optimize_client
Back up a supported MCP client configuration and replace its MCP server list with NCP. Requires explicit user confirmation.
This record as markdown: /tools/io-github-portel-dev-ncp/optimize-client.md
What optimize_client does on Ncp
AI agents use optimize_client to create or update resources in Ncp, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ncp environment.
Why optimize_client is rated Medium
Modifies client configuration by replacing MCP server list, but creates backup first.
From the tool's definition back up configuration and replace its MCP server list
Attacks that exploit this kind of access
The rule that runs optimize_client 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 optimize_client, this is the rule to start with:
optimize_client stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. 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 optimize_client call is checked against it from then on.
Questions about optimize_client
Back up a supported MCP client configuration and replace its MCP server list with NCP. Requires explicit user confirmation. It is categorised as a Write tool in the Ncp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ncp MCP server in PolicyLayer and add a rule for optimize_client: 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.
optimize_client is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the optimize_client 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 optimize_client. 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.
optimize_client 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