This record as markdown: /tools/io-github-portel-dev-ncp/get-prediction.md
What get_prediction does on Ncp
AI agents call get_prediction to retrieve information from Ncp without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why get_prediction is rated Low
This tool retrieves or queries prediction status information with no side effects. It falls squarely into the Read category. The low severity reflects that accessing prediction status poses minimal risk unless the predictions themselves contain highly sensitive information, which is not indicated in the description.
From the tool's definition Tool name 'get_prediction' and description 'Get prediction status' indicate a retrieval operation that queries the state of a prediction without modifying or executing anything.
Attacks that exploit this kind of access
The rule that runs get_prediction safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Ncp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For get_prediction, this is the rule to start with:
get_prediction 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 Ncp, apply this rule, and every get_prediction call is checked against it from then on.
Questions about get_prediction
Get prediction status. It is categorised as a Read tool in the Ncp MCP Server, which means it retrieves data without modifying state.
Register the Ncp MCP server in PolicyLayer and add a rule for get_prediction: 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 Ncp. Nothing to install.
get_prediction 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_prediction 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_prediction. 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_prediction is provided by the Ncp MCP server (@portel/ncp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Ncp, and thousands of servers like it.
This server
Across the catalogue