visualize_graph
Open interactive HTML graph in browser showing file/symbol dependencies. Supports force/hierarchical/radial layouts, community coloring. Use granularity=symbol to see individual functions/classes/methods as nodes instead of files. Writes an HTML file to disk. For static Mermaid/DOT output use get...
This record as markdown: /tools/nikolai-vysotskyi-trace-mcp/visualize-graph.md
What visualize_graph does on Trace
AI agents invoke visualize_graph to trigger actions in Trace. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why visualize_graph is rated High
This tool performs two notable actions: it writes an HTML file to disk (a filesystem side effect) and opens it in the browser (triggering an external operation). While the primary purpose is visualization/read, the act of writing files and launching browser processes makes this Execute rather than Read.
From the tool's definition 'Open interactive HTML graph in browser' and 'Writes an HTML file to disk' — the tool triggers a browser action and writes a file to the filesystem
Attacks that exploit this kind of access
The rule that runs visualize_graph safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Trace, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For visualize_graph, this is the rule to start with:
visualize_graph stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Trace, apply this rule, and every visualize_graph call is checked against it from then on.
Questions about visualize_graph
Open interactive HTML graph in browser showing file/symbol dependencies. Supports force/hierarchical/radial layouts, community coloring. Use granularity=symbol to see individual functions/classes/methods as nodes instead of files. Writes an HTML file to disk. For static Mermaid/DOT output use get_dependency_diagram instead. Returns JSON: { outputPath, nodes, edges }. It is categorised as a Execute tool in the Trace MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Trace MCP server in PolicyLayer and add a rule for visualize_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 Trace. Nothing to install.
visualize_graph is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the visualize_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 visualize_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.
visualize_graph is provided by the Trace MCP server (nikolai-vysotskyi/trace-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Trace, and thousands of servers like it.
Across the catalogue