Cross-project topic tunnels: links between registered subprojects that share canonical entities — package names from manifests (package.json / composer.json / pyproject.toml / Cargo.toml / go.mod), declared dependencies (top-level only), and human contributors from
AI agents call detect_topic_tunnels 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 performs static analysis and navigation of code dependencies and relationships. It reads manifest files and dependency declarations to identify connections between projects, which is a read-only operation. There is no mutation of data, execution of code, deletion, or financial transaction. The scope is limited to understanding project topology, making it low severity with high confidence.
From the tool's definition The tool 'detect_topic_tunnels' retrieves and analyzes links between subprojects by examining 'canonical entities — package names from manifests...declared dependencies...and human contributors'.
Documented attack patterns abuse exactly the kind of access detect_topic_tunnels 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 detect_topic_tunnels:
{
"version": "1",
"default": "deny",
"tools": {
"detect_topic_tunnels": {}
}
}detect_topic_tunnels 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.
Cross-project topic tunnels: links between registered subprojects that share canonical entities — package names from manifests (package.json / composer.json / pyproject.toml / Cargo.toml / go.mod), declared dependencies (top-level only), and human contributors from. 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 detect_topic_tunnels: 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.
detect_topic_tunnels 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 detect_topic_tunnels 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 detect_topic_tunnels. 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.
detect_topic_tunnels 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.