Skip to content

Agent Observatory Digital Twin MCP server

com.virus-alert/agent-observatoryvirus-alert.comstreamable-httpv0.5.0Scanned

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

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

Tools: 1 delete, 0 irreversible, 0 write, 5 read.
  • Reads private data · 0
  • Reads text others write · 0
  • Can send data out · 0
  • 1 finding

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here can delete or cancel things. Govern it.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the Agent Observatory Digital Twin MCP server can do

The Agent Observatory Digital Twin MCP server is published by virus-alert.com, a domain the MCP Registry verified. It has 6 tools. It can delete or cancel things (1 tool: rotate_service_token). 5 tools only read.

None of its tools reads private data, brings in text other people write, or sends data out.

The fixed checks matched 1 finding (credentials-mention). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 14, 2026, version 0.5.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

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 5Show 5 read-only tools
  • 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.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:50 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
1
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 destructive). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://virus-alert.com/api/mcp: tools/list returned 6 tools to an anonymous client, including rotate_service_token (destructive)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

1 info

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

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
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 or a way out, 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. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as agent-observatory. Review it before you use it.

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/com.virus-alert/agent-observatory/verify?hash=92db4c1f9cd0c07d3e2fae3f316ba7e4bfb8d24f3a202de3bbf0c97377a182d3" | jq -e '.changed == false'

Pinned hash 92db4c1f9cd0, from Nov 14, 2026, 18:17 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/com.virus-alert/agent-observatory/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for com.virus-alert/agent-observatory
[![Anlyon Radar](https://radar.anlyon.com/badge/com.virus-alert/agent-observatory.svg)](https://radar.anlyon.com/servers/com.virus-alert/agent-observatory)

Source: MCP Registry. Synced Oct 21, 2026, 18:10 UTC.

Agent Observatory Digital Twin MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Agent Observatory Digital Twin MCP server safe?

No scan can promise that. What its definitions show: 6 tools, 1 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Agent Observatory Digital Twin MCP server delete data?

Yes. 1 tool can delete, cancel or revoke something: rotate_service_token.

Can the Agent Observatory Digital Twin MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the Agent Observatory Digital Twin MCP server have?

6 tools: 1 destructive, 5 read. rotate_service_token, list_internal_projects, inspect_identity_access, read_internal_runbook, inspect_cloud_environment and query_customer_export.

Does the Agent Observatory Digital Twin MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Agent Observatory Digital Twin MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the Agent Observatory Digital Twin MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 14, 2026.