find_unknown_words
AI agents call find_unknown_words to retrieve information from Võro MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to query and identify unknown/unrecognized words in text—a read-only operation with no side effects. No data is created, modified, deleted, or executed. The empty description lowers confidence slightly, but the naming pattern and sibling tools strongly suggest it retrieves or classifies linguistic data rather than modifying it.
From the tool's definition Tool name 'find_unknown_words' indicates a search/identification operation similar to sibling tools 'find_estonian_leakage', 'find_unrecognized_words', and 'find_usage_examples', all of which are read-only query operations.
Attacks that exploit this kind of access
find_unknown_words. It is categorised as a Read tool in the Võro MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Võro MCP Server MCP server in PolicyLayer and add a rule for find_unknown_words: 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 Võro MCP Server. Nothing to install.
find_unknown_words 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 find_unknown_words 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 find_unknown_words. 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.
find_unknown_words is provided by the Võro MCP Server MCP server (leo-martin-pala/voro-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 →