FTS5 keyword search over all ingested exchanges.
AI agents call stenographer_query_history to retrieve information from Omega Stenographer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical data through full-text search without creating, modifying, executing, or deleting anything. It is purely informational and represents a read-only query operation over ingested conversation data.
From the tool's definition Tool performs 'FTS5 keyword search over all ingested exchanges' — a passive query operation with no modification or execution capabilities. The name and description indicate retrieval/searching functionality only.
Attacks that exploit this kind of access
FTS5 keyword search over all ingested exchanges. It is categorised as a Read tool in the Omega Stenographer MCP Server, which means it retrieves data without modifying state.
Register the Omega Stenographer MCP server in PolicyLayer and add a rule for stenographer_query_history: 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 Omega Stenographer. Nothing to install.
stenographer_query_history 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 stenographer_query_history 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 stenographer_query_history. 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.
stenographer_query_history is provided by the Omega Stenographer MCP server (vrtxomega/omega-stenographer-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 →