Extract entities and relationships from text using NLP
AI agents call extract_entities to retrieve information from r3 (Recall) without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Entity extraction is a read-only NLP operation that analyzes input text to identify and categorize entities and their relationships. It retrieves semantic information from data but does not create, modify, delete, or execute code. The tool has no side effects on stored data or external systems.
From the tool's definition The tool 'extract_entities' with description 'Extract entities and relationships from text using NLP' performs text analysis and information extraction without modifying, deleting, or executing external operations.
Attacks that exploit this kind of access
Extract entities and relationships from text using NLP. It is categorised as a Read tool in the r3 (Recall) MCP Server, which means it retrieves data without modifying state.
Register the r3 (Recall) MCP server in PolicyLayer and add a rule for extract_entities: 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 r3 (Recall). Nothing to install.
extract_entities 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 extract_entities 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 extract_entities. 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.
extract_entities is provided by the r3 (Recall) MCP server (n3wth/r3). 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 →