multi_criteria_score
Deterministic weighted multi-criteria decision analysis (MCDM). Takes options with numeric values per criterion, normalizes using min-max scaling, applies directional weights, and returns ranked results. No LLM involved — purely mathematical. Use for travel booking optimization, investment compar...
This record as markdown: /tools/io-github-homenshum-nodebench/multi-criteria-score.md
What multi_criteria_score does on Nodebench
AI agents call multi_criteria_score 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.
Why multi_criteria_score is rated Low
This tool is a mathematical decision-analysis function that reads input data, applies algorithmic weighting and normalization, and outputs scores or rankings. It does not create, modify, or delete data; does not execute code or shell commands; does not move money; and has no external side effects. The description explicitly states 'No LLM involved — purely mathematical,' confirming it is a deterministic computation.
From the tool's definition Tool performs 'deterministic weighted multi-criteria decision analysis' with 'normalizes using min-max scaling, applies directional weights, and returns ranked results.' No modifications, deletions, code execution, or financial transactions are performed.
Attacks that exploit this kind of access
The rule that runs multi_criteria_score 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 multi_criteria_score, this is the rule to start with:
multi_criteria_score is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Nodebench, apply this rule, and every multi_criteria_score call is checked against it from then on.
Questions about multi_criteria_score
Deterministic weighted multi-criteria decision analysis (MCDM). Takes options with numeric values per criterion, normalizes using min-max scaling, applies directional weights, and returns ranked results. No LLM involved — purely mathematical. Use for travel booking optimization, investment comparison, vendor selection, or any multi-attribute decision. Supports custom classification thresholds (e.g., points-per-cent valuation tiers). It is categorised as a Read tool in the Nodebench MCP Server, which means it retrieves data without modifying state.
Register the Nodebench MCP server in PolicyLayer and add a rule for multi_criteria_score: 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.
multi_criteria_score is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the multi_criteria_score 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.
Set action: deny in the PolicyLayer policy for multi_criteria_score. 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.
multi_criteria_score 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.
More on Nodebench, and thousands of servers like it.
This server
Across the catalogue