在飞书文档中插入图片。支持通过文件 token 插入已上传的图片。
AI agents use feishu_insert_image to create or update resources in Feishu MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Feishu MCP Server environment.
This tool modifies documents by inserting images into them. It is a Write operation because it creates new content within documents reversibly—images can be removed or replaced. It is not Destructive since insertions can be undone.
From the tool's definition Tool name 'feishu_insert_image' and description '在飞书文档中插入图片' (insert image into Feishu document) indicates content creation/modification. The phrase 'supports inserting uploaded images via file token' confirms this creates or modifies document content.
Attacks that exploit this kind of access
在飞书文档中插入图片。支持通过文件 token 插入已上传的图片。. It is categorised as a Write tool in the Feishu MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Feishu MCP Server MCP server in PolicyLayer and add a rule for feishu_insert_image: 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 Feishu MCP Server. Nothing to install.
feishu_insert_image 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 feishu_insert_image 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 feishu_insert_image. 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.
feishu_insert_image is provided by the Feishu MCP Server MCP server (redleaves/feishu-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 →