infomaniak_list_ai_models
List the public catalogue of LLM/STT/embedding models hosted by Infomaniak (Mixtral, Llama variants, Whisper, ...). Useful to know what to target with the OpenAI-compatible chat endpoint.
This record as markdown: /tools/henrikogaard-infomaniak-admin-mcp/infomaniak-list-ai-models.md
What infomaniak_list_ai_models does on Infomaniak Admin
AI agents call infomaniak_list_ai_models to retrieve information from Infomaniak Admin without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why infomaniak_list_ai_models is rated Low
This tool queries and returns information about publicly available models without creating, modifying, deleting, executing code, or transferring funds. It is a straightforward read operation with minimal security risk - the information returned is public catalogue data about hosted models.
From the tool's definition Tool name is 'list_ai_models' and description states it 'List[s] the public catalogue of LLM/STT/embedding models' - a pure retrieval operation with no side effects.
Attacks that exploit this kind of access
The rule that runs infomaniak_list_ai_models safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Infomaniak Admin, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For infomaniak_list_ai_models, this is the rule to start with:
infomaniak_list_ai_models is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Infomaniak Admin, apply this rule, and every infomaniak_list_ai_models call is checked against it from then on.
Questions about infomaniak_list_ai_models
List the public catalogue of LLM/STT/embedding models hosted by Infomaniak (Mixtral, Llama variants, Whisper, ...). Useful to know what to target with the OpenAI-compatible chat endpoint. It is categorised as a Read tool in the Infomaniak Admin MCP Server, which means it retrieves data without modifying state.
Register the Infomaniak Admin MCP server in PolicyLayer and add a rule for infomaniak_list_ai_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 Infomaniak Admin. Nothing to install.
infomaniak_list_ai_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 infomaniak_list_ai_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 infomaniak_list_ai_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.
infomaniak_list_ai_models is provided by the Infomaniak Admin MCP server (henrikogaard/infomaniak-admin-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Infomaniak Admin, and thousands of servers like it.
This server
Across the catalogue