Replace the ENTIRE table structure with a modified version. Use for MODIFYING existing rows, DELETING rows, REORDERING rows, or STRUCTURAL changes. CRITICAL: Must send the FULL table structure (not just modified fields). DO NOT use for simple additions - use append_table instead. Required workflo...
AI agents use update_table to create or update resources in Openl — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Openl environment.
While this tool can delete rows as part of a structural update, it is fundamentally a Write operation because: (1) modifications are reversible through subsequent update_table calls, (2) row deletions occur within the context of replacing the entire table (not selective irreversible deletion like delete_table), and (3) the primary use case is modifying existing data.
From the tool's definition Tool description explicitly states 'Replace the ENTIRE table structure with a modified version' and 'Use for MODIFYING existing rows, DELETING rows, REORDERING rows, or STRUCTURAL changes.' The operation modifies and restructures data but is reversible (can…
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Replace the ENTIRE table structure with a modified version. Use for MODIFYING existing rows, DELETING rows, REORDERING rows, or STRUCTURAL changes. CRITICAL: Must send the FULL table structure (not just modified fields). DO NOT use for simple additions - use append_table instead. Required workflow: 1) Call get_table() to retrieve complete structure, 2) Modify the returned object, 3) Pass the ENTIRE modified object to update_table(). IMPORTANT: an edit that relocates the table (it had no room to grow in place) CHANGES its location-derived id; the response always returns the table. It is categorised as a Write tool in the Openl MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Openl MCP server in PolicyLayer and add a rule for update_table: 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 Openl. Nothing to install.
update_table 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_table 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_table. 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_table is provided by the Openl MCP server (openl-mcp-server). 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 →