delta_retain
Preserve context for future sessions. Produces a delta.retain packet storing important notes, decisions, meeting outcomes, or research findings that should persist across sessions.
This record as markdown: /tools/io-github-homenshum-nodebench/delta-retain.md
What delta_retain does on Nodebench
AI agents use delta_retain to create or update resources in Nodebench, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Nodebench environment.
Why delta_retain is rated Medium
This tool writes/stores data (notes, decisions, findings) that persists across sessions. It creates a new stored artifact (delta.retain packet), which is a reversible write operation. Misuse could lead to polluting persistent context with incorrect or misleading information, hence medium severity.
From the tool's definition Preserve context for future sessions. Produces a delta.retain packet storing important notes, decisions, meeting outcomes, or research findings that should persist across sessions.
Attacks that exploit this kind of access
The rule that runs delta_retain 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_retain, this is the rule to start with:
delta_retain stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. 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_retain call is checked against it from then on.
Questions about delta_retain
Preserve context for future sessions. Produces a delta.retain packet storing important notes, decisions, meeting outcomes, or research findings that should persist across sessions. It is categorised as a Write tool in the Nodebench MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Nodebench MCP server in PolicyLayer and add a rule for delta_retain: 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_retain is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the delta_retain 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_retain. 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_retain 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