This record as markdown: /tools/io-github-portel-dev-ncp/cache-set.md
What cache_set does on Ncp
AI agents use cache_set 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 cache_set is rated Medium
The tool creates or modifies data in a cache store (Memcached). While reversible in nature, caching systems are typically write operations that can affect application behavior and performance. Severity is medium because cache poisoning or incorrect cached data could impact application logic, but it's not destructive (data persists elsewhere) nor financial.
From the tool's definition Tool name 'cache_set' and description 'Store data in Memcached' indicate this writes/stores data in a cache system.
Attacks that exploit this kind of access
The rule that runs cache_set 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 cache_set, this is the rule to start with:
cache_set 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 cache_set call is checked against it from then on.
Questions about cache_set
Store data in Memcached. 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 cache_set: 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.
cache_set 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 cache_set 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 cache_set. 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.
cache_set 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