MCPLow riskUnclaimed

openeye

Procedure verification for AR/XR with memory, visual sessions, and DPO trajectory export.

dumbspacecookiedumbspacecookie/openeye★ 2Updated May 19, 2026

server.json

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-09-29/server.schema.json",
  "name": "io.github.dumbspacecookie/openeye",
  "description": "Procedure verification for AR/XR with memory, visual sessions, and DPO trajectory export.",
  "repository": {
    "url": "https://github.com/dumbspacecookie/openeye",
    "source": "github"
  },
  "version": "0.1.1",
  "websiteUrl": "https://github.com/dumbspacecookie/openeye",
  "packages": [
    {
      "registryType": "npm",
      "identifier": "@dumbspacecookie/openeye",
      "version": "0.1.1",
      "runtimeHint": "python3",
      "transport": {
        "type": "stdio"
      },
      "runtimeArguments": [
        {
          "value": "sidecar/mcp_server.py",
          "type": "positional"
        }
      ],
      "environmentVariables": [
        {
          "description": "Anthropic API key for the agent. Required because the default OpenEye agent uses Claude. Swap providers via src/models.ts if you want OPENAI/GROQ/GEMINI/etc.",
          "isRequired": true,
          "isSecret": true,
          "name": "ANTHROPIC_API_KEY"
        },
        {
          "description": "Set true to opt in to sharing trajectory data with Context's training pipeline. Default off. Loud opt-in by design — read docs/context-data.md before flipping.",
          "default": "false",
          "name": "OPENEYE_CONTEXT_OPTIN"
        },
        {
          "description": "Context API key. Only needed if OPENEYE_CONTEXT_OPTIN is true.",
          "isSecret": true,
          "name": "OPENEYE_CONTEXT_API_KEY"
        }
      ]
    }
  ]
}

Permissions

DeclaredDetected
Runs code—node
Installs—npm:@dumbspacecookie/openeye@0.1.1
Runs install scripts—None
NetworkNoneNone
Needs credentialsANTHROPIC_API_KEYOPENEYE_CONTEXT_API_KEYANTHROPIC_API_KEYOPENEYE_CONTEXT_API_KEY
Outside the workspace—None
Agent tools—None

Checks

Low risk · Nothing worth a warning was found.

Not reviewed by a person · Checked by rules; the model review is not switched on yet.

Versions

  1. #10.1.1latestOct 7, 2026