Skip to main content

Connect RunReveal to Hermes

Give Hermes governed access to RunReveal’s 53 tools through Runlayer, with identity, policy, scanning, and audit on every call.

Set up

Add RunReveal to Hermes in four steps

Admins approve the server once. Everyone in Hermes then gets it through the same governed connection.

  1. 1

    Add RunReveal to Runlayer

    RunReveal isn’t in the Runlayer catalog yet, so an admin adds it by its MCP server URL.

    Adding a connector manually
  2. 2

    Connect Hermes to Runlayer

    Users add the Runlayer Plugin to Hermes by following Runlayer’s setup guide. Hermes reaches RunReveal’s 53 tools through the Runlayer Plugin’s search and execute tools instead of listing each one.

    Hermes setup guide
  3. 3

    Sign in to RunReveal

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

  4. 4

    Use RunReveal from Hermes

    RunReveal’s approved tools appear in Hermes. Every call is checked against policy and recorded.

Tools

53 RunReveal tools in Hermes

Runlayer policy decides which of these Hermes users can call.

  • List agent resources

    List built-in reference documents available to load with AgentResourcesLoad.

  • Agent resources load

    Load a built-in reference document by uri.

  • Create agent skills

    Create a new agent skill in this workspace.

  • List agent skills

    List the agent skills available in this workspace.

  • Agent skills load

    Load a single agent skill by name.

  • Update agent skills

    Apply a partial edit to an existing agent skill.

  • Create agents

    Create a scheduled AI agent that runs a prompt on a cron schedule.

  • Delete agents

    Delete a scheduled AI agent by id, including its auto-created role and access policies.

See all 53 RunReveal tools

Control

What Runlayer can see and stop in Hermes

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

  • Gateway policy (available)

    Every RunReveal call from Hermes passes through Runlayer, where your policies can allow, alert, mask, or block it.

  • Audit trail (available)

    Each call is recorded with the user, Hermes 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 Hermes runs it.

  • Block output after it runs (available)

    Runlayer can block a tool’s output in Hermes and show a message in its place.

  • Redact output in place (not available)

    Hermes cannot take masked output, so Runlayer can block a tool’s output but not mask it. The gateway still applies policy to the call.

In Hermes

  • Hermes can replace blocked tool output with a message, but its after-call event is for monitoring only.

Frequently asked questions

Connect more

Find another combination