delta_review
Reconcile a forecast or recommendation against reality. Produces a delta.review packet so the next decision uses outcomes instead of memory drift.
This record as markdown: /tools/io-github-homenshum-nodebench/delta-review.md
What delta_review does on Nodebench
AI agents call delta_review 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 delta_review is rated Low
This tool reads and compares historical forecast data against actual results to generate an informational delta review packet. While it processes data, it does not modify the underlying forecast or recommendation data, delete anything, execute external commands, or move money. The primary function is analysis and comparison—characteristic of Read operations.
From the tool's definition Tool performs reconciliation and analysis of forecasts/recommendations against actual outcomes, producing a review packet.
Attacks that exploit this kind of access
The rule that runs delta_review 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 delta_review, this is the rule to start with:
delta_review 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 delta_review call is checked against it from then on.
Questions about delta_review
Reconcile a forecast or recommendation against reality. Produces a delta.review packet so the next decision uses outcomes instead of memory drift. 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 delta_review: 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.
delta_review 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 delta_review 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 delta_review. 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.
delta_review 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