1Write flow rules
Add privacy_policy.flows to agentleak.yaml: who may receive which data type, and for what purpose. The CI gate already reads the same rules.
2Wrap the server
In your MCP client configuration, launch agentleak proxy with the real server command after --.
3Let calls through
Permitted flows pass, refused values are redacted, and denied flows are blocked with a reason the agent can act on.
4Verify the evidence
Run agentleak evidence to summarize decisions and check that no entry in the chain was altered.
Guard an MCP server
{
"mcpServers": {
"github": {
"command": "agentleak",
"args": ["proxy", "--config", "agentleak.yaml",
"--evidence", "evidence.jsonl", "--",
"npx", "-y", "@modelcontextprotocol/server-github"]
}
}
}
Read the complete implementation guide →