get_harvest_data
AI agents call get_harvest_data to retrieve information from SORACOM Data Reader MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears designed to retrieve Harvest sensor data from the SORACOM IoT platform. The get_ prefix, context of sibling read-only tools, and lack of any modification/deletion semantics in the server description indicate this is a query/retrieval operation with no side effects.
From the tool's definition Tool name 'get_harvest_data' and sibling tools all prefixed with 'get_' or 'export_' indicating retrieval operations. Server description states tools enable 'access to SORACOM IoT platform data' with no mention of modification or deletion capabilities.
Attacks that exploit this kind of access
get_harvest_data. It is categorised as a Read tool in the SORACOM Data Reader MCP MCP Server, which means it retrieves data without modifying state.
Register the SORACOM Data Reader MCP server in PolicyLayer and add a rule for get_harvest_data: 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 SORACOM Data Reader MCP. Nothing to install.
get_harvest_data 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 get_harvest_data 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 get_harvest_data. 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.
get_harvest_data is provided by the SORACOM Data Reader MCP server (leaveanest/alt-soracom-data-reader-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 →