Update Allowed Tools

🌐Community
by vinta · vlatest · Repository

This skill dynamically updates the list of available tools, ensuring your agent always has access to the latest functionalities and improving its performance.

Install on your platform

We auto-selected Claude Code based on this skill’s supported platforms.

1

Run in terminal (recommended)

terminal
claude mcp add update-allowed-tools npx -- -y @trustedskills/update-allowed-tools
2

Or manually add to ~/.claude/settings.json

~/.claude/settings.json
{
  "mcpServers": {
    "update-allowed-tools": {
      "command": "npx",
      "args": [
        "-y",
        "@trustedskills/update-allowed-tools"
      ]
    }
  }
}

Requires Claude Code (claude CLI). Run claude --version to verify your install.

About This Skill

What it does

This skill allows you to dynamically modify the list of tools an AI agent is permitted to use at runtime. It provides a mechanism to enable or disable specific capabilities without changing the core agent configuration, offering flexible control over what actions the agent can perform in a given session.

When to use it

  • You need to restrict an agent's access to certain tools for security reasons during a specific task.
  • You want to test how an agent performs with a subset of available tools without redeploying the entire system.
  • You are building a multi-stage workflow where different phases require different toolsets.
  • You need to temporarily disable a problematic or expensive tool while keeping the agent active.

Key capabilities

  • Dynamically updates the allowed tools list for an AI agent instance.
  • Enables fine-grained control over agent behavior by toggling specific tool permissions.
  • Supports runtime adjustments without requiring code changes or restarts.

Example prompts

  • "Update the allowed tools to only include search and read_file, removing all others."
  • "Disable the execute_code tool for this session due to security constraints."
  • "Add browser_use and send_email to the list of allowed tools for this agent."

Tips & gotchas

Ensure you have administrative access to the agent configuration before attempting to modify tool permissions. Changes made via this skill are typically temporary and may reset when the agent session ends or is restarted, so document any critical restrictions accordingly.

Tags

🛡️

TrustedSkills Verification

Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.

Security Audits

Gen Agent Trust HubPass
SocketPass
SnykPass

Details

Version
vlatest
License
Author
vinta
Installs
33

🌐 Community

Passed automated security scans.