create_visual_pr

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/create-visual-pr.md

WHAT IT DOES

What create_visual_pr does on Nodebench

AI agents use create_visual_pr 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 create_visual_pr is rated Medium

The tool pushes code to a remote repository and creates a GitHub Pull Request. These are write operations (creating a PR, pushing commits) that are reversible (PR can be closed, push can be reverted), but the blast radius is high because it modifies remote repository state and could expose unintended code changes or trigger CI/CD pipelines.

From the tool's definition creates a GitHub PR via... pushes, and creates a GitHub PR

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs create_visual_pr 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 create_visual_pr, this is the rule to start with:

create_visual_pr Rate-limited

create_visual_pr 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": {
    "create_visual_pr": {
      "limits": [
        {
          "counter": "create_visual_pr_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 create_visual_pr call is checked against it from then on.

FAQ

Questions about create_visual_pr

What does the create_visual_pr tool do? +

End-to-end PR creation: exports screenshots, generates a rich markdown PR body with visual evidence (before/after comparisons, timeline, bug fixes, past sessions), checks git state, pushes, and creates a GitHub PR via. 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 create_visual_pr? +

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

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

Can I rate-limit create_visual_pr? +

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

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

create_visual_pr 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

create_task on 0rca Dojo MCP Server →create-task on Kanban MCP Server →create_package_backup on Android Forensics ADB MCP Server →create_project on Stitch MCP Server → The MCP Attack Database →

Guides

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