AgentGuard by Audiscape

com.audiscape.agentguardPublished by agentguard.audiscape.comOfficial publisherv3.0.0Updated Nov 2, 2026

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

VerifiedStreamable HTTPWeb executableSecurity & MonitoringAI & ML

Overview

AI-generated overview

Remote MCP server that checks an AI agent's tool-call log before each call to stop loops and budget overruns, plus domain HTTP audits and remediation checkout.

What you can do
  • Replay an agent's tool-call log through a loop and budget guard and decide whether the next call should run, catching identical or near-repeat loops, re-reads of finished items, failing-tool retry streaks and USD or token caps before spend.
  • Run a live HTTP audit against a public domain and get a score, grade and report URL.
  • Fetch a remediation preview and scorecard URL for a domain.
  • Create a Stripe checkout link for a domain's remediation pack.
When to use it
Useful when an agent runs long tool-call sessions and you want a pre-call check that halts repeated loops or stops spend once token or USD caps are reached. The domain audit tools suit quick HTTP checks of a public site with an optional paid remediation pack.
Requirements
A remote streamable HTTP endpoint; no local package, environment variables or headers are declared. The manifest declares no authentication and the description says no signup. Network access to the endpoint is required.
Before you install
The guard tool receives your agent's tool-call log, which may contain file paths, URLs and commands, and sends it to a third-party service. One tool returns a Stripe checkout link for a paid remediation pack, so review pricing before paying. The audit tools act on public domains and return report URLs.

Installation

In SourceWeft

  1. Open AgentGuard by Audiscape in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/com.audiscape.agentguard%2Fagentguard/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "agentguard-by-audiscape": {
      "type": "http",
      "url": "https://agentguard.audiscape.com/mcp"
    }
  }
}

Tools

4

audit_domain

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

Parametersmodedomainrequired

get_remediation_preview

Return the remediation preview and scorecard URL for a domain.

Parametersdomainrequired

create_checkout_session

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

Parametersmodedomainrequired

guard_check_session

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.

Parametersnextrequiredcallsrequiredconfig

Version history

1
  1. v3.0.0LatestNov 1, 2026

Score

72% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts

    Publish an icon in the registry entry.

  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.