Generate and store embeddings for text fields in a data type. Creates or updates embeddings parquet file.
AI agents use generate_embeddings to create or update resources in Parquet MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Parquet MCP Server environment.
The tool performs reversible data modification (creates or updates embeddings files) rather than destructive deletion, code execution, or financial operations. While it writes data, this is a standard CRUD operation typical of structured data management systems.
From the tool's definition Tool description states 'Creates or updates embeddings parquet file' — modifying parquet files reversibly through create/update operations.
Attacks that exploit this kind of access
Generate and store embeddings for text fields in a data type. Creates or updates embeddings parquet file. It is categorised as a Write tool in the Parquet MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Parquet MCP Server MCP server in PolicyLayer and add a rule for generate_embeddings: 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 Parquet MCP Server. Nothing to install.
generate_embeddings is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the generate_embeddings 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 generate_embeddings. 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.
generate_embeddings is provided by the Parquet MCP Server MCP server (markmhendrickson/mcp-server-parquet). 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 →