Connect Sourcegraph to Goose
Give Goose governed access to Sourcegraph through Runlayer, with identity, policy, scanning, and audit on every call.
Set up
Add Sourcegraph to Goose in four steps
Admins approve the server once. Everyone in Goose then gets it through the same governed connection.
- 1
Approve Sourcegraph in Runlayer
Add Sourcegraph from the catalog and choose who can use it and which of its tools are allowed.
- 2
Connect Goose to Runlayer
Users add the Runlayer Plugin as a Goose extension; Goose has no native plugin install. Goose reaches Sourcegraph’s tools through the Runlayer Plugin’s search and execute tools instead of listing each one.
Goose setup guide - 3
Sign in to Sourcegraph
Each user signs in to Sourcegraph with OAuth. Runlayer keeps the tokens out of the client’s configuration.
- 4
Use Sourcegraph from Goose
Sourcegraph’s approved tools appear in Goose. Every call is checked against policy and recorded.
Tools
Sourcegraph tools in Goose
Sourcegraph reports its tools when your organization connects it, so the list depends on your deployment.
Control
What Runlayer can see and stop in Goose
Some controls apply to every client at the gateway. Others depend on what Goose exposes to Runlayer.
Gateway policy (available)
Every Sourcegraph call from Goose passes through Runlayer, where your policies can allow, alert, mask, or block it.
Audit trail (available)
Each call is recorded with the user, Goose 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 Goose runs it.
Block output after it runs (available)
Runlayer can block a tool’s output before Goose’s model sees it.
Redact output in place (not available)
Goose cannot apply masking, so Runlayer blocks output it would otherwise mask. The gateway still applies policy to the call.
Frequently asked questions
Connect more