Infraveil Agent Guard MCP Server
io.github.infraveilhq/agent-guard
What this kind of tool is for
- Scan a repository or dependency tree for known vulnerabilities.
- Audit secrets, permissions, or headers during a pre-release review.
- Have your agent explain a suspicious script or config before you run it.
How to compare servers like this
- Failure mode:
- Vulnerability reports are probabilistic; read findings as leads to verify, not verdicts.
- Data leaving the box:
- Check whether files or code are uploaded anywhere before scanning anything private.
- Maintenance signal:
- Security rulesets age fast; stale tools miss new classes of issue.
- Report clarity:
- The best tools say what is wrong, how sure they are, and how to fix it — verify findings yourself.
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 Infraveil Agent Guard MCP server?
Gate an AI agent's destructive actions behind human approval, with a tamper-evident log.
How to install Infraveil Agent Guard
Copy-paste configuration for popular MCP clients.
INFRAVEIL_GUARD_THRESHOLDSeverity at/above which an action is gated: none|low|medium|high|critical (default high).
INFRAVEIL_GUARD_MODEenforce (block dangerous actions pending approval) or audit (log only, never block). Default enforce.
INFRAVEIL_GUARD_HOMEDirectory for the ledger and approval queue (default ~/.infraveil-guard).
{
"mcpServers": {
"agent-guard": {
"command": "uvx",
"args": [
"infraveil-guard"
],
"env": {
"INFRAVEIL_GUARD_THRESHOLD": "<YOUR_INFRAVEIL_GUARD_THRESHOLD>",
"INFRAVEIL_GUARD_MODE": "<YOUR_INFRAVEIL_GUARD_MODE>",
"INFRAVEIL_GUARD_HOME": "<YOUR_INFRAVEIL_GUARD_HOME>"
}
}
}
}Related MCP servers

Infraveil Control Plane
Govern your backend control plane from your AI agent - signed, human-approval-gated.

io.github.ingressward/mcp-server
Block prompt injection, evasive spacing, and obscene content before it reaches your LLM.

io.github.inkog-io/inkog
Security co-pilot for AI agents. Scan for vulnerabilities, audit MCP servers, verify governance.
Stop your agent before it runs rm -rf /etc or emails your .env. Deterministic preflight checks.

eBPF-based GPU causal observability with 7 MCP tools for AI-assisted GPU debugging
View repository →
Exec Sandbox
Single exec tool running caller Python in a network-isolated locked-down sandbox.