get_trajectory_summary
Compute a trajectory summary for a date range: event counts by type, diff counts by change type, path step counts, and top affected entities.
This record as markdown: /tools/io-github-homenshum-nodebench/get-trajectory-summary.md
What get_trajectory_summary does on Nodebench
AI agents call get_trajectory_summary 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_trajectory_summary is rated Low
This tool retrieves and aggregates historical data (events, diffs, paths, entities) for analysis within a date range. It is a read-only query operation that computes summaries without side effects or mutations. No code execution, data modification, deletion, or financial operations are involved.
From the tool's definition Tool performs 'Compute a trajectory summary' with aggregations of 'event counts', 'diff counts', 'path step counts', and 'top affected entities' — all retrieval and summarization operations with no modification, deletion, or execution of external systems.
Attacks that exploit this kind of access
The rule that runs get_trajectory_summary 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_trajectory_summary, this is the rule to start with:
get_trajectory_summary 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_trajectory_summary call is checked against it from then on.
Questions about get_trajectory_summary
Compute a trajectory summary for a date range: event counts by type, diff counts by change type, path step counts, and top affected entities. 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_trajectory_summary: 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_trajectory_summary 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_trajectory_summary 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_trajectory_summary. 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_trajectory_summary 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