Get available chat and embedding models from Perplexica.
AI agents call get_available_models to retrieve information from Perplexica MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves configuration/metadata information about available models. It has no side effects, does not execute code or commands, does not modify data, and does not commit financial or destructive operations. It is purely informational (Read category). Severity is low because even if misused, listing available models poses minimal risk.
From the tool's definition Tool name 'get_available_models' and description 'Get available chat and embedding models from Perplexica' indicate a query operation that retrieves model metadata without modifying or executing anything.
Documented attack patterns abuse exactly the kind of access get_available_models gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Perplexica MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_available_models:
{
"version": "1",
"default": "deny",
"tools": {
"get_available_models": {}
}
}get_available_models is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get available chat and embedding models from Perplexica. It is categorised as a Read tool in the Perplexica MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Perplexica MCP Server MCP server in PolicyLayer and add a rule for get_available_models: 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 Perplexica MCP Server. Nothing to install.
get_available_models 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_available_models 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_available_models. 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_available_models is provided by the Perplexica MCP Server MCP server (tianmu/perplexica-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Perplexica MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
7 Perplexica MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.