grammar_check_vro
AI agents call grammar_check_vro 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.
Grammar checking is fundamentally a read operation—it analyzes input text and returns diagnostic information (errors, suggestions) with no side effects on data. The empty description slightly lowers confidence, but the tool name and cohort of linguisitic analysis tools on the server strongly indicate this is a benign, read-only utility for language processing.
From the tool's definition Tool name 'grammar_check_vro' indicates a grammar checking function for the Võro language; alongside sibling tools like 'analyze_word', 'check_setup', 'count_text', 'find_unknown_words', and 'lookup_word', this is clearly a read-only analysis tool.
Attacks that exploit this kind of access
grammar_check_vro. 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 grammar_check_vro: 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.
grammar_check_vro 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 grammar_check_vro 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 grammar_check_vro. 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.
grammar_check_vro 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 →