snow_cache_set
Store a string value in the in-memory tool cache under a key, with a TTL in seconds (default 3600). Read back with snow_cache_get within the same session.
This record as markdown: /tools/serac/snow-cache-set.md
What snow_cache_set does on Serac
AI agents use snow_cache_set to create or update resources in Serac, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Serac environment.
Why snow_cache_set is rated Medium
This tool creates or modifies data (cache entries) in memory. It is not destructive because cache entries automatically expire and are not permanent. It is not execute, read, financial, or other. The low severity reflects that the blast radius is minimal—cached data is temporary, local to the session, and contains no persistent or critical state.
From the tool's definition Tool name 'snow_cache_set' and description 'Store a string value in the in-memory tool cache under a key' indicate a write operation that creates or modifies data. The cache is session-local and temporary (TTL-based), making modifications reversible.
Attacks that exploit this kind of access
The rule that runs snow_cache_set safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Serac, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For snow_cache_set, this is the rule to start with:
snow_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 Serac, apply this rule, and every snow_cache_set call is checked against it from then on.
Questions about snow_cache_set
Store a string value in the in-memory tool cache under a key, with a TTL in seconds (default 3600). Read back with snow_cache_get within the same session. It is categorised as a Write tool in the Serac MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Serac MCP server in PolicyLayer and add a rule for snow_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 Serac. Nothing to install.
snow_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 snow_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 snow_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.
snow_cache_set is provided by the Serac MCP server (serac-labs/serac). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Serac, and thousands of servers like it.
This server
Across the catalogue