export
Export current NCP configuration. Use clipboard for security (no chat history), response for transparency.
This record as markdown: /tools/io-github-portel-dev-ncp/export.md
What export does on Ncp
AI agents call export 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 export is rated Low
The tool reads and exports the current NCP configuration, which is a read/query operation with no side effects. However, it carries medium severity because configuration data may contain sensitive credentials, API keys, or architectural details that could be exploited if exposed. The note about using clipboard 'for security (no chat history)' reinforces that the exported data is sensitive.
From the tool's definition Export current NCP configuration. Use clipboard for security (no chat history), response for transparency.
Attacks that exploit this kind of access
The rule that runs export 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 export, this is the rule to start with:
export 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 export call is checked against it from then on.
Questions about export
Export current NCP configuration. Use clipboard for security (no chat history), response for transparency. 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 export: 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.
export 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 export 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 export. 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.
export 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