上传 HTML 内容到项目。支持直接传入 HTML 字符串或本地文件路径。返回幻灯片数量、每页文本摘要和结构性警告。
AI agents use upload_html to create or update resources in Flash Cast — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Flash Cast environment.
This tool creates or modifies project data by accepting HTML input (either as string or file path) and storing it in the project. It is reversible (content can be updated or removed), making it a Write operation rather than Destructive.
From the tool's definition Tool description states '上传 HTML 内容到项目' (upload HTML content to project), which creates/modifies project data. Returns slide count and text summaries, indicating persistent storage of the uploaded content.
Attacks that exploit this kind of access
上传 HTML 内容到项目。支持直接传入 HTML 字符串或本地文件路径。返回幻灯片数量、每页文本摘要和结构性警告。. It is categorised as a Write tool in the Flash Cast MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Flash Cast MCP server in PolicyLayer and add a rule for upload_html: 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 Flash Cast. Nothing to install.
upload_html 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 upload_html 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 upload_html. 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.
upload_html is provided by the Flash Cast MCP server (trtian/flash-cast-mcp). 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 →