get_tool_graph
Returns a JSON graph of tool relationships that grows with usage.
This record as markdown: /tools/io-github-homenshum-nodebench/get-tool-graph.md
What get_tool_graph does on Nodebench
AI agents call get_tool_graph 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 get_tool_graph is rated Low
This is a read-only operation that fetches and returns existing data (tool relationship graphs). There is no creation, modification, deletion, execution of external operations, or financial impact. The tool has minimal blast radius if misused by an AI agent — at worst it exposes metadata about tool relationships, which is informational only.
From the tool's definition Tool name and description indicate it 'Returns a JSON graph' — a retrieval operation with no side effects. The phrase 'grows with usage' describes how the graph data accumulates over time, but the tool itself only queries/retrieves this information.
Attacks that exploit this kind of access
The rule that runs get_tool_graph 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 get_tool_graph, this is the rule to start with:
get_tool_graph 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 get_tool_graph call is checked against it from then on.
Questions about get_tool_graph
Returns a JSON graph of tool relationships that grows with usage. 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 get_tool_graph: 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.
get_tool_graph 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 get_tool_graph 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 get_tool_graph. 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.
get_tool_graph 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