link_durable_objects

Create a durable relationship such as screen -> action, workflow -> run, run -> artifact, or outcome -> evidence.

SERVERNodebench SOURCEnodebench-mcp

Medium RISK CLASS

Category Write

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-homenshum-nodebench/link-durable-objects.md

WHAT IT DOES

What link_durable_objects does on Nodebench

AI agents use link_durable_objects to create or update resources in Nodebench, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Nodebench environment.

RISK

Why link_durable_objects is rated Medium

The tool creates persistent relationships/links between entities. This is a write operation that modifies data by establishing durable associations. It is reversible in principle (links can typically be removed), so it does not qualify as Destructive. Severity is medium as misuse could create incorrect or misleading relationships between workflow artifacts.

From the tool's definition Create a durable relationship such as screen -> action, workflow -> run, run -> artifact, or outcome -> evidence.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs link_durable_objects safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Nodebench, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For link_durable_objects, this is the rule to start with:

link_durable_objects Rate-limited

link_durable_objects stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "link_durable_objects": {
      "limits": [
        {
          "counter": "link_durable_objects_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Nodebench, apply this rule, and every link_durable_objects call is checked against it from then on.

FAQ

Questions about link_durable_objects

What does the link_durable_objects tool do? +

Create a durable relationship such as screen -> action, workflow -> run, run -> artifact, or outcome -> evidence. 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 link_durable_objects? +

Register the Nodebench MCP server in PolicyLayer and add a rule for link_durable_objects: 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 link_durable_objects? +

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

Can I rate-limit link_durable_objects? +

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

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

link_durable_objects 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.

KEEP EXPLORING

More on Nodebench, and thousands of servers like it.

This server

All 824 Nodebench tools →

Across the catalogue

The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →