Skip to main content
Book a demo

Connect Exa to GitHub Copilot CLI

Give GitHub Copilot CLI governed access to Exa’s 3 tools through Runlayer, with identity, policy, scanning, and audit on every call.

Book a demo GitHub Copilot CLI setup guide

Set up

Add Exa to GitHub Copilot CLI in four steps

Admins approve the server once. Everyone in GitHub Copilot CLI then gets it through the same governed connection.

  1. 1

    Approve Exa in Runlayer

    Add Exa from the catalog and choose who can use it and which of its tools are allowed.

  2. 2

    Connect GitHub Copilot CLI to Runlayer

    Users add the Runlayer Plugin to GitHub Copilot CLI by following Runlayer’s setup guide. GitHub Copilot CLI reaches Exa’s 3 tools through the Runlayer Plugin’s search and execute tools instead of listing each one.

    GitHub Copilot CLI setup guide
  3. 3

    Sign in to Exa

    Sign in the way Exa requires. Runlayer holds the credentials so they stay out of the client’s configuration.

  4. 4

    Use Exa from GitHub Copilot CLI

    Exa’s approved tools appear in GitHub Copilot CLI. Every call is checked against policy and recorded.

Tools

3 Exa tools in GitHub Copilot CLI

Runlayer policy decides which of these GitHub Copilot CLI users can call. 1 read data only.

  • Agent run

    Start or resume an Exa Agent run for multi-step research, list-building, or enrichment.

  • Web fetch Exa

    Read a webpage's full content as clean markdown.

  • Web search Exa

    Search the web for any topic and get clean, ready-to-use content.

Control

What Runlayer can see and stop in GitHub Copilot CLI

Some controls apply to every client at the gateway. Others depend on what GitHub Copilot CLI exposes to Runlayer.

  • Gateway policy (available)

    Every Exa call from GitHub Copilot CLI passes through Runlayer, where your policies can allow, alert, mask, or block it.

  • Audit trail (available)

    Each call is recorded with the user, GitHub Copilot 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 or permission request before GitHub Copilot CLI runs it.

  • Block output after it runs (available)

    Runlayer can block a tool’s output before GitHub Copilot CLI’s model sees it.

  • Redact output in place (available)

    Runlayer can mask sensitive parts of a successful tool’s output in GitHub Copilot CLI and pass the rest through.

In GitHub Copilot CLI

  • When a tool fails, Runlayer records the error but cannot replace it.

Frequently asked questions

Connect more

Find another combination