Henter relationer mellem to moduler
AI agents call list_relations to retrieve information from Tracelink MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves relationship data between modules without creating, modifying, deleting, or executing any operations. This is a straightforward data query operation with minimal blast radius if misused by an AI agent.
From the tool's definition Tool name 'list_relations' and description 'Henter relationer mellem to moduler' (retrieves relations between two modules) indicate a query/retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Henter relationer mellem to moduler. It is categorised as a Read tool in the Tracelink MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Tracelink MCP Server MCP server in PolicyLayer and add a rule for list_relations: 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 Tracelink MCP Server. Nothing to install.
list_relations 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 list_relations 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 list_relations. 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.
list_relations is provided by the Tracelink MCP Server MCP server (tracelink-devops/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →