AI agents call get_examples to retrieve information from Eff without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves examples and templates for educational or reference purposes related to the Ethics Filter Framework. It performs a query or fetch operation that reads existing data without creating, modifying, deleting, or executing any external actions. The information returned is static documentation/templates, making this a straightforward Read operation with minimal risk.
From the tool's definition The tool description states it 'Return[s] the EFF worked examples and templates', which is a retrieval operation with no modification or side effects. The URI reference (eff://examples) further indicates this is a data lookup function.
Attacks that exploit this kind of access
Return the EFF worked examples and templates (eff://examples). It is categorised as a Read tool in the Eff MCP Server, which means it retrieves data without modifying state.
Register the Eff MCP server in PolicyLayer and add a rule for get_examples: 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 Eff. Nothing to install.
get_examples 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 get_examples 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 get_examples. 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.
get_examples is provided by the Eff MCP server (vs3kulic/eff-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 →