Developer · Local MCP server
Agentguard47
Read-only MCP server for coding-agent traces, alerts, costs, usage, and budget health.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.bmdhodl/agentguard47- Version
- 0.2.2
- Status
- Active
- Category
- developer
- Transport
- stdio (local process)
- Package
- npm
- Published
- 2026-05-31
- Updated
- 2026-05-31
- Publisher
- bmdhodl (GitHub)
- Repository
- github.com/bmdhodl/agent47
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| npm | @agentguard47/mcp-server | 0.2.2 | stdio |
How to connect Agentguard47
Agentguard47 runs locally from a Node.js package published to the npm registry: @agentguard47/mcp-server version 0.2.2. 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 @agentguard47/mcp-server@0.2.2. It reads these environment variables: AGENTGUARD_API_KEY (required, secret) and AGENTGUARD_URL; 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": {
"agentguard47": {
"command": "npx",
"args": [
"-y",
"@agentguard47/mcp-server@0.2.2"
],
"env": {
"AGENTGUARD_API_KEY": "<secret>",
"AGENTGUARD_URL": "<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 developer servers
| Server | Runs |
|---|---|
| agentguardMCP policy proxy: spend caps, approvals for destructive tools, kill switch, dry-run, audit log. | Local · stdio |
| AgentguardAgentGuard — 20-tool AI safety MCP: policy preflight, risk scoring, audit logging, rate limits. | Remote · HTTP |
| agentguard — policy proxy for agent tool callsFree spend report from an agent log, no key. Hosted proxies: caps, audit export, buy calls. | Remote · HTTP |
| AgentGuard — security checks for AI agentsSecret, CVE and dependency-vulnerability scanning for AI agents (free, OSV.dev). | Local · stdio |
| agenthostAgent-first web hosting: deploy sites, apps, databases and domains over MCP. | Remote · HTTP |
| Agenthub MonitorRenders a pipeline DAG and test-harness dashboard inline as an MCP App. | Local · stdio |
| Agentic AdsAd network for AI agents — monetize MCP servers with contextual ads. 70% revenue share. | Remote & Local · HTTP, stdio |
| Agentic HILDevelop firmware on the real board behind a debug probe: flash, reset, UART and CAN, policy-gated. | Local · stdio |