AgentGuard by Audiscape

Stops runaway AI agent loops and token burn. Checks each tool call before it runs. No signup.

Should I use this

Quality & Safety

A
Description quality
95%
Schema completeness
84%
Naming quality
95%
Poisoning risk
100%
Permission match
100%
Protocol compliance
100%

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~620Tokens (tool definitions)
~1.2 KBTypical response size
Minimal attention impact (0.48% of 128k context)

This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.

Install

One-Click Install

Add this to your `claude_desktop_config.json` file:

{
  "mcpServers": {
    "agentguard": {
      "url": "https://agentguard.audiscape.com/mcp"
    }
  }
}

Remote endpoints

https://agentguard.audiscape.com/mcpstreamable-http

What it can do

Tool inventory

Tools (4)

🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
🟢guard_check_session(calls, next, config)

Call before each tool call your agent makes. Send the calls so far and the one you are about to make, get back allowed true or false with the reason. Catches identical and near-repeat loops (same file, URL or command), re-reads of finished items, failing-tool retry streaks and USD or token caps before spend. Free, no account, arguments are not stored, nothing is executed. Smallest valid call: {"calls":[],"next":{"tool":"bash"}}

Input Schema

{
  "type": "object",
  "properties": {
    "calls": {
      "type": "array",
      "maxItems": 20000,
      "items": {
        "type": "object",
        "properties": {
          "tool": {
            "type": "string"
          },
          "arguments": {},
          "isError": {
            "type": "boolean"
          },
          "costUsd": {
            "type": "number",
            "minimum": 0
          },
          "totalCostUsd": {
            "type": "number",
            "minimum": 0,
            "description": "Running session spend so far; spend becomes max(spend, total)"
          },
          "totalTokens": {
            "type": "number",
            "minimum": 0,
            "description": "Running session tokens so far"
          },
          "tokens": {
            "type": "number",
            "minimum": 0
          },
          "errorText": {
            "type": "string",
            "description": "Error message when isError; permanent errors (missing binary, 4xx, quota, permission) halt after 1 retry"
          },
          "readOnly": {
            "type": "boolean",
            "description": "Call had no side effects; lets the opt-in completed-read rule apply"
          },
          "resultHash": {
            "type": "string",
            "description": "Stable hash of the tool result; repeats with the same hash count as no progress"
          }
        },
        "required": [
          "tool"
        ]
      }
    },
    "next": {
      "type": "object",
      "properties": {
        "tool": {
          "type": "string"
        },
        "arguments": {}
      },
      "required": [
        "tool"
      ]
    },
    "config": {
      "type": "object",
      "description": "Optional agentguard.json contents"
    }
  },
  "required": [
    "next"
  ],
  "examples": [
    {
      "calls": [],
      "next": {
        "tool": "bash"
      }
    }
  ]
}
⚪audit_domain(domain, mode)

Run a live HTTP audit against a public domain and return score, grade and report URL.

Input Schema

{
  "type": "object",
  "properties": {
    "domain": {
      "type": "string",
      "description": "Target domain, e.g. cursor.com"
    },
    "mode": {
      "type": "string",
      "enum": [
        "citerank",
        "checkoutguard",
        "agentguard",
        "signalstrike"
      ]
    }
  },
  "required": [
    "domain"
  ]
}
🟢get_remediation_preview(domain)

Return the remediation preview and scorecard URL for a domain.

Input Schema

{
  "type": "object",
  "properties": {
    "domain": {
      "type": "string"
    }
  },
  "required": [
    "domain"
  ]
}
🟡create_checkout_session(domain, mode)

Return a Stripe checkout link for the remediation pack for a domain.

Input Schema

{
  "type": "object",
  "properties": {
    "domain": {
      "type": "string"
    },
    "mode": {
      "type": "string",
      "enum": [
        "citerank",
        "checkoutguard",
        "agentguard",
        "signalstrike"
      ]
    }
  },
  "required": [
    "domain"
  ]
}

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded4 tools