searchThreads
Full-text search across narrative threads by keyword.
This record as markdown: /tools/io-github-homenshum-nodebench/searchthreads.md
What searchThreads does on Nodebench
AI agents call searchThreads 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 searchThreads is rated Low
This tool performs a read-only full-text search operation. It retrieves or queries data (narrative threads) without creating, modifying, deleting, or executing any operations. The keyword-based search is inherently a retrieval function with no ability to alter state, making it a Read category risk with low severity.
From the tool's definition Tool name 'searchThreads' and description 'Full-text search across narrative threads by keyword' indicates a search/query operation with no side effects.
Attacks that exploit this kind of access
The rule that runs searchThreads 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 searchThreads, this is the rule to start with:
searchThreads 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 searchThreads call is checked against it from then on.
Questions about searchThreads
Full-text search across narrative threads by keyword. 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 searchThreads: 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.
searchThreads 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 searchThreads 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 searchThreads. 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.
searchThreads 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