query_knowledge_base
Read everything recorded so far for a target: JS assets, endpoints, roles, role access, tokens, business flows, third parties, client observations, and notes. Call this first when switching into a mode or resuming work on a target.
This record as markdown: /tools/intellirecon-console/query-knowledge-base.md
What query_knowledge_base does on Intellirecon Console
AI agents call query_knowledge_base to retrieve information from Intellirecon Console without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why query_knowledge_base is rated Low
This tool retrieves and queries previously collected reconnaissance data without side effects. It is clearly a Read operation. Severity is medium rather than low because the data it accesses (tokens, roles, endpoints, business flows) could be sensitive information valuable in an attack chain, making misuse moderately damaging even though the tool itself performs no destructive actions.
From the tool's definition Tool description explicitly states "Read everything recorded so far" and lists data retrieval activities: JS assets, endpoints, roles, tokens, business flows, etc. No modification, deletion, or execution capabilities mentioned.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The rule that runs query_knowledge_base safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Intellirecon Console, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For query_knowledge_base, this is the rule to start with:
query_knowledge_base 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 Intellirecon Console, apply this rule, and every query_knowledge_base call is checked against it from then on.
Questions about query_knowledge_base
Read everything recorded so far for a target: JS assets, endpoints, roles, role access, tokens, business flows, third parties, client observations, and notes. Call this first when switching into a mode or resuming work on a target. It is categorised as a Read tool in the Intellirecon Console MCP Server, which means it retrieves data without modifying state.
Register the Intellirecon Console MCP server in PolicyLayer and add a rule for query_knowledge_base: 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 Intellirecon Console. Nothing to install.
query_knowledge_base 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 query_knowledge_base 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 query_knowledge_base. 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.
query_knowledge_base is provided by the Intellirecon Console MCP server (dokotela021/intellirecon-console). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Intellirecon Console, and thousands of servers like it.
This server
Across the catalogue