Semantic search using embeddings. Searches text fields (title, description, notes, etc.) for semantically similar records.
AI agents call search_parquet to retrieve information from Parquet MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Semantic search is a query operation that retrieves matching records based on embeddings. It does not create, modify, delete, or execute code. The search operation has no side effects on the data itself—it only reads and returns results. This is a Read category tool with low severity since misuse would only expose information without risking data loss or unauthorized actions.
From the tool's definition Tool description states it 'Searches text fields (title, description, notes, etc.) for semantically similar records.' The verb 'search' and explicit mention of searching without modification indicates data retrieval only.
Attacks that exploit this kind of access
Semantic search using embeddings. Searches text fields (title, description, notes, etc.) for semantically similar records. It is categorised as a Read tool in the Parquet MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Parquet MCP Server MCP server in PolicyLayer and add a rule for search_parquet: 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.
search_parquet 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 search_parquet 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 search_parquet. 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.
search_parquet 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 →