run_research_cell
Run a bounded re-analysis cell for a DeepTrace entity investigation. Queries existing DeepTrace state through parallel branches (evidence gap analysis, counter-hypothesis, dimension coverage, source diversification) to surface gaps and weaknesses. Does NOT acquire new external evidence — use due-...
This record as markdown: /tools/io-github-homenshum-nodebench/run-research-cell.md
What run_research_cell does on Nodebench
AI agents invoke run_research_cell to trigger actions in Nodebench. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why run_research_cell is rated High
This tool executes analysis logic across multiple branches (evidence gap analysis, counter-hypothesis, dimension coverage, source diversification) to process and re-analyze existing data. While it does not acquire new external evidence or modify underlying state, it runs bounded computational procedures that execute analysis code paths determined by input parameters.
From the tool's definition 'Run a bounded re-analysis cell' and 'Queries existing DeepTrace state through parallel branches' indicate active code/query execution.
Attacks that exploit this kind of access
The rule that runs run_research_cell 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 run_research_cell, this is the rule to start with:
run_research_cell stays usable, but rate-capped: a runaway agent can't fire it dozens of times 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 run_research_cell call is checked against it from then on.
Questions about run_research_cell
Run a bounded re-analysis cell for a DeepTrace entity investigation. Queries existing DeepTrace state through parallel branches (evidence gap analysis, counter-hypothesis, dimension coverage, source diversification) to surface gaps and weaknesses. Does NOT acquire new external evidence — use due-diligence orchestrator for that. Triggers when confidence is low, coverage is sparse, or operator requests deeper analysis. Returns merged findings in standard DeepTrace format with receipts and dimension profile. It is categorised as a Execute tool in the Nodebench MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Nodebench MCP server in PolicyLayer and add a rule for run_research_cell: 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.
run_research_cell is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the run_research_cell 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 run_research_cell. 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.
run_research_cell 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.
Across the catalogue