Save, load, list, or delete reusable filter configurations. Allows LLMs to store commonly used capture and analysis parameters for easy reuse.
AI agents use manage_config 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 stored configuration metadata rather than network capture data or system state. While it includes a delete function, configurations are user-created preferences/settings that can be regenerated, making it a Write operation rather than Destructive. The severity is medium because misconfiguration could affect network analysis accuracy, but the blast radius is limited to configuration scope.
From the tool's definition Tool performs create, update, and delete operations on configuration files: 'Save, load, list, or delete reusable filter configurations.' The 'delete' action on stored configurations is reversible (configurations can be recreated), distinguishing it from…
Documented attack patterns abuse exactly the kind of access manage_config 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 manage_config:
{
"version": "1",
"default": "deny",
"tools": {
"manage_config": {
"limits": [
{
"counter": "manage_config_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}manage_config 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.
Save, load, list, or delete reusable filter configurations. Allows LLMs to store commonly used capture and analysis parameters for easy reuse. 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 manage_config: 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.
manage_config 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 manage_config 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 manage_config. 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.
manage_config is provided by the Shark MCP server (tuliperis/sharkmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 4 SharkMCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4 SharkMCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.