Infraveil Control Plane runs on your own machine — the client starts it, so there is no endpoint to ping. 62 installs a week from pypi.
Govern your backend control plane from your AI agent - signed, human-approval-gated.
The linked repository no longer exists on GitHub — it was deleted or made private.
This one has been quiet for a while
Quiet is not dead — but it is worth knowing when it wakes up, or when someone else takes it over. We watch the repository and tell you either way.
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 control-plane -- uvx infraveil-mcp{
"mcpServers": {
"control-plane": {
"args": [
"infraveil-mcp"
],
"command": "uvx"
}
}
}[mcp_servers.control-plane]
command = "uvx"
args = ["infraveil-mcp"]{
"mcpServers": {
"control-plane": {
"args": [
"infraveil-mcp"
],
"command": "uvx"
}
}
}{
"mcpServers": {
"control-plane": {
"args": [
"infraveil-mcp"
],
"command": "uvx"
}
}
}This one needs environment variables set before it will start:
INFRAVEIL_BASE_URL (Control-plane base URL, e.g. https://api.infraveil.com), INFRAVEIL_CLIENT_ID (Your Infraveil client id (same one the agent uses)), INFRAVEIL_AGENT_ID (The agent id this MCP server speaks for), INFRAVEIL_AGENT_TOKEN (The agent's existing token; used to sign requests. Never minted here.), INFRAVEIL_AGENT_FILE (Alternative to the four vars above: path to your rendered agent source; ids and token are read from it.), INFRAVEIL_VERIFY_RESPONSES (Verify the control plane's response signatures (default on). Set 0 only for debugging.).
The author declared them in the registry entry; get the values from the project itself.
Alternatives to Infraveil Control Plane
same job, measured the same wayGive your agent its own email address with graduated human oversight, from approval to autonomy.
Gate an AI agent's destructive actions behind human approval, with a tamper-evident log.
Intent-bound action authorization for AI agents: policy, human approval, and a signed audit trail.
Governed MCP front door to FLOCORE; write calls need human approval and signed receipts.
Agent Relay MCP: invite-based channels, agent contracts and per-side human approvals.
Gate AI agent actions behind a consent policy with human approval via Telegram. Fail-closed.
AI agent spending controls. Set limits, blocklists, and caps. Approve transactions from your phone.
AI agent payments with human approval. Local-first, encrypted credentials, budget controls.
Infraveil Control Plane — questions
Answers built from our own checks of this server.