feishu_base_record_upsert · Lark Cli MCP: Risk & Policy

WHAT IT DOES

What feishu_base_record_upsert does on Lark Cli

AI agents use feishu_base_record_upsert to create or update resources in Lark Cli — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Lark Cli environment.

WHY IT NEEDS A POLICY

Why feishu_base_record_upsert needs a policy

The tool modifies data in Feishu's base/table system by either creating new records or updating existing ones. While reversible (not Destructive), it changes persistent data and represents a Write operation. Severity is high because the AI operates 'as the user's own identity' with no apparent approval mechanism, creating risk of unintended data modifications across the user's Feishu workspace.

From the tool's definition Tool name 'feishu_base_record_upsert' and description stating it creates or updates records (conditional on record_id presence): '创建或更新一条记录（给 record_id 则更新，否则创建）'. This is reversible modification of data in a multi-dimensional table.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

feishu_base_record_upsert Rate-limited

feishu_base_record_upsert 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "feishu_base_record_upsert": {
      "limits": [
        {
          "counter": "feishu_base_record_upsert_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Lark Cli, so you can run agents against it safely.

FAQ

Questions about feishu_base_record_upsert

What does the feishu_base_record_upsert tool do? +

在多维表格数据表中创建或更新一条记录（给 record_id 则更新，否则创建）. It is categorised as a Write tool in the Lark Cli MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on feishu_base_record_upsert? +

Register the Lark Cli MCP server in PolicyLayer and add a rule for feishu_base_record_upsert: 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 Cli. Nothing to install.

What risk level is feishu_base_record_upsert? +

feishu_base_record_upsert is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit feishu_base_record_upsert? +

Yes. Add a rate_limit block to the feishu_base_record_upsert 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.

How do I block feishu_base_record_upsert completely? +

Set action: deny in the PolicyLayer policy for feishu_base_record_upsert. 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.

What MCP server provides feishu_base_record_upsert? +

feishu_base_record_upsert is provided by the Lark Cli MCP server (yoreland/lark-cli-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.