nb_filter_receipts
Filter action receipts by channel, policy, approval state, or direction.
This record as markdown: /tools/io-github-homenshum-nodebench/nb-filter-receipts.md
What nb_filter_receipts does on Nodebench
AI agents call nb_filter_receipts 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 nb_filter_receipts is rated Low
The tool retrieves or queries receipts based on specified filter criteria. Filtering is a read-only operation that does not create, modify, delete, or execute external actions. The output is determined by the input criteria, not execution of arbitrary logic. This poses minimal risk in the context of AI agent misuse.
From the tool's definition Tool performs filtering of receipts by channel, policy, approval state, or direction—classic querying/retrieval operation with no data modification or deletion.
Attacks that exploit this kind of access
The rule that runs nb_filter_receipts 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_filter_receipts, this is the rule to start with:
nb_filter_receipts 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 nb_filter_receipts call is checked against it from then on.
Questions about nb_filter_receipts
Filter action receipts by channel, policy, approval state, or direction. 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 nb_filter_receipts: 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.
nb_filter_receipts 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 nb_filter_receipts 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 nb_filter_receipts. 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.
nb_filter_receipts 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