AI agents use litopys_link to create or update resources in Litopys — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Litopys environment.
litopys_link creates or modifies relational connections within persistent memory storage. While reversible (relations can presumably be removed), this is a state-changing Write operation that could alter how an AI agent's knowledge graph is structured.
From the tool's definition Tool description states 'Add a relation from source node to target node' — this creates new data (relations/links) in the graph-based memory system. The no-op behavior on existing relations confirms it modifies state.
Attacks that exploit this kind of access
Add a relation from source node to target node. No-op if the relation already exists. It is categorised as a Write tool in the Litopys MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Litopys MCP server in PolicyLayer and add a rule for litopys_link: 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_link is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the litopys_link 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_link. 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_link 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 →