gribstream_get_dataset
NO AUTH / PUBLIC / READ-ONLY. Gets full public metadata for one dataset code, including archive coverage, cadence, tags, source links, and members. This tool does not query weather values and cannot return forecast data.
This record as markdown: /tools/com-gribstream-mcp/gribstream-get-dataset.md
What gribstream_get_dataset does on GribStream MCP
AI agents call gribstream_get_dataset to retrieve information from GribStream MCP without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
dataset | string | Yes | Dataset code, for example gfs, nbm, ifsoper, hrrr, urma. |
Parameters from the server's own tool schema.
Why gribstream_get_dataset is rated Low
This is a straightforward metadata retrieval operation with no capability to modify data, execute code, delete information, or access sensitive weather forecasts. It merely returns public information about dataset structure and coverage. The read-only nature and public accessibility make this a low-severity Read operation with minimal risk even if misused by an AI agent.
From the tool's definition Tool description explicitly states 'NO AUTH / PUBLIC / READ-ONLY' and 'Gets full public metadata' and 'does not query weather values and cannot return forecast data'. The tool only retrieves dataset metadata without side effects.
Attacks that exploit this kind of access
The rule that runs gribstream_get_dataset safely
PolicyLayer is an MCP gateway: it sits between your AI agents and GribStream MCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For gribstream_get_dataset, this is the rule to start with:
gribstream_get_dataset is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect GribStream MCP, apply this rule, and every gribstream_get_dataset call is checked against it from then on.
Questions about gribstream_get_dataset
NO AUTH / PUBLIC / READ-ONLY. Gets full public metadata for one dataset code, including archive coverage, cadence, tags, source links, and members. This tool does not query weather values and cannot return forecast data. It is categorised as a Read tool in the GribStream MCP MCP Server, which means it retrieves data without modifying state.
gribstream_get_dataset accepts 1 parameter: dataset. Required: dataset. The full parameter table on this page comes from the server's own tool schema.
Register the GribStream MCP server in PolicyLayer and add a rule for gribstream_get_dataset: 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 GribStream MCP. Nothing to install.
gribstream_get_dataset 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 gribstream_get_dataset 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 gribstream_get_dataset. 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.
gribstream_get_dataset is provided by the GribStream MCP server (https://gribstream.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on GribStream, and thousands of servers like it.
This server
Across the catalogue