Koskamo

AgentGuard MCP

AgentGuard is a circuit breaker for AI agent loops, retry storms, and budget burn. It wraps MCP servers and LLM gateways to check tool calls before execution, enforcing semantic loop detection, destructive tool gating, and Stripe billing margin enforcement via JSON-RPC 2.0.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

AgentGuard MCP logo, by AudiscapeVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-01Operated by Audiscape
MCP endpoint (Streamable HTTP)
https://agentguard.audiscape.com/mcp
Vendor documentation

What you can do with it

  • Check session tool calls to prevent runaway loops
  • Gate destructive tools behind approval workflows
  • Enforce Stripe billing margin limits per tenant
  • Auto-downgrade negative-margin Stripe tenants

Source and maintenance

Vendor evidenceRegistry 3.0.0
mcp-registry: com.audiscape.agentguard/agentguard@3.0.0Project website

Protocol and capabilities

Server
AgentGuard 3.0.0
MCP protocol
2025-06-18
Tools
4 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": false
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

Call guard_check_session before each tool call with the session's call log to stop loops and budget overruns.

Tools

4 advertised

audit_domain
Advertised by the server during the last successful anonymous check.

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

audit_domain input schema
{
  "type": "object",
  "required": [
    "domain"
  ],
  "properties": {
    "mode": {
      "enum": [
        "citerank",
        "checkoutguard",
        "agentguard",
        "signalstrike"
      ],
      "type": "string"
    },
    "domain": {
      "type": "string",
      "description": "Target domain, e.g. cursor.com"
    }
  }
}
get_remediation_preview
Advertised by the server during the last successful anonymous check.

Return the remediation preview and scorecard URL for a domain.

get_remediation_preview input schema
{
  "type": "object",
  "required": [
    "domain"
  ],
  "properties": {
    "domain": {
      "type": "string"
    }
  }
}
create_checkout_session
Advertised by the server during the last successful anonymous check.

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

create_checkout_session input schema
{
  "type": "object",
  "required": [
    "domain"
  ],
  "properties": {
    "mode": {
      "enum": [
        "citerank",
        "checkoutguard",
        "agentguard",
        "signalstrike"
      ],
      "type": "string"
    },
    "domain": {
      "type": "string"
    }
  }
}
guard_check_session
Advertised by the server during the last successful anonymous check.

Replay an agent's tool-call log through the AgentGuard loop and budget guard and decide whether the next call should run. 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.

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

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
456 ms
95th percentile latency
456 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 456 ms · metadata changed · 4 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http agentguard-mcp-audiscape https://agentguard.audiscape.com/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add agentguard-mcp-audiscape --url https://agentguard.audiscape.com/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable agentguard-mcp-audiscape in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "agentguard-mcp-audiscape": {
      "url": "https://agentguard.audiscape.com/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "agentguard-mcp-audiscape": {
      "type": "streamableHttp",
      "url": "https://agentguard.audiscape.com/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start agentguard-mcp-audiscape and inspect its tools.
VS Code configuration
{
  "servers": {
    "agentguard-mcp-audiscape": {
      "type": "http",
      "url": "https://agentguard.audiscape.com/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http agentguard-mcp-audiscape https://agentguard.audiscape.com/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.
Claude Desktop configuration
{
  "mcpServers": {
    "agentguard-mcp-audiscape": {
      "url": "https://agentguard.audiscape.com/mcp"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "agentguard-mcp-audiscape": {
      "serverUrl": "https://agentguard.audiscape.com/mcp"
    }
  }
}

Let your agent find its tools

Find servers like AgentGuard MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 4,376

Do you run AgentGuard MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing