nb_search_from_chat

Run a grounded search from the chat surface.

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/nb-search-from-chat.md

WHAT IT DOES

What nb_search_from_chat does on Nodebench

AI agents call nb_search_from_chat 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 nb_search_from_chat is rated Low

This tool performs a search query, which is a read operation that retrieves information without side effects. However, the severity is marked as medium rather than low because the search is 'grounded' (likely cross-referenced against external data sources) and operates from the chat surface, which could potentially expose or surface sensitive information depending on what data sources are being searched.

From the tool's definition Tool name includes 'search' and description states 'Run a grounded search from the chat surface.' Search operations are retrieval-based with no modification or deletion of data.

Attacks that exploit this kind of access

RECOMMENDED RULE

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

nb_search_from_chat Allowed

nb_search_from_chat 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": {
    "nb_search_from_chat": {}
  }
}

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 nb_search_from_chat call is checked against it from then on.

FAQ

Questions about nb_search_from_chat

What does the nb_search_from_chat tool do? +

Run a grounded search from the chat surface. 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 nb_search_from_chat? +

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

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

Can I rate-limit nb_search_from_chat? +

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

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

nb_search_from_chat 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

search_torrents on M-Team MCP Server →aiva_search_customers on AIVA MCP Server →search_channel on YouTube MCP Server →hybrid_search on Azure AI Agent Service + Azure AI Search MCP Server → The MCP Attack Database →

Guides

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