AI agents call get_alternatives to retrieve information from Disvr without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about alternative tools based on tool status. It has no side effects, does not modify data, and does not execute external operations. It is a read-only query operation that helps users discover backup options when a tool is unhealthy.
From the tool's definition Tool returns alternatives for a degraded tool; no modification, deletion, or execution of external operations. Description indicates 'returns' (query/retrieval operation).
Attacks that exploit this kind of access
Get healthy alternatives for a degraded or dead tool. Returns empty if the tool is healthy. It is categorised as a Read tool in the Disvr MCP Server, which means it retrieves data without modifying state.
Register the Disvr MCP server in PolicyLayer and add a rule for get_alternatives: 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 Disvr. Nothing to install.
get_alternatives 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 get_alternatives 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 get_alternatives. 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.
get_alternatives is provided by the Disvr MCP server (svanik-yan/disvr). 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 →