Set ELFA base URL (e.g., https://api.elfa.ai).
AI agents use elfa_set_base to create or update resources in CG Alpha MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your CG Alpha MCP environment.
This tool modifies application configuration by updating the ELFA base URL. While not destructive (changes are reversible) and not directly accessing data, it is a write operation that alters system state. Severity is medium because misconfiguration could redirect API calls to unintended endpoints, potentially causing service disruption or enabling man-in-the-middle attacks if an attacker controls the input.
From the tool's definition Tool description states 'Set ELFA base URL', which modifies configuration state. The verb 'Set' indicates a write/configuration change operation.
Attacks that exploit this kind of access
Set ELFA base URL (e.g., https://api.elfa.ai). It is categorised as a Write tool in the CG Alpha MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the CG Alpha MCP server in PolicyLayer and add a rule for elfa_set_base: 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 CG Alpha MCP. Nothing to install.
elfa_set_base 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 elfa_set_base 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 elfa_set_base. 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.
elfa_set_base is provided by the CG Alpha MCP server (jcf0/cg-alpha-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 →