Other · Local MCP server
AgentGuard
Local spend caps, kill-switch blocking and Ed25519-signed receipts for AI agent tool calls.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.MerchantGuard/agentguard- Version
- 0.3.1
- Status
- Active
- Category
- other
- Transport
- stdio (local process)
- Package
- npm
- Published
- 2026-09-21
- Updated
- 2026-09-21
- Publisher
- MerchantGuard (GitHub)
- Website
- agentguard.run
- Repository
- github.com/MerchantGuard/agentguard-mcp
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| npmruntime: npx | @agentguard-run/mcp | 0.3.1 | stdio |
How to connect AgentGuard
AgentGuard runs locally from a Node.js package published to the npm registry: @agentguard-run/mcp version 0.3.1. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Node.js; clients usually start it with npx — the usual command is npx -y @agentguard-run/mcp@0.3.1. It reads these environment variables: AGENTGUARD_MCP_DAILY_CAP_CENTS, AGENTGUARD_MCP_PER_CALL_CAP_CENTS, AGENTGUARD_MCP_TENANT, AGENTGUARD_HOME, AGENTGUARD_MCP_LEDGER, AGENTGUARD_MCP_DISABLE_COST_OVERRIDE, AGENTGUARD_LOCK_COST_OVERRIDES, AGENTGUARD_ACTOR_DIGEST, AGENTGUARD_LICENSE_KEY (secret), AGENTGUARD_LICENSE_ENDPOINT, AGENTGUARD_NO_BEACON, AGENTGUARD_TELEMETRY, AGENTGUARD_INSTALL_ID, AGENTGUARD_ANONYMOUS_INSTALL_ID, CI, GITHUB_ACTIONS, GITLAB_CI, CIRCLECI, BUILDKITE and VERCEL; set them in the client's configuration for this server.
In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):
{
"mcpServers": {
"agentguard": {
"command": "npx",
"args": [
"-y",
"@agentguard-run/mcp@0.3.1"
],
"env": {
"AGENTGUARD_MCP_DAILY_CAP_CENTS": "<value>",
"AGENTGUARD_MCP_PER_CALL_CAP_CENTS": "<value>",
"AGENTGUARD_MCP_TENANT": "<value>",
"AGENTGUARD_HOME": "<value>",
"AGENTGUARD_MCP_LEDGER": "<value>",
"AGENTGUARD_MCP_DISABLE_COST_OVERRIDE": "<value>",
"AGENTGUARD_LOCK_COST_OVERRIDES": "<value>",
"AGENTGUARD_ACTOR_DIGEST": "<value>",
"AGENTGUARD_LICENSE_KEY": "<secret>",
"AGENTGUARD_LICENSE_ENDPOINT": "<value>",
"AGENTGUARD_NO_BEACON": "<value>",
"AGENTGUARD_TELEMETRY": "<value>",
"AGENTGUARD_INSTALL_ID": "<value>",
"AGENTGUARD_ANONYMOUS_INSTALL_ID": "<value>",
"CI": "<value>",
"GITHUB_ACTIONS": "<value>",
"GITLAB_CI": "<value>",
"CIRCLECI": "<value>",
"BUILDKITE": "<value>",
"VERCEL": "<value>"
}
}
}
}Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More other servers
| Server | Runs |
|---|---|
| AgentExchangeStackExchange-style Q&A network where AI agents ask, answer, critique, and earn reputation. | Remote · HTTP |
| AgentFEMBuild, run, inspect, and verify finite-element simulations with AgentFEM. | Local · stdio |
| Agentfuse MCPAffiliate API for AI agents -- browse programs, generate tracked links, record conversions. | Local · stdio |
| AgentGateHuman-in-the-loop approval gateway for AI agents over MCP: request, decide, approve. | Local · stdio |
| AgentguardNetwork-egress firewall for agent tools: check URLs against a declarative policy. | Local · stdio |
| Agentic Commerce ReadinessScore a Magento or Adobe Commerce store on eight AI agent-readiness checks. | Remote · HTTP |
| Agentic Design SystemRender web and SwiftUI evidence, run explicit visual judgment, and trace ADS UI decisions. | Local · stdio |
| Agentic Diaries AuditChecks what a support agent knew but did not say against its policies. Free tier, no login. | Remote · HTTP |