InnerVault

AgentGuard

Stale Official MCP Registry, io.github.MerchantGuard

Local spend caps, kill-switch blocking and Ed25519-signed receipts for AI agent tool calls.

Open the source (opens github.com) https://github.com/merchantguard/agentguard-mcp

Before you use it

  • Runs on your computer with your permissions. Read what it can do before connecting it to an agent.
  • Needs credentials: AGENTGUARD_LICENSE_KEY. Use a key with the least access you can.

What it is

MCP servers from io.github.MerchantGuard.

The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.

How to get it

npm package (stdio)

@agentguard-run/mcp@0.3.1

From the server's entry in the official MCP Registry

Settings it asks for

  • 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 secret · 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.

Related

  1. agentguard

    MCP servers

    AgentGuard — 20-tool AI safety MCP: policy preflight, risk scoring, audit logging, rate limits.

    Stale Official MCP Registry, io.tooloracle Updated 6 months ago 1 note

  2. agentguard

    MCP servers

    Network-egress firewall for agent tools: check URLs against a declarative policy.

    Stale Official MCP Registry, io.github.MukundaKatta Updated 6 months ago 1 note

    @mukundakatta/agentguard-mcp@0.1.0
  3. agentguard47

    MCP servers

    Read-only MCP server for coding-agent traces, alerts, costs, usage, and budget health.

    Stale Official MCP Registry, io.github.bmdhodl Updated 5 months ago 2 notes

    @agentguard47/mcp-server@0.2.2
  4. Stops runaway AI agent loops and token burn. Checks each tool call before it runs. No signup.

    Stale Official MCP Registry, com.audiscape.agentguard Updated 15 days ago 1 note

  5. agentguard

    MCP servers

    MCP policy proxy: spend caps, approvals for destructive tools, kill switch, dry-run, audit log.

    Stale Official MCP Registry, io.github.agentwares Updated 40 days ago 1 note

    @agentwares/agentguard@0.1.9
  6. Secret, CVE and dependency-vulnerability scanning for AI agents (free, OSV.dev).

    Stale Official MCP Registry, io.github.shuaicongxiaomai Updated 4 months ago 1 note

    ghcr.io/shuaicongxiaomai/agentguard:0.1.2