Update existing records in a parquet file. Creates audit log entry and optionally creates full snapshot based on configuration. Use when a rule or workflow requires Parquet updates (per .cursor/rules/neotoma_parquet_migration.mdc, write to Neotoma first; then update via this tool if the data type...
AI agents use update_records 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.
This tool modifies data by updating existing records in a Parquet file. It is categorized as Write rather than Destructive because: (1) updates are reversible through the audit logging and rollback capabilities explicitly mentioned in the server description, (2) the tool preserves existing records rather than deleting them, and (3) the modification is incremental rather than irreversible.
From the tool's definition Tool description states 'Update existing records in a parquet file' and 'Creates audit log entry and optionally creates full snapshot'. The operation is reversible via 'rollback capabilities' mentioned in server description.
Attacks that exploit this kind of access
Update existing records in a parquet file. Creates audit log entry and optionally creates full snapshot based on configuration. Use when a rule or workflow requires Parquet updates (per .cursor/rules/neotoma_parquet_migration.mdc, write to Neotoma first; then update via this tool if the data type still uses Parquet). Use when updating existing records matching specific criteria (use upsert_record if you want to create if not found). 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 update_records: 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.
update_records 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 update_records 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 update_records. 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.
update_records 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 →