json_select

Select a sub-value from a local JSON file using a JSON Pointer (RFC 6901) and return a bounded preview. Deterministic, no network.

SERVERNodebench SOURCEnodebench-mcp

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-homenshum-nodebench/json-select.md

WHAT IT DOES

What json_select does on Nodebench

AI agents call json_select to retrieve information from Nodebench without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

RISK

Why json_select is rated Low

The tool reads and returns a portion of a local JSON file using a pointer path. It is purely a read/query operation with no side effects, no network access, and no data modification. Severity is low as it only exposes local file content, bounded by a preview.

From the tool's definition 'Select a sub-value from a local JSON file using a JSON Pointer (RFC 6901) and return a bounded preview. Deterministic, no network.'

Attacks that exploit this kind of access

RECOMMENDED RULE

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

json_select Allowed

json_select is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "json_select": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

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

FAQ

Questions about json_select

What does the json_select tool do? +

Select a sub-value from a local JSON file using a JSON Pointer (RFC 6901) and return a bounded preview. Deterministic, no network. It is categorised as a Read tool in the Nodebench MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on json_select? +

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

json_select is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit json_select? +

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

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

json_select 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

Roll out MCP under one policy →Data exfiltration →MCP token cost →