Get directions between two points
AI agents call maps_directions to retrieve information from Helm Chart CLI without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves directional data between geographic points, which is a passive information query with no side effects, reversible actions, code execution, data destruction, or financial implications. It is clearly a Read category tool with low severity since misuse would only result in retrieval of navigation data.
From the tool's definition Tool name 'maps_directions' and description 'Get directions between two points' indicate a read-only query operation that retrieves routing information without modifying data or executing arbitrary code.
Attacks that exploit this kind of access
Get directions between two points. It is categorised as a Read tool in the Helm Chart CLI MCP Server, which means it retrieves data without modifying state.
Register the Helm Chart CLI MCP server in PolicyLayer and add a rule for maps_directions: 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 Helm Chart CLI. Nothing to install.
maps_directions 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 maps_directions 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 maps_directions. 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.
maps_directions is provided by the Helm Chart CLI MCP server (jeff-nasseri/servers). 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 →