Agent Utility MCP

io.github.insivotronPublished by GitHub account insivotronv0.3.0Updated Oct 24, 2026

Stop your agent before it runs rm -rf /etc or emails your .env. Deterministic preflight checks.

VerifiedStreamable HTTPWeb executableSecurity & Monitoring

Overview

AI-generated overview

A remote MCP endpoint that runs deterministic preflight checks so an agent's risky actions can be stopped before they execute.

What you can do
Agent Utility MCP is a remote streamable HTTP server that provides deterministic preflight checks for agent actions. According to its registry description, it is meant to catch dangerous operations before they run, with examples such as deleting system files or sending a secrets file. No tool list is published, so the exact checks and their inputs are not documented here.
When to use it
Consider it when an assistant can execute commands or send data and you want a guard step that evaluates an action before it happens. It may suit setups where destructive shell commands or outbound messages need a deterministic block rather than a model judgement.
Requirements
A remote MCP client that supports streamable HTTP, connecting to the provider's hosted endpoint. No packages, environment variables, headers, or authentication are declared, so no credentials appear to be needed.
Before you install
The endpoint is third party and hosted remotely, so whatever you send it for checking leaves your machine; the description gives no detail on logging or retention. No authentication is declared, so treat it as a public endpoint and do not send secrets or sensitive file contents to it. The published description is short and no tool list is available, so verify what it actually inspects before relying on it as a safety barrier.

Installation

In SourceWeft

  1. Open Agent Utility MCP 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/io.github.insivotron%2Fagent-utility-mcp/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": {
    "agent-utility": {
      "type": "http",
      "url": "https://agent-utility-mcp.insivotron.workers.dev/mcp"
    }
  }
}

Tools

4

analyze_url_risk

Analyze a URL for structural and security risk signals and return a deterministic, policy-aware decision (allow, notice, confirm or block) under the applicable policy — permissive, balanced or strict, balanced by default.

Parametersurlrequiredpolicycontext

inspect_command

Analyze a shell command before execution and return a deterministic, policy-aware decision (allow, notice, confirm or block) without running it, under the applicable policy — permissive, balanced or strict, balanced by default. Paths outside a known workspace_root are treated as higher risk than paths inside it.

Parameterscwdshellpolicycommandrequiredcontext

inspect_file

Inspect a Base64-encoded file locally for deterministic structural and security risk signals without executing it, and return a policy-aware decision (allow, notice, confirm or block) under the applicable policy — permissive, balanced or strict, balanced by default.

Parameterspolicycontextfilenamerequiredcontent_base64required

analyze_tool_call

Analyze a proposed AI-agent tool call before execution and return a deterministic, policy-aware decision (allow, notice, confirm or block) covering destructive actions, sensitive-data exposure, external transmission, privilege changes and irreversible operations, under the applicable policy — permissive, balanced or strict, balanced by default. Filesystem paths outside a known workspace_root are treated as higher risk than paths inside it.

Parameterspolicycontextargumentsrequiredtool_namerequired

Version history

1
  1. v0.3.0LatestSep 16, 2026

Score

83% 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
  • 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.