AgentGuard runs on your own machine — the client starts it, so there is no endpoint to ping. 195 installs a week from npm. Last commit 21 Sep 2026.
Local spend caps, kill-switch blocking and Ed25519-signed receipts for AI agent tool calls.
Today is the operative word: we check AgentGuard every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
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 agentguard -- npx -y @agentguard-run/mcp
{
"mcpServers": {
"agentguard": {
"args": [
"-y",
"@agentguard-run/mcp"
],
"command": "npx"
}
}
}
[mcp_servers.agentguard]
command = "npx"
args = ["-y", "@agentguard-run/mcp"]
{
"mcpServers": {
"agentguard": {
"args": [
"-y",
"@agentguard-run/mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"agentguard": {
"args": [
"-y",
"@agentguard-run/mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
AGENTGUARD_MCP_DAILY_CAP_CENTS (Local daily spend cap in cents. A nonnegative integer.), AGENTGUARD_MCP_PER_CALL_CAP_CENTS (Local per-call spend cap in cents. A nonnegative integer.), AGENTGUARD_MCP_TENANT (Tenant identifier stamped into local receipts.), AGENTGUARD_HOME (Local signing-key, configuration and ledger directory. Defaults to .agentguard in the operating system home directory.), AGENTGUARD_MCP_LEDGER (Local decision storage. ndjson persists receipts across restarts; memory retains this process only.), AGENTGUARD_MCP_DISABLE_COST_OVERRIDE (Set to 1 to discard and prevent model pricing overrides for this server.), AGENTGUARD_LOCK_COST_OVERRIDES (Spend SDK startup lock. Set to 1 to prevent model pricing overrides.), AGENTGUARD_ACTOR_DIGEST (Set to 1 to hash actor identifiers before they enter local receipts.), AGENTGUARD_LICENSE_KEY (Optional AgentGuard license key for license validation and seat registration. Otherwise read from local configuration.), AGENTGUARD_LICENSE_ENDPOINT (License and seat service base URL. No prompts, tool content or receipts are sent.), AGENTGUARD_NO_BEACON (Set to 1 to disable optional activation telemetry regardless of saved consent.), AGENTGUARD_TELEMETRY (Set to 1 to opt in to content-free activation telemetry. Otherwise saved consent applies, default off.), AGENTGUARD_INSTALL_ID (Optional identifier used only by opted-in activation telemetry when no saved install identifier exists.), AGENTGUARD_ANONYMOUS_INSTALL_ID (Legacy fallback for AGENTGUARD_INSTALL_ID in opted-in activation telemetry.), CI (Existing runtime marker. A nonempty value marks opted-in activation telemetry as CI; it does not enable telemetry.), GITHUB_ACTIONS (Existing runtime marker. A nonempty value marks opted-in activation telemetry as CI; it does not enable telemetry.), GITLAB_CI (Existing runtime marker. A nonempty value marks opted-in activation telemetry as CI; it does not enable telemetry.), CIRCLECI (Existing runtime marker. A nonempty value marks opted-in activation telemetry as CI; it does not enable telemetry.), BUILDKITE (Existing runtime marker. A nonempty value marks opted-in activation telemetry as CI; it does not enable telemetry.), VERCEL (Existing runtime marker. A nonempty value marks opted-in activation telemetry as CI; it does not enable telemetry.), NETLIFY (Existing runtime marker. A nonempty value marks opted-in activation telemetry as CI; it does not enable telemetry.).
The author declared them in the registry entry; get the values from the project itself.
Governed USDC wallet for AI agents — policy gates, spending caps, and Ed25519-signed receipts.
Fail-closed Cedar policy gate + Ed25519 signed receipts for agent tool calls. Denies on any error.
Runtime verification for agent tool calls: Ed25519 signed receipts, fail-closed RCE/SSRF checks.
MCP policy proxy: spend caps, approvals for destructive tools, kill switch, dry-run, audit log.
Ed25519-signed receipts for every AI agent action. Local-first, verifiable, no server required.
Signed receipts and Cedar policies for AI agent tool calls. Claude Code hooks, MCP gateway.
Hard spend cap, OS sandbox, and signed receipts for unattended coding agents like Claude Code.
Free spend report from an agent log, no key. Hosted proxies: caps, audit export, buy calls.
Answers built from our own checks of this server.