cosmic-mcp

All servers

agentguard

io.github.agentwares/agentguard · version 0.1.9

Community listing. Not installed or verified by cosmic-mcp. Read the source and its permissions before you run it.

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

https://github.com/agentwares/agentguard

Quick facts

  • Listing: Community
  • Published Oct 7, 23:59 UTC
  • Transport: stdio
  • Package: npm @agentwares/agentguard 0.1.9
  • Listed by cosmic-mcp: Nov 8, 18:59 UTC

Security

Setup snippets

Generated from the registry entry. cosmic-mcp has not run or reviewed this server; values in angle brackets are yours to fill in.

Run it locally (npm)

npx -y '@agentwares/[email protected]'

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "agentguard": {
      "args": [
        "-y",
        "@agentwares/[email protected]"
      ],
      "command": "npx",
      "env": {
        "AGENTGUARD_CONFIG": "<your agentguard config>",
        "AGENTGUARD_KILL": "<your agentguard kill>"
      }
    }
  }
}

Claude Code

claude mcp add 'agentguard' -- npx -y '@agentwares/[email protected]'

Cursor (.cursor/mcp.json)

{
  "mcpServers": {
    "agentguard": {
      "args": [
        "-y",
        "@agentwares/[email protected]"
      ],
      "command": "npx",
      "env": {
        "AGENTGUARD_CONFIG": "<your agentguard config>",
        "AGENTGUARD_KILL": "<your agentguard kill>"
      }
    }
  }
}

VS Code (.vscode/mcp.json)

{
  "servers": {
    "agentguard": {
      "args": [
        "-y",
        "@agentwares/[email protected]"
      ],
      "command": "npx",
      "env": {
        "AGENTGUARD_CONFIG": "<your agentguard config>",
        "AGENTGUARD_KILL": "<your agentguard kill>"
      },
      "type": "stdio"
    }
  }
}

Related servers

  • AgentTrust — Identity & Trust for A2A Agents Verified domain
    Identity, trust, and A2A orchestration for autonomous AI agents. Official A2A partner.
  • 13FLOW
    Source-linked SEC 13F research, quality checks, watchlists and audit trails for agents.
  • 1Claw Vault
    HSM-backed vault secrets for AI agents (JIT fetch) plus prompt-injection and threat scanning.
  • 212medya Growth Check Verified domain
    Audit a public website for B2B marketing readiness and AI search visibility.
  • 3ilm-mcp
    Search 1,032 verified smart contract vulnerability findings from Sherlock audits by pattern.
  • 402shield
    x402 payment security and pre-execution transaction risk screening for autonomous AI agents.