AI agents use set_preference to create or update resources in SharkMCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your SharkMCP environment.
This tool modifies application preferences/settings, which is a reversible Write operation. It lacks destructive severity since preference changes can typically be reverted. Severity is medium because misconfigured preferences could affect subsequent analysis operations or expose sensitive analyzer behaviors, but the blast radius is limited to configuration state rather than data deletion or financial impact.
From the tool's definition Tool name 'set_preference' indicates modification of configuration state. Sibling tools include 'get_preference', suggesting a preference management system.
Documented attack patterns abuse exactly the kind of access set_preference gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and SharkMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for set_preference:
{
"version": "1",
"default": "deny",
"tools": {
"set_preference": {
"limits": [
{
"counter": "set_preference_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}set_preference 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.
Free to start. No card required.
set_preference. It is categorised as a Write tool in the SharkMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Shark MCP server in PolicyLayer and add a rule for set_preference: 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 SharkMCP. Nothing to install.
set_preference 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 set_preference 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 set_preference. 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.
set_preference is provided by the Shark MCP server (weirdmachine64/sharkmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 30 SharkMCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
30 SharkMCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.