agent hooks send each prompt and tool call to Speakeasy, which allows or denies it before Claude Code runs it.
- Category
- Data & analytics
- Authentication
- None
- Claude Code
- CLI
Behind the MCP Gateway
Run Cube MCP behind the MCP Gateway
One URL for every agent, sign-in through your IdP, RBAC down to the tool, and every Cube call inspected and logged.
Set up
Add Cube to Claude Code in 4 steps
- 01
Add Cube from the catalog
An admin finds Cube in the MCP Catalog (MCP Gateway > MCP > Catalog) and clicks Add. Speakeasy registers the vendor's server as a remote MCP server and proxies sessions to it. Nothing is copied or re-hosted.
Where MCP-scoped policies are enabled, the install offers a recommended risk policy for the new server that detects secrets and PII and inspects tool requests and responses.
- 02
Choose who can use Cube
Give teams the
mcp:connectscope on the Cube server through team access or a role. The organization gateway works out each person's servers from their live access, so granting access adds Cube to their gateway on the next call, and removing it takes it away. - 03
Connect Claude Code
Add the organization gateway as an HTTP MCP server, then authenticate from /mcp.
Run the command below with your organization gateway URL.
Open
/mcpin Claude Code and choose Authenticate to sign in.claude mcp add --transport http --scope user \ 'speakeasy' \ 'https://<organization host>/mcp/gateway/<organization slug>' - 04
Sign in and use Cube from Claude Code
The first time Claude Code connects, it opens a browser so the person can sign in to Speakeasy through your identity provider.
From then on, Cube's tools appear in Claude Code, limited to what the person's access allows, and every call lands in the gateway's tool logs.
To roll it out to a whole team, publish the server in a plugin and register the plugin marketplace in Claude Code's managed settings, so every member gets it without running the command. The device agent can also write and reapply these settings on each laptop.
Use cases
What Claude Code users do with Cube
Check the numbers behind a feature
Before changing code that feeds a dashboard, ask Claude Code to explore the related analytics data in Cube and confirm what the current figures look like.
Generate SQL for a script
When a script or migration needs a query against analytics data, Claude Code asks Cube to generate the SQL, which you review before it goes into the code.
Answer a usage question from the terminal
A product manager asks how a feature is used. Without leaving the terminal, Claude Code explores the Cube data and summarizes what it finds for the reply.
Control
What Speakeasy can see and stop in Claude Code
The gateway covers every client the same way. The rest depends on what Claude Code exposes to Speakeasy.
Tool logs
Gateway
Every Cube call is logged with the person and the client that made it.
Access by role
Gateway
People reach only the Cube tools their team or role allows.
Request and response blocking
Gateway
A risk policy scoped to Cube can reject a tool request before it reaches the server, or withhold a result from Claude Code. MCP-scoped policies are enabled per organization.
Prompt and tool-call blocking
Claude Code
Agent hooks send each prompt and tool call to Speakeasy, which allows or denies it before Claude Code runs it.
User attribution
Claude Code
Claude Code's OpenTelemetry exporter ties each session to a named person. Without it, activity can't be attributed.
Budgets
Claude Code
Spend limits can block Claude Code traffic once a budget is reached.
Device agent and MDM
Claude Code
The device agent installs the marketplace, plugin and telemetry settings and reapplies them every minute. It deploys through MDM.
Anthropic inference hooks
Claude Code
On Claude Enterprise, prompts can be checked before inference with nothing installed on the device (beta).
- Claude Code on the web doesn't use the laptop setup. It needs the device agent in a shared Anthropic-hosted environment.
- Plugin marketplace URLs for Claude Code carry an access token, so share install snippets only through a private channel.
Questions
Frequently asked questions
Can access to Cube be limited by team in Claude Code?
Does Claude Code hold a Cube credential?
How do Claude Code users get Cube?
Are Cube calls from Claude Code logged?
Connect more