AI agents call litopys_related to retrieve information from Litopys without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
litopys_related retrieves and traverses existing graph data to discover relationships between nodes. It has no side effects, cannot modify the graph structure, and only reads information. The blast radius of misuse is minimal—an agent could learn about relationships in the graph but cannot alter, delete, or execute operations. This is a classic Read operation analogous to 'get' or 'search'.
From the tool's definition Tool performs 'BFS traversal' and 'Returns a subgraph of connected nodes and edges'—a graph query operation with no modification, deletion, or execution of external code.
Attacks that exploit this kind of access
BFS traversal from a node. Returns a subgraph of connected nodes and edges up to the given depth. It is categorised as a Read tool in the Litopys MCP Server, which means it retrieves data without modifying state.
Register the Litopys MCP server in PolicyLayer and add a rule for litopys_related: 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 Litopys. Nothing to install.
litopys_related 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 litopys_related 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 litopys_related. 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.
litopys_related is provided by the Litopys MCP server (litopys-dev/litopys). 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 →