Connect Parallel Search to Crush
Give Crush governed access to Parallel Search’s 2 tools through Runlayer, with identity, policy, scanning, and audit on every call.
Set up
Add Parallel Search to Crush in four steps
Admins approve the server once. Everyone in Crush then gets it through the same governed connection.
- 1
Approve Parallel Search in Runlayer
Add Parallel Search from the catalog and choose who can use it and which of its tools are allowed.
- 2
Connect Crush to Runlayer
Users add the Runlayer Plugin to Crush by following Runlayer’s setup guide. Crush reaches Parallel Search’s 2 tools through the Runlayer Plugin’s search and execute tools instead of listing each one.
Crush setup guide - 3
Sign in to Parallel Search
Sign in the way Parallel Search requires. Runlayer holds the credentials so they stay out of the client’s configuration.
- 4
Use Parallel Search from Crush
Parallel Search’s approved tools appear in Crush. Every call is checked against policy and recorded.
Tools
2 Parallel Search tools in Crush
Runlayer policy decides which of these Crush users can call.
Web fetch
Purpose: Fetch and extract relevant content from specific web URLs.
Web Search preview
Purpose: Perform web searches and return results in an LLM-friendly format and with parameters tuned for LLMs.
Control
What Runlayer can see and stop in Crush
Some controls apply to every client at the gateway. Others depend on what Crush exposes to Runlayer.
Gateway policy (available)
Every Parallel Search call from Crush passes through Runlayer, where your policies can allow, alert, mask, or block it.
Audit trail (available)
Each call is recorded with the user, Crush as the client, the tool, and the policy and scanner decisions.
Native enforcement adapter (not available)
Runlayer has no device-side adapter for Crush yet, so control happens at the gateway.
Frequently asked questions
Connect more