Connect Runlayer to Cline CLI
Give Cline CLI governed access to Runlayer’s 139 tools through Runlayer, with identity, policy, scanning, and audit on every call.
Set up
Add Runlayer to Cline CLI in four steps
Admins approve the server once. Everyone in Cline CLI then gets it through the same governed connection.
- 1
Approve Runlayer in Runlayer
Add Runlayer from the catalog and choose who can use it and which of its tools are allowed.
- 2
Connect Cline CLI to Runlayer
Users add the Runlayer Plugin to Cline CLI by following Runlayer’s setup guide. Cline CLI reaches Runlayer’s 139 tools through the Runlayer Plugin’s search and execute tools instead of listing each one.
Cline CLI setup guide - 3
Sign in to Runlayer
Sign in the way Runlayer requires. Runlayer holds the credentials so they stay out of the client’s configuration.
- 4
Use Runlayer from Cline CLI
Runlayer’s approved tools appear in Cline CLI. Every call is checked against policy and recorded.
Tools
139 Runlayer tools in Cline CLI
Runlayer policy decides which of these Cline CLI users can call.
Add agent connectors
Add or update connectors on an agent (incremental edit).
Add agent skills
Add skills to an agent (incremental edit).
Add agent subagent
Add one subagent to an existing agent.
Add AI watch enforce entry
Put one source in an Enforce allowlist or Protect denylist.
Add plugin connectors
Add or update connectors on a plugin (incremental edit).
Add plugin skills
Add skills to a plugin (incremental edit).
Create agent
Create a new agent.
Create agent eval
Create an offline eval run: replay selected past agent runs, optionally with overrides, and judge the replays.
Control
What Runlayer can see and stop in Cline CLI
Some controls apply to every client at the gateway. Others depend on what Cline CLI exposes to Runlayer.
Gateway policy (available)
Every Runlayer call from Cline CLI passes through Runlayer, where your policies can allow, alert, mask, or block it.
Audit trail (available)
Each call is recorded with the user, Cline CLI 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 Cline CLI runs it.
Block output after it runs (not available)
Cline CLI ignores Runlayer after a tool runs, so Runlayer cannot block its output. The gateway still applies policy to the call.
Redact output in place (not available)
Runlayer cannot mask tool output in Cline CLI. The gateway still applies policy to the call.
In Cline CLI
- If Runlayer’s hook times out or crashes, Cline CLI lets the tool call through.
- This covers the Cline CLI, not the Cline extension for VS Code.
Frequently asked questions
Connect more
