AI agents call openInstallation to retrieve information from KotorMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool explicitly states it is read-only and does not write to disk. It builds an in-memory snapshot of a game installation and returns a handle for further queries, which is purely a data retrieval/indexing operation with no side effects.
From the tool's definition 'Build or reuse a compacted in-memory installation snapshot and return a handle for paged follow-up queries. Read-only; does not write to disk.'
Attacks that exploit this kind of access
Build or reuse a compacted in-memory installation snapshot and return a handle for paged follow-up queries. Read-only; does not write to disk. It is categorised as a Read tool in the KotorMCP MCP Server, which means it retrieves data without modifying state.
Register the Kotor MCP server in PolicyLayer and add a rule for openInstallation: 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 KotorMCP. Nothing to install.
openInstallation 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 openInstallation 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 openInstallation. 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.
openInstallation is provided by the Kotor MCP server (th3w1zard1/kotormcp). 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 →