Connect Statsig to VS Code
Give VS Code governed access to Statsig’s 93 tools through Runlayer, with identity, policy, scanning, and audit on every call.
Set up
Add Statsig to VS Code in four steps
Admins approve the server once. Everyone in VS Code then gets it through the same governed connection.
- 1
Approve Statsig in Runlayer
Add Statsig from the catalog and choose who can use it and which of its tools are allowed.
- 2
Connect VS Code to Runlayer
Runlayer’s CLI installs the Runlayer Plugin natively in VS Code; users can also add it over MCP. With direct tool listing turned on for your deployment, Statsig’s 93 tools show up in VS Code’s own tool list (VS Code 1.103 or newer).
VS Code setup guide - 3
Sign in to Statsig
Sign in the way Statsig requires. Runlayer holds the credentials so they stay out of the client’s configuration.
- 4
Use Statsig from VS Code
Statsig’s approved tools appear in VS Code. Every call is checked against policy and recorded.
Tools
93 Statsig tools in VS Code
Runlayer policy decides which of these VS Code users can call.
Approve autotune review
Approve an in-flight review of an autotune experiment.
Approve dynamic config review
Approve an in-flight review of a dynamic config.
Approve experiment review
Approve an in-flight review of an experiment (A/B test).
Approve gate review
Approve an in-flight review of a gate (feature flag).
Cancel autotune review
Cancel (withdraw) an in-flight review of an autotune experiment.
Cancel dynamic config review
Cancel (withdraw) an in-flight review of a dynamic config.
Cancel experiment review
Cancel (withdraw) an in-flight review of an experiment (A/B test).
Cancel gate review
Cancel (withdraw) an in-flight review of a gate (feature flag).
Control
What Runlayer can see and stop in VS Code
Some controls apply to every client at the gateway. Others depend on what VS Code exposes to Runlayer.
Gateway policy (available)
Every Statsig call from VS Code passes through Runlayer, where your policies can allow, alert, mask, or block it.
Audit trail (available)
Each call is recorded with the user, VS Code as the client, the tool, and the policy and scanner decisions.
Client hooks (available)
Capture supported prompts, reasoning, local and MCP tool calls, responses, and scanner decisions in real time.
Stop a call before it runs (available)
Runlayer can deny a tool call before VS Code runs it.
Block output after it runs (available)
Runlayer can block a tool’s output before VS Code’s model sees it.
Redact output in place (available)
Runlayer can mask sensitive parts of a tool’s output in VS Code and pass the rest through.
Frequently asked questions
Connect more