AI agents call litopys_search 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.
This tool only reads and searches existing data in the knowledge graph. It returns search results without creating, modifying, deleting, or executing any operations. Full-text search is a classic Read category operation. The low severity reflects minimal blast radius — search results cannot cause harm unless downstream tools misuse them, but the search itself is passive.
From the tool's definition Tool performs 'Full-text search' with 'Returns ranked hits' — a retrieval operation with no modification or side effects. Description explicitly indicates query/search functionality without data mutation.
Attacks that exploit this kind of access
Full-text search over the Litopys knowledge graph. Returns ranked hits by name, alias, body, and tags. 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_search: 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_search 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_search 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_search. 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_search 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 →