Get analytics on prediction quality and patterns for a project
AI agents call get_propagation_stats to retrieve information from Semantic Context MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries analytics data about prediction quality and patterns. It performs a read-only operation with no side effects—no data is created, modified, deleted, or executed. The analytics being retrieved are observational/analytical in nature, making this a pure Read operation with low severity.
From the tool's definition Tool name and description indicate data retrieval only: 'Get analytics on prediction quality and patterns' uses the verb 'Get' and describes fetching analytics/metrics for a project. No modification, deletion, execution, or financial operations are described.
Attacks that exploit this kind of access
Get analytics on prediction quality and patterns for a project. It is categorised as a Read tool in the Semantic Context MCP MCP Server, which means it retrieves data without modifying state.
Register the Semantic Context MCP server in PolicyLayer and add a rule for get_propagation_stats: 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 Semantic Context MCP. Nothing to install.
get_propagation_stats 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_propagation_stats 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_propagation_stats. 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_propagation_stats is provided by the Semantic Context MCP server (semanticintent/semantic-wake-intelligence-mcp). 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 →