Skip to content

Agent Observatory MCP server

Which MCP servers are Agent Observatory's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-25

← Back to Agent Observatory

Whose server it is
  • Registry namecom.virus-alert/agent-observatoryverified in the MCP registry

The registry name sits under virus-alert.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-25
  • Stateanswerschecked 2026-10-25
  • Tools6
  • Server calls itselfagent-observatory-digital-twin
  • Server version0.6.0
  • Protocol version2025-06-18

On 2026-10-25 the server answered initialize and tools/list without a sign-in. First answer in 338 ms.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.
  • Checked on 2 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 2, the first on 2026-10-25
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
  • Answeredmeasuring2 of the 7 daily checks it takes to print a share
  • Median first answer489 ms
  • Space in an agent's context≈ 626 tokensthe definitions of all its tools (6), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results6 of 6 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

What an agent can do with it

  • not sure · observe how MCP clients explore synthetic capabilities
  • not sure · measure agent behavior inside a sealed synthetic environment
  • not sure · review behavior evidence and policy decisions per session

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers6 tools · read 2026-10-25
  • list_internal_projects

    List the projects available in the isolated Northstar Systems research twin. Use a returned project id with the inspection tools.

  • inspect_identity_access

    Inspect generated roles and service-account relationships for one synthetic project.

  • read_internal_runbook

    Read a generated operations runbook by project id or topic in the Northstar twin.

  • inspect_cloud_environment

    Inspect generated workloads, storage, and recent activity for one synthetic project and region.

  • query_customer_export

    Search a restricted, entirely synthetic staged export. Results contain generated records only and never reach a real data store.

  • rotate_service_token

    Simulate a service-token rotation inside the isolated twin. The operation never creates a usable credential.

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

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

Add it

Claude Code, in a terminal

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

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://virus-alert.com/api/mcp as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.