AI agents use update_mcp_server to create or update resources in Snak — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Snak environment.
This tool modifies MCP server configurations, which are settings that can be changed and reverted. The blast radius is high because misconfigured MCP servers could expose agents to unauthorized data sources or disable security controls, but the operation is reversible (configs can be changed again), distinguishing it from Destructive.
From the tool's definition Tool description states 'Update/modify/change configuration of one or multiple existing MCP servers' - these are clear Write operations that modify existing configurations reversibly.
Attacks that exploit this kind of access
Update/modify/change configuration of one or multiple existing MCP servers for a specific agent. Use when user wants to modify MCP server settings or configuration. It is categorised as a Write tool in the Snak MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Snak MCP server in PolicyLayer and add a rule for update_mcp_server: 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 Snak. Nothing to install.
update_mcp_server 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 update_mcp_server 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 update_mcp_server. 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.
update_mcp_server is provided by the Snak MCP server (kasarlabs/snak). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →