Medium Risk

update_settings

Update user settings (persisted to ~/.agentcash/settings.json). Currently supports maxAmount — the maximum USD amount allowed per fetch request. If a fetch response requests more than this, the payment is rejected. Returns the current settings after applying changes.

Part of the Agentcash server.

update_settings can modify Agentcash data, with no limits today. PolicyLayer puts allow, deny, and rate-limit rules on every call. Live in minutes.

SECURE AGENTCASH →

Free to start. No card required.

AI agents use update_settings to create or modify resources in Agentcash. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.

Without a policy, an AI agent could call update_settings repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Agentcash.

Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "update_settings": {
      "limits": [
        {
          "counter": "update_settings_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

See the full Agentcash policy for all 11 tools.

Get this rule live on your own Agentcash server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY AGENTCASH →

View all 11 tools →

These attack patterns abuse exactly the kind of access update_settings gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so update_settings only ever does what you allow.

SECURE AGENTCASH →

Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.

What does the update_settings tool do? +

Update user settings (persisted to ~/.agentcash/settings.json). Currently supports maxAmount — the maximum USD amount allowed per fetch request. If a fetch response requests more than this, the payment is rejected. Returns the current settings after applying changes.. It is categorised as a Write tool in the Agentcash MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on update_settings? +

Register the Agentcash MCP server in PolicyLayer and add a rule for update_settings: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Agentcash. Nothing to install.

What risk level is update_settings? +

update_settings is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit update_settings? +

Yes. Add a rate_limit block to the update_settings rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block update_settings completely? +

Set action: deny in the PolicyLayer policy for update_settings. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides update_settings? +

update_settings is provided by the Agentcash MCP server (agentcash). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Agentcash tool call.

Deterministic rules across all 11 Agentcash tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.