上传图片到飞书。返回 file_token,可用于 feishu_insert_image 插入文档。⚠️ 需要 drive:drive:media:upload 权限。
AI agents use feishu_upload_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.
The tool creates new image resources in Feishu's file system. While reversible (images can be deleted), it modifies the state of the platform by adding new files. It is not destructive (does not delete or overwrite), not financial, and not arbitrary code execution.
From the tool's definition Tool name 'feishu_upload_image' and description state it uploads images to Feishu and returns a file_token for insertion. The Chinese text '上传图片到飞书' means 'upload images to Feishu'. This is a create/write operation that stores new media files.
Attacks that exploit this kind of access
上传图片到飞书。返回 file_token,可用于 feishu_insert_image 插入文档。⚠️ 需要 drive:drive:media:upload 权限。. 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_upload_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_upload_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_upload_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_upload_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_upload_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 →