List available embedding models. Shows models configured in embedder.toml. Model types: - text: Text embedding models (e.g., OpenAI text-embedding-3-large) - clip: Multimodal models for images - whisper: Audio transcription models Args: model_type: Filter by model type (optional) Returns: List of...
AI agents call memvid_models to retrieve information from Memvid without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is clearly a Read operation—it queries and returns a list of available models from configuration. There is no capability to modify, delete, or execute code. The blast radius is minimal since the output is informational and read-only. Confidence is high because the description explicitly uses 'List' and describes a passive retrieval of configuration data.
From the tool's definition The tool 'memvid_models' with description 'List available embedding models' and 'Shows models configured in embedder.toml' performs a retrieval operation with no side effects. It returns configuration information without modifying or executing anything.
Attacks that exploit this kind of access
List available embedding models. Shows models configured in embedder.toml. Model types: - text: Text embedding models (e.g., OpenAI text-embedding-3-large) - clip: Multimodal models for images - whisper: Audio transcription models Args: model_type: Filter by model type (optional) Returns: List of available models with configuration. It is categorised as a Read tool in the Memvid MCP Server, which means it retrieves data without modifying state.
Register the Memvid MCP server in PolicyLayer and add a rule for memvid_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 Memvid. Nothing to install.
memvid_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 memvid_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 memvid_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.
memvid_models is provided by the Memvid MCP server (tapiocapioca/memvid-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 →