mcpbeat Sign in

AgentGuard MCP Server

by merchantguard Your server? Claim it
local only

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.

Installs per day peak 608 · avg 57 · +410% w/w
a month agotoday
195
Installs / week
npm · @agentguard-run/mcp
0
Stars
0 open issues
21 Sep 2026
Last commit
0 releases in 90 days
custom licence
License
JavaScript

Nothing serious here today

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.

Three servers free · no card

Connect this server

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.

run in your terminal
claude mcp add agentguard -- npx -y @agentguard-run/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "agentguard": {
      "args": [
        "-y",
        "@agentguard-run/mcp"
      ],
      "command": "npx"
    }
  }
}
~/.codex/config.toml
[mcp_servers.agentguard]
command = "npx"
args = ["-y", "@agentguard-run/mcp"]
.cursor/mcp.json
{
  "mcpServers": {
    "agentguard": {
      "args": [
        "-y",
        "@agentguard-run/mcp"
      ],
      "command": "npx"
    }
  }
}
.vscode/mcp.json
{
  "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.

Alternatives to AgentGuard

same job, measured the same way
Agent Wallet
by dingdawg

Governed USDC wallet for AI agents — policy gates, spending caps, and Ed25519-signed receipts.

35 installs/wk local only
Protect MCP
by scopeblind

Fail-closed Cedar policy gate + Ed25519 signed receipts for agent tool calls. Denies on any error.

local only
Ccs MCP Server
by dshcorrectover

Runtime verification for agent tool calls: Ed25519 signed receipts, fail-closed RCE/SSRF checks.

265 installs/wk local only
agentguard
by agentwares

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

52 installs/wk local only
Agent Receipts
by webaesbyamin

Ed25519-signed receipts for every AI agent action. Local-first, verifiable, no server required.

52 installs/wk local only
Protect MCP
by tomjwxf

Signed receipts and Cedar policies for AI agent tool calls. Claude Code hooks, MCP gateway.

1 760 installs/wk local only
Covenant Guard
by opencovenant

Hard spend cap, OS sandbox, and signed receipts for unattended coding agents like Claude Code.

local only
agentguard — policy proxy for agent tool calls
by agentwares

Free spend report from an agent log, no key. Hosted proxies: caps, audit export, buy calls.

7 tools answering

AgentGuard — questions

Answers built from our own checks of this server.

Why is there no uptime for AgentGuard?
AgentGuard runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the npm package @agentguard-run/mcp was installed 195 times last week.
How do I connect AgentGuard?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls @agentguard-run/mcp straight from npm; nothing to host, nothing to sign up for.
How many people use AgentGuard?
The npm package @agentguard-run/mcp was installed 195 times in the last week. Week over week that is +410%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is AgentGuard open source?
No, and the distinction matters: it ships its own licence file rather than a standard open-source licence. That makes it source-available — you can read the code, but the terms are the author's own, not one of the recognised open-source licences. Read them before you build on it.