This record as markdown: /tools/io-github-portel-dev-ncp/retrieve.md
What retrieve does on Ncp
AI agents call retrieve 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 retrieve is rated Low
The 'retrieve' tool performs a read-only operation—searching and filtering existing jobs and executions. There is no indication of data modification, deletion, execution of commands, or financial transactions. This is a straightforward query/fetch operation with no blast radius beyond potential information disclosure.
From the tool's definition Tool name 'retrieve' and description 'Get jobs and/or executions with search and filtering' indicate data retrieval operations without modification or side effects.
Attacks that exploit this kind of access
The rule that runs retrieve 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 retrieve, this is the rule to start with:
retrieve 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 retrieve call is checked against it from then on.
Questions about retrieve
Get jobs and/or executions with search and filtering. 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 retrieve: 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.
retrieve 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 retrieve 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 retrieve. 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.
retrieve 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