AI agents call gva_query to retrieve information from MCP4GVA without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
gva_query performs data retrieval and filtering operations against a geographic database. While it does not modify or delete data (Read category, not Write/Destructive/Execute), the severity is medium rather than low because: (1) geographic/land activity data may be sensitive or have privacy implications, (2) SQL-like query capabilities could potentially be leveraged for information gathering to identify valuable…
From the tool's definition Tool description states 'Query features from the GVA GIS layer with SQL-like WHERE clause and optional parameters' - this is a retrieval operation with no mention of modifications, deletions, or side effects.
Attacks that exploit this kind of access
Query features from the GVA GIS layer with SQL-like WHERE clause and optional parameters. It is categorised as a Read tool in the MCP4GVA MCP Server, which means it retrieves data without modifying state.
Register the MCP4GVA MCP server in PolicyLayer and add a rule for gva_query: 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 MCP4GVA. Nothing to install.
gva_query 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 gva_query 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 gva_query. 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.
gva_query is provided by the MCP4GVA MCP server (pepo1275/mcp4gva). 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 →