run_recon
Start a reconnaissance research session. Use this at the start of Phase 1 (Context Gathering) to organize research into external sources (SDKs, APIs, blogs) AND internal context (codebase, project details, existing patterns). Returns a structured research plan with suggested sources and context-g...
This record as markdown: /tools/io-github-homenshum-nodebench/run-recon.md
What run_recon does on Nodebench
AI agents invoke run_recon 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_recon is rated High
The tool triggers a reconnaissance operation that reaches out to external sources (SDKs, APIs, blogs) and accesses internal context (codebase, project details). This is an Execute action because it initiates a defined process with side effects—organizing and gathering data from multiple sources—rather than a simple Read query.
From the tool's definition Tool performs 'Start a reconnaissance research session' which initiates an external operation that 'organize[s] research into external sources (SDKs, APIs, blogs) AND internal context (codebase, project details)'.
Attacks that exploit this kind of access
The rule that runs run_recon 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_recon, this is the rule to start with:
run_recon 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_recon call is checked against it from then on.
Questions about run_recon
Start a reconnaissance research session. Use this at the start of Phase 1 (Context Gathering) to organize research into external sources (SDKs, APIs, blogs) AND internal context (codebase, project details, existing patterns). Returns a structured research plan with suggested sources and context-gathering questions. 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_recon: 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_recon 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_recon 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_recon. 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_recon 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