Medium Risk

upsert_durable_object

Register or update a durable local object so views, tools, workflows, runs, artifacts, and outcomes share one replayable identity spine.

Part of the Nodebench server.

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

SECURE NODEBENCH →

Free to start. No card required.

AI agents use upsert_durable_object to create or modify resources in Nodebench. 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 upsert_durable_object 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 Nodebench.

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

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

See the full Nodebench policy for all 724 tools.

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

ENFORCE ON MY NODEBENCH →

View all 724 tools →

These attack patterns abuse exactly the kind of access upsert_durable_object 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 upsert_durable_object only ever does what you allow.

SECURE NODEBENCH →

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

What does the upsert_durable_object tool do? +

Register or update a durable local object so views, tools, workflows, runs, artifacts, and outcomes share one replayable identity spine.. It is categorised as a Write tool in the Nodebench MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on upsert_durable_object? +

Register the Nodebench MCP server in PolicyLayer and add a rule for upsert_durable_object: 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 Nodebench. Nothing to install.

What risk level is upsert_durable_object? +

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

Can I rate-limit upsert_durable_object? +

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

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

upsert_durable_object is provided by the Nodebench MCP server (nodebench-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Nodebench tool call.

Deterministic rules across all 724 Nodebench 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.