Find architectural bottleneck edges in the import graph: edges sitting on many shortest paths (edge betweenness, Brandes), edges whose removal would disconnect the graph (bridges, Tarjan), and nodes that are single points of failure (articulation points). Score combines structural centrality with...
AI agents call get_edge_bottlenecks to retrieve information from Trace without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool analyzes and queries the dependency graph structure to identify architectural bottlenecks through graph algorithms (betweenness centrality, bridge detection, articulation point analysis). It retrieves computed metrics and returns data for informational purposes only.
From the tool's definition Tool description explicitly states 'Read-only' and performs graph analysis operations: 'Find architectural bottleneck edges', 'edge betweenness', 'bridges', 'articulation points'.
Documented attack patterns abuse exactly the kind of access get_edge_bottlenecks gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Trace, and nothing reaches the server without passing your rules. This is the rule we recommend for get_edge_bottlenecks:
{
"version": "1",
"default": "deny",
"tools": {
"get_edge_bottlenecks": {}
}
}get_edge_bottlenecks is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Find architectural bottleneck edges in the import graph: edges sitting on many shortest paths (edge betweenness, Brandes), edges whose removal would disconnect the graph (bridges, Tarjan), and nodes that are single points of failure (articulation points). Score combines structural centrality with co-change weight (bottleneckScore = betweenness × (1 + coChangeWeight)). Use to identify edges to monitor during refactoring and to prioritize decoupling work. For general importance use get_pagerank instead. Read-only. Returns JSON: { edges: [{ sourceFile, targetFile, betweenness, coChangeWeight, bottleneckScore, isBridge }], articulationPoints: [...], stats }. It is categorised as a Read tool in the Trace MCP Server, which means it retrieves data without modifying state.
Register the Trace MCP server in PolicyLayer and add a rule for get_edge_bottlenecks: 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.
get_edge_bottlenecks 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_edge_bottlenecks 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_edge_bottlenecks. 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_edge_bottlenecks 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.
Deterministic rules across all 178 Trace tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
178 Trace tools catalogued and risk-classified — across an index of 42,500+ MCP servers.