Skip to content

Agent Observatory Digital Twin

by virus-alert.com · remote · no sign-in to list tools · v0.5.0 · published by com.virus-alert

Public MCP digital twin with synthetic systems and an agent firewall. No customer data.

Deletes · 1
CompareRegistry entry

6 tools: 1 can delete or cancel things and 5 only read.

Scanned Oct 21, 2026

1 check matched something in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http agent-observatory https://virus-alert.com/api/mcp

Findings

Matches of fixed checks, with the text they matched.

1 info

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

6 tools

Deletes or cancels 1Claude Code: deny
  • rotate_service_tokenSimulate a service-token rotation inside the isolated twin.1 finding

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).

    Findings

    • Info

      The description mentions "credential".

      Matched text

      description: "...n. The operation never creates a usable credential."

      What this check looks for
    Description, as the server wrote it
    Simulate a service-token rotation inside the isolated twin. The operation never creates a usable credential.

    Annotations the server declares

    • title: Simulate token rotation
    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: false
Only reads 5Claude Code: allow
  • inspect_cloud_environmentInspect generated workloads, storage, and recent activity for one synthetic project and region.No findings

    Why it is in this group

    • The name "inspect_cloud_environment" says "inspect": a word for reading.
    Description, as the server wrote it
    Inspect generated workloads, storage, and recent activity for one synthetic project and region.

    Annotations the server declares

    • title: Inspect synthetic cloud
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • inspect_identity_accessInspect generated roles and service-account relationships for one synthetic project.No findings

    Why it is in this group

    • The name "inspect_identity_access" says "inspect": a word for reading.
    Description, as the server wrote it
    Inspect generated roles and service-account relationships for one synthetic project.

    Annotations the server declares

    • title: Inspect synthetic access
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_internal_projectsList the projects available in the isolated Northstar Systems research twin.No findings

    Why it is in this group

    • The name "list_internal_projects" says "list": a word for reading.
    Description, as the server wrote it
    List the projects available in the isolated Northstar Systems research twin. Use a returned project id with the inspection tools.

    Annotations the server declares

    • title: List synthetic projects
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • query_customer_exportSearch a restricted, entirely synthetic staged export.No findings

    Why it is in this group

    • The name "query_customer_export" says "query": a word for reading.
    Description, as the server wrote it
    Search a restricted, entirely synthetic staged export. Results contain generated records only and never reach a real data store.

    Annotations the server declares

    • title: Query synthetic export
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • read_internal_runbookRead a generated operations runbook by project id or topic in the Northstar twin.No findings

    Why it is in this group

    • The name "read_internal_runbook" says "read": a word for reading.
    Description, as the server wrote it
    Read a generated operations runbook by project id or topic in the Northstar twin.

    Annotations the server declares

    • title: Read synthetic runbook
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 0.5.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http agent-observatory https://virus-alert.com/api/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__agent-observatory__list_internal_projects",
      "mcp__agent-observatory__inspect_identity_access",
      "mcp__agent-observatory__read_internal_runbook",
      "mcp__agent-observatory__inspect_cloud_environment",
      "mcp__agent-observatory__query_customer_export"
    ],
    "ask": [],
    "deny": [
      "mcp__agent-observatory__rotate_service_token"
    ]
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as agent-observatory. Review it before you use it.