scan_capabilities
Analyze a source file for structural code patterns. Returns a capability report showing what the code can structurally DO — state management (hooks, refs, reducers), layout (overlay, sidebar, grid, responsive), interactions (keyboard, drag-drop, clipboard, voice, touch), rendering (markdown, code...
This record as markdown: /tools/io-github-homenshum-nodebench/scan-capabilities.md
What scan_capabilities does on Nodebench
AI agents call scan_capabilities 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 scan_capabilities is rated Low
This tool reads and inspects source code to extract and categorize structural patterns (state management, layout, interactions, rendering, backend patterns). It performs static analysis only—no code execution, no data modification, no destructive operations. The explicit mention of 'pure regex analysis, no LLM needed' confirms it is a passive inspection tool.
From the tool's definition The tool performs 'pure regex analysis' to 'Analyze a source file for structural code patterns' and returns 'a capability report showing what the code can structurally DO'.
Attacks that exploit this kind of access
The rule that runs scan_capabilities 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 scan_capabilities, this is the rule to start with:
scan_capabilities 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 scan_capabilities call is checked against it from then on.
Questions about scan_capabilities
Analyze a source file for structural code patterns. Returns a capability report showing what the code can structurally DO — state management (hooks, refs, reducers), layout (overlay, sidebar, grid, responsive), interactions (keyboard, drag-drop, clipboard, voice, touch), rendering (markdown, code highlighting, math, streaming), and backend patterns (REST routes, middleware, DB queries, auth guards, WebSocket). Pure regex analysis, no LLM needed. 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 scan_capabilities: 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.
scan_capabilities 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 scan_capabilities 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 scan_capabilities. 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.
scan_capabilities 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