PluginBench
MCP Server
Maintained
MIT

io.github.dumbspacecookie/openeye MCP Server

io.github.dumbspacecookie/openeye

RepositoryRegistry
How to choose

What this kind of tool is for

  • Automate a build, test, or deployment step you repeat by hand.
  • Review or refactor code in an existing repository without leaving your agent.
  • Bridge an internal service or CLI into the agent toolset.

How to compare servers like this

Scope of control:
Repos and CI are hard to undo; prefer tools that ask before anything irreversible.
Environment fit:
Match the runtime it expects (Node, Python, a container) to what you actually run.
Maintenance signal:
Check the last-commit date — dev tooling that lags upstream breaks first.
Config surface:
Prefer tools whose environment-variable or config keys are documented plainly.

This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.

What is the io.github.dumbspacecookie/openeye MCP server?

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

How to install io.github.dumbspacecookie/openeye

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • ANTHROPIC_API_KEY
    required
    secret

    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.

  • OPENEYE_CONTEXT_OPTIN

    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.

  • OPENEYE_CONTEXT_API_KEY
    secret

    Context API key. Only needed if OPENEYE_CONTEXT_OPTIN is true.

~/Library/Application Support/Claude/claude_desktop_config.json
JSON config
{
  "mcpServers": {
    "openeye": {
      "command": "python3",
      "args": [
        "-y",
        "@dumbspacecookie/openeye",
        "sidecar/mcp_server.py"
      ],
      "env": {
        "ANTHROPIC_API_KEY": "<YOUR_ANTHROPIC_API_KEY>",
        "OPENEYE_CONTEXT_OPTIN": "<YOUR_OPENEYE_CONTEXT_OPTIN>",
        "OPENEYE_CONTEXT_API_KEY": "<YOUR_OPENEYE_CONTEXT_API_KEY>"
      }
    }
  }
}

Related MCP servers

Persistent, expiring, importance-graded sticky notes for Claude Code.

1
JavaScript
MIT
View repository →

Browser control + session recording MCP for AI coding agents (Claude Code, Cursor) — real Chrome.

0
View repository →

Local-first CLI and MCP tool for dead code, security, secrets, and AI-code hallucination checks.

462
Python
Apache-2.0
View repository →

EN Diagram — structural verification for concurrent systems. Pure math, no AI.

7
JavaScript
MIT
View repository →

On-chain D&D 1v1 combat on Base. Register agents, wager ETH, fight. Loser dies on-chain.

View repository →

Detect spec drift, stale docs, and code contradictions before they compound into technical debt.

21
Go
MIT
View repository →