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 AgentGuard MCP server?
Local spend caps, kill-switch blocking and Ed25519-signed receipts for AI agent tool calls.
How to install AgentGuard
Copy-paste configuration for popular MCP clients.
AGENTGUARD_MCP_DAILY_CAP_CENTSLocal daily spend cap in cents. A nonnegative integer.
AGENTGUARD_MCP_PER_CALL_CAP_CENTSLocal per-call spend cap in cents. A nonnegative integer.
AGENTGUARD_MCP_TENANTTenant identifier stamped into local receipts.
AGENTGUARD_HOMELocal signing-key, configuration and ledger directory. Defaults to .agentguard in the operating system home directory.
AGENTGUARD_MCP_LEDGERLocal decision storage. ndjson persists receipts across restarts; memory retains this process only.
AGENTGUARD_MCP_DISABLE_COST_OVERRIDESet to 1 to discard and prevent model pricing overrides for this server.
AGENTGUARD_LOCK_COST_OVERRIDESSpend SDK startup lock. Set to 1 to prevent model pricing overrides.
AGENTGUARD_ACTOR_DIGESTSet to 1 to hash actor identifiers before they enter local receipts.
AGENTGUARD_LICENSE_KEYsecretOptional AgentGuard license key for license validation and seat registration. Otherwise read from local configuration.
AGENTGUARD_LICENSE_ENDPOINTLicense and seat service base URL. No prompts, tool content or receipts are sent.
AGENTGUARD_NO_BEACONSet to 1 to disable optional activation telemetry regardless of saved consent.
AGENTGUARD_TELEMETRYSet to 1 to opt in to content-free activation telemetry. Otherwise saved consent applies, default off.
AGENTGUARD_INSTALL_IDOptional identifier used only by opted-in activation telemetry when no saved install identifier exists.
AGENTGUARD_ANONYMOUS_INSTALL_IDLegacy fallback for AGENTGUARD_INSTALL_ID in opted-in activation telemetry.
CIExisting runtime marker. A nonempty value marks opted-in activation telemetry as CI; it does not enable telemetry.
GITHUB_ACTIONSExisting runtime marker. A nonempty value marks opted-in activation telemetry as CI; it does not enable telemetry.
GITLAB_CIExisting runtime marker. A nonempty value marks opted-in activation telemetry as CI; it does not enable telemetry.
CIRCLECIExisting runtime marker. A nonempty value marks opted-in activation telemetry as CI; it does not enable telemetry.
BUILDKITEExisting runtime marker. A nonempty value marks opted-in activation telemetry as CI; it does not enable telemetry.
VERCELExisting runtime marker. A nonempty value marks opted-in activation telemetry as CI; it does not enable telemetry.
NETLIFYExisting runtime marker. A nonempty value marks opted-in activation telemetry as CI; it does not enable telemetry.
{
"mcpServers": {
"agentguard": {
"command": "npx",
"args": [
"-y",
"@agentguard-run/mcp"
],
"env": {
"AGENTGUARD_MCP_DAILY_CAP_CENTS": "<YOUR_AGENTGUARD_MCP_DAILY_CAP_CENTS>",
"AGENTGUARD_MCP_PER_CALL_CAP_CENTS": "<YOUR_AGENTGUARD_MCP_PER_CALL_CAP_CENTS>",
"AGENTGUARD_MCP_TENANT": "<YOUR_AGENTGUARD_MCP_TENANT>",
"AGENTGUARD_HOME": "<YOUR_AGENTGUARD_HOME>",
"AGENTGUARD_MCP_LEDGER": "<YOUR_AGENTGUARD_MCP_LEDGER>",
"AGENTGUARD_MCP_DISABLE_COST_OVERRIDE": "<YOUR_AGENTGUARD_MCP_DISABLE_COST_OVERRIDE>",
"AGENTGUARD_LOCK_COST_OVERRIDES": "<YOUR_AGENTGUARD_LOCK_COST_OVERRIDES>",
"AGENTGUARD_ACTOR_DIGEST": "<YOUR_AGENTGUARD_ACTOR_DIGEST>",
"AGENTGUARD_LICENSE_KEY": "<YOUR_AGENTGUARD_LICENSE_KEY>",
"AGENTGUARD_LICENSE_ENDPOINT": "<YOUR_AGENTGUARD_LICENSE_ENDPOINT>",
"AGENTGUARD_NO_BEACON": "<YOUR_AGENTGUARD_NO_BEACON>",
"AGENTGUARD_TELEMETRY": "<YOUR_AGENTGUARD_TELEMETRY>",
"AGENTGUARD_INSTALL_ID": "<YOUR_AGENTGUARD_INSTALL_ID>",
"AGENTGUARD_ANONYMOUS_INSTALL_ID": "<YOUR_AGENTGUARD_ANONYMOUS_INSTALL_ID>",
"CI": "<YOUR_CI>",
"GITHUB_ACTIONS": "<YOUR_GITHUB_ACTIONS>",
"GITLAB_CI": "<YOUR_GITLAB_CI>",
"CIRCLECI": "<YOUR_CIRCLECI>",
"BUILDKITE": "<YOUR_BUILDKITE>",
"VERCEL": "<YOUR_VERCEL>",
"NETLIFY": "<YOUR_NETLIFY>"
}
}
}
}Related MCP servers
Local-first supply-chain security gate for npm/pnpm/bun: typosquat, release age, provenance checks
Scan AI agents for tool-calling vulnerabilities: prompt leaks, hijacking, injections, and more.
Agent governance with A2A/Shopify/MCP trust audits, action screening, and decision UI.
UK compliance documentation for the EU AI Act, Worker Protection Act 2024, and UK GDPR.
Generic MCP server for calling x402-protected APIs with automatic payment handling
View repository →
PraisonAI
Build autonomous, self-reflecting AI agents and connect them to any MCP server in minutes.

