AI agents call propose_snippets to retrieve information from Looba without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries snippet data from Looba to present options to the user. It has no side effects—no creation, modification, deletion, or execution of code. It is a read operation aligned with the server's read-only design purpose.
From the tool's definition Tool description states 'Search Looba and propose...snippet options' with URLs. Server description emphasizes 'read-only access' and 'snippet discovery'. The tool performs a search and returns information without modifying data.
Attacks that exploit this kind of access
Search Looba and propose exactly 3 snippet options to the user with their looba.dev post URLs. It is categorised as a Read tool in the Looba MCP Server, which means it retrieves data without modifying state.
Register the Looba MCP server in PolicyLayer and add a rule for propose_snippets: 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 Looba. Nothing to install.
propose_snippets 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 propose_snippets 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 propose_snippets. 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.
propose_snippets is provided by the Looba MCP server (looba-snippet/looba-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 →