ソラカメのライブストリーミングURLを取得します
AI agents call get_soracam_stream_url 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.
This tool retrieves a URL for a live camera stream. It only fetches/reads data (a URL) with no side effects. The severity is low as it merely returns an access URL, though that URL could expose camera footage — the act of retrieval itself is a read operation consistent with other sibling tools on this read-focused server.
From the tool's definition get_soracam_stream_url — 'ライブストリーミングURLを取得します' (retrieves the live streaming URL)
Attacks that exploit this kind of access
ソラカメのライブストリーミングURLを取得します. 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_soracam_stream_url: 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_soracam_stream_url 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_soracam_stream_url 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_soracam_stream_url. 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_soracam_stream_url 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 →