Safety audit trail
Preview — part of the MCP Gateway private beta. Join the waitlist →
The audit trail answers one question — "did this server try anything?" — with evidence. It's a forensic log of what every server did and what the sandbox blocked.
What it records
| Event | Meaning |
|---|---|
connect |
A server was connected, with the capabilities it was granted |
tool_call |
A tool ran, and whether it succeeded |
tool_blocked |
A tool was refused by policy |
egress_blocked |
An outbound connection was refused, with the target host |
egress_allowed |
An allowlisted connection was permitted |
disconnect |
A server was torn down |
It records what was contained — not your arguments, results, or secrets. It's a security artifact, distinct from usage analytics.
Querying
From any client, use the mcp_audit meta-tool. For the security-reviewer view — only blocks and errored calls:
Use mcp_audit with securityOnly true
Durable log
Set an environment variable to append every event to a JSONL file you can ship to a SIEM:
MCP_GATEWAY_AUDIT_LOG=/var/log/mcp-audit.jsonl npx @mcprating/gateway
See also
- Egress allowlist — the source of
egress_blockedevents.