detect_narrative_voice
AI agents call detect_narrative_voice to retrieve information from BigContext MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to analyze and extract information about narrative voice from documents—a read-only analytical function. No keywords suggesting modification, execution, deletion, or financial operations are present.
From the tool's definition Tool name 'detect_narrative_voice' suggests analysis of existing document content. No description provided, but sibling tools like 'analyze_subdetermination', 'detect_inference_violations', and 'detect_pattern_contamination' are all analytical/read-only…
Attacks that exploit this kind of access
detect_narrative_voice. It is categorised as a Read tool in the BigContext MCP MCP Server, which means it retrieves data without modifying state.
Register the BigContext MCP server in PolicyLayer and add a rule for detect_narrative_voice: 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 BigContext MCP. Nothing to install.
detect_narrative_voice 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 detect_narrative_voice 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 detect_narrative_voice. 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.
detect_narrative_voice is provided by the BigContext MCP server (rixmerz/bigcontext_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 →