object_custom_request · Zadara Storage MCP Server MCP

WHAT IT DOES

What object_custom_request does on Zadara Storage MCP Server

AI agents invoke object_custom_request to trigger actions in Zadara Storage MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why object_custom_request needs a policy

This tool allows arbitrary API requests to Object Storage, meaning it can perform any operation including reads, writes, deletions, or financial actions depending on the endpoint called. Since it enables arbitrary execution against a storage system with no described constraints, it must be classified at the most severe applicable category.

From the tool's definition Make a custom API request to Object Storage. Use this for endpoints not covered by other tools.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

object_custom_request Rate-limited

object_custom_request stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "object_custom_request": {
      "limits": [
        {
          "counter": "object_custom_request_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Zadara Storage MCP Server, so you can run agents against it safely.

FAQ

Questions about object_custom_request

What does the object_custom_request tool do? +

Make a custom API request to Object Storage. Use this for endpoints not covered by other tools. It is categorised as a Execute tool in the Zadara Storage MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on object_custom_request? +

Register the Zadara Storage MCP Server MCP server in PolicyLayer and add a rule for object_custom_request: 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 Zadara Storage MCP Server. Nothing to install.

What risk level is object_custom_request? +

object_custom_request is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit object_custom_request? +

Yes. Add a rate_limit block to the object_custom_request 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 object_custom_request completely? +

Set action: deny in the PolicyLayer policy for object_custom_request. 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 object_custom_request? +

object_custom_request is provided by the Zadara Storage MCP Server MCP server (zadarastorage/zadara-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.