Read and query a parquet file with optional filters and sorting. Supports enhanced filtering operators: $contains, $starts_with, $ends_with, $regex, $fuzzy, $gt, $gte, $lt, $lte, $in, $ne
AI agents call read_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.
This tool performs read-only operations on Parquet files. It retrieves and queries data with various filtering and sorting options but does not create, modify, delete, or execute code. The presence of sibling tools like 'add_record', 'delete_records', and 'rollback_operation' confirms that this tool is isolated to the Read category.
From the tool's definition Tool name 'read_parquet' and description 'Read and query a parquet file with optional filters and sorting' explicitly indicate data retrieval without modification.
Attacks that exploit this kind of access
Read and query a parquet file with optional filters and sorting. Supports enhanced filtering operators: $contains, $starts_with, $ends_with, $regex, $fuzzy, $gt, $gte, $lt, $lte, $in, $ne. 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 read_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.
read_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 read_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 read_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.
read_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 →