AI agents call system.runtime_config to retrieve information from Dynamic without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and returns runtime configuration information without modifying, deleting, or executing operations. It is a read-only query operation. The 'sanitized' aspect reduces exposure of sensitive credentials or internal details. Severity is low because config snapshots are typically informational with limited blast radius when disclosed, assuming proper sanitization.
From the tool's definition Tool name 'system.runtime_config' combined with description 'Return sanitized runtime config snapshot' indicates retrieval of configuration data with no modification capability.
Attacks that exploit this kind of access
Return sanitized runtime config snapshot. It is categorised as a Read tool in the Dynamic MCP Server, which means it retrieves data without modifying state.
Register the Dynamic MCP server in PolicyLayer and add a rule for system.runtime_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 Dynamic. Nothing to install.
system.runtime_config is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the system.runtime_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 system.runtime_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.
system.runtime_config is provided by the Dynamic MCP server (mcpland/dynamic-mcp). 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 →