inspect_topology_shape
Inspect the persisted Convex topology shape for the Reports graph. Use this after search_memory/search_report_context when deciding whether to expand a dense Mapper cluster, inspect an outlier, or reuse first-ring graph context before live search. Returns density, PCA, centroid/outlier, clusters,...
This record as markdown: /tools/io-github-homenshum-nodebench/inspect-topology-shape.md
What inspect_topology_shape does on Nodebench
AI agents call inspect_topology_shape 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 inspect_topology_shape is rated Low
This tool queries and analyzes persisted topology data to inform retrieval decisions. It retrieves structural analysis of a graph but does not modify, execute external operations, or cause destructive effects. It is a Read operation with low blast radius if misused by an agent.
From the tool's definition Tool returns topology metadata: 'density, PCA, centroid/outlier, clusters, neighbors, and recommended retrieval actions.' The description states 'inspect' and 'Returns' (passive retrieval), with no write/execute/delete operations mentioned.
Attacks that exploit this kind of access
The rule that runs inspect_topology_shape 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 inspect_topology_shape, this is the rule to start with:
inspect_topology_shape 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 inspect_topology_shape call is checked against it from then on.
Questions about inspect_topology_shape
Inspect the persisted Convex topology shape for the Reports graph. Use this after search_memory/search_report_context when deciding whether to expand a dense Mapper cluster, inspect an outlier, or reuse first-ring graph context before live search. Returns density, PCA, centroid/outlier, clusters, neighbors, and recommended retrieval actions. 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 inspect_topology_shape: 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.
inspect_topology_shape 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 inspect_topology_shape 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 inspect_topology_shape. 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.
inspect_topology_shape 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