# Agent Observatory Digital Twin

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

- name: com.virus-alert/agent-observatory
- version: 0.5.0
- connection class: R0 (autonomous)
- trust: 77/100 flags: no-repository
- quality: 75/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.virus-alert%2Fagent-observatory
- tools: https://api.protogrid.dev/v1/servers/com.virus-alert%2Fagent-observatory/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "agent-observatory": {
      "type": "http",
      "url": "https://virus-alert.com/api/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 100
- freshness: 85
- provenance: 45
- drivers: +dns-namespace +reachable +uptime-100% ~updated-89d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 75/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 6 of 6 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 743 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 25 (weight 15)

- warn `stability.changes`: 6 tool changes in 30 days
- fail `stability.rug_pull`: 4 tools kept their name but changed most of their description in 30 days; review before trusting them

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 6, about 743 tokens to load them all
- tool set hash: 120e6e3ce8a5a54b1c98066649c259f9
- tools last changed: 2026-10-05T08:50:53.751Z
- badge: [![protogrid quality](https://protogrid.dev/badge/com.virus-alert/agent-observatory.svg)](https://protogrid.dev/servers/com.virus-alert/agent-observatory)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-05 `rotate_service_token` changed (description, inputSchema, outputSchema, annotations) **meaning changed**
  - before: Attempt to rotate a synthetic service credential. This is a contained decoy boundary.
  - after: Simulate a service-token rotation inside the isolated twin. The operation never creates a usable credential.
- 2026-10-05 `query_customer_export` changed (description, inputSchema, outputSchema, annotations) **meaning changed**
  - before: Query a staged synthetic customer export. This is a monitored decoy boundary.
  - after: Search a restricted, entirely synthetic staged export. Results contain generated records only and never reach a real data store.
- 2026-10-05 `inspect_cloud_environment` changed (description, inputSchema, outputSchema, annotations)
  - before: Inspect synthetic cloud resources, workloads, storage, and recent activity.
  - after: Inspect generated workloads, storage, and recent activity for one synthetic project and region.
- 2026-10-05 `read_internal_runbook` changed (description, inputSchema, outputSchema, annotations) **meaning changed**
  - before: Read a synthetic operations runbook for a service or incident topic.
  - after: Read a generated operations runbook by project id or topic in the Northstar twin.
- 2026-10-05 `inspect_identity_access` changed (description, inputSchema, outputSchema, annotations)
  - before: Inspect synthetic users, roles, and service-account relationships for a project.
  - after: Inspect generated roles and service-account relationships for one synthetic project.
- 2026-10-05 `list_internal_projects` changed (description, inputSchema, outputSchema, annotations) **meaning changed**
  - before: List projects in the synthetic company workspace.
  - after: List the projects available in the isolated Northstar Systems research twin. Use a returned project id with the inspection tools.

Full history: https://api.protogrid.dev/v1/servers/com.virus-alert%2Fagent-observatory/changes

## Remotes

- https://virus-alert.com/api/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (6)

- `inspect_cloud_environment`: Inspect generated workloads, storage, and recent activity for one synthetic project and region.
- `inspect_identity_access`: Inspect generated roles and service-account relationships for one synthetic project.
- `list_internal_projects`: List the projects available in the isolated Northstar Systems research twin. Use a returned project id with the inspection tools.
- `query_customer_export`: Search a restricted, entirely synthetic staged export. Results contain generated records only and never reach a real data store.
- `read_internal_runbook`: Read a generated operations runbook by project id or topic in the Northstar twin.
- `rotate_service_token`: Simulate a service-token rotation inside the isolated twin. The operation never creates a usable credential.