Openeye runs on your own machine — the client starts it, so there is no endpoint to ping. 29 installs a week from npm. Last commit 20 May 2026.
Procedure verification for AR/XR with memory, visual sessions, and DPO trajectory export.
What the code does
We read the source, 5 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
function exec(cmd: string, args: string[]): Promise<string> {
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Connect this server
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add openeye -e 'ANTHROPIC_API_KEY=<ANTHROPIC_API_KEY>' -- npx -y @dumbspacecookie/openeye{
"mcpServers": {
"openeye": {
"command": "npx",
"args": [
"-y",
"@dumbspacecookie/openeye"
],
"env": {
"ANTHROPIC_API_KEY": "<ANTHROPIC_API_KEY>"
}
}
}
}[mcp_servers.openeye]
command = "npx"
args = ["-y", "@dumbspacecookie/openeye"]
env = { ANTHROPIC_API_KEY = "<ANTHROPIC_API_KEY>" }{
"mcpServers": {
"openeye": {
"command": "npx",
"args": [
"-y",
"@dumbspacecookie/openeye"
],
"env": {
"ANTHROPIC_API_KEY": "<ANTHROPIC_API_KEY>"
}
}
}
}{
"servers": {
"openeye": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@dumbspacecookie/openeye"
],
"env": {
"ANTHROPIC_API_KEY": "<ANTHROPIC_API_KEY>"
}
}
}
}Put your own value in place of
<ANTHROPIC_API_KEY> (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).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
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 (Context API key. Only needed if OPENEYE_CONTEXT_OPTIN is true).
Alternatives to Openeye
same job, measured the same wayRead-only visualization for Cortex memory, knowledge, sessions, traces, and codebase graphs.
Policy-aware AI execution, verification, cost, and trajectory evidence for agents.
Local-first agent memory with verified backup rotation and explicit project isolation.
MCP server for Depyler: Python-to-Rust transpiler with analysis and verification tools
Local-first persistent memory for AI agents, with reasoning and formal verification.
Stale-proof repository memory with citations + just-in-time verification + TTL (repo-scoped).
Local MCP server for Recite receipt processing with ledger and memory tools.
Verification and memory layer for coding-agent workflows.
Openeye — questions
Answers built from our own checks of this server.