AI agents use update_table to create or update resources in Lark Base MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Lark Base MCP Server environment.
Update operations that modify database table definitions are Write-category (reversible changes to structure/metadata) rather than Destructive, unless they involve dropping columns or irreversible alterations—which cannot be confirmed from the empty description. The tool sits in a Write tier due to its reversibility and scope.
From the tool's definition Tool name 'update_table' indicates modification of table structures or metadata. Description is empty, limiting specificity. Context shows sibling tools include create_table, delete_table, and other write/destructive operations on a Feishu Base database.
Documented attack patterns abuse exactly the kind of access update_table gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Lark Base MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for update_table:
{
"version": "1",
"default": "deny",
"tools": {
"update_table": {
"limits": [
{
"counter": "update_table_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_table stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
update_table. It is categorised as a Write tool in the Lark Base MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Lark Base MCP Server 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 Lark Base MCP Server. 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 Lark Base MCP Server MCP server (lark-base-team/lark-base-mcp-node-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Lark Base MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
13 Lark Base MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.