fusionSearch

Multi-source fusion search with reranking. Modes: fast (single source), balanced (2-3 sources), comprehensive (all sources with reranking).

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/fusionsearch.md

WHAT IT DOES

What fusionSearch does on Nodebench

AI agents call fusionSearch 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 fusionSearch is rated Low

fusionSearch retrieves and ranks search results from multiple sources without creating, modifying, deleting, or executing operations. This is a pure data retrieval function with configurable result filtering/ranking, characteristic of Read category tools. Low severity because search results alone pose minimal risk even if an agent misuses them—the tool cannot alter data or trigger external operations.

From the tool's definition Tool performs 'search' across multiple sources with reranking modes (fast, balanced, comprehensive). No modification, deletion, or execution capabilities described. Operates in query/retrieval-only patterns.

Attacks that exploit this kind of access

RECOMMENDED RULE

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

fusionSearch Allowed

fusionSearch 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": {
    "fusionSearch": {}
  }
}

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 fusionSearch call is checked against it from then on.

FAQ

Questions about fusionSearch

What does the fusionSearch tool do? +

Multi-source fusion search with reranking. Modes: fast (single source), balanced (2-3 sources), comprehensive (all sources with reranking). 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 fusionSearch? +

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

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

Can I rate-limit fusionSearch? +

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

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

fusionSearch 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 →