Accountable Autonomy: open-source evidence layer that gates every AI agent tool call against your policy and writes a hash-chained record an auditor verifies offline, without trusting you. Root-agnostic; binds to TPM 2.0 / SEV-SNP when present. Your environment, no SaaS, no telemetry. AGPL-3.0.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add vaara -- uvx vaara --upstream '<UPSTREAM>'~/.codex/config.toml
[mcp_servers.vaara]
command = "uvx"
args = ["vaara", "--upstream", "<UPSTREAM>"]
# codex mcp add vaara -- uvx vaara --upstream '<UPSTREAM>'~/.cursor/mcp.json
{
"mcpServers": {
"vaara": {
"command": "uvx",
"args": [
"vaara",
"--upstream",
"<UPSTREAM>"
]
}
}
}.vscode/mcp.json
{
"servers": {
"vaara": {
"type": "stdio",
"command": "uvx",
"args": [
"vaara",
"--upstream",
"<UPSTREAM>"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"vaara": {
"command": "uvx",
"args": [
"vaara",
"--upstream",
"<UPSTREAM>"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"vaara": {
"command": "uvx",
"args": [
"vaara",
"--upstream",
"<UPSTREAM>"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"vaara": {
"command": "uvx",
"args": [
"vaara",
"--upstream",
"<UPSTREAM>"
]
}
}
}