通过上传 PDF 文件创建新的证据
AI agents use create_evidence_by_pdf to create or update resources in KnowS MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your KnowS MCP Server environment.
This tool creates or adds new data (medical evidence records) to the system through PDF file upload, which is a reversible write operation. It is not destructive (records can be modified or deleted later), not financial, and not execute/code-running.
From the tool's definition Tool name 'create_evidence_by_pdf' and description '通过上传 PDF 文件创建新的证据' (create new evidence by uploading PDF file) indicates the tool creates new records in the medical evidence database by processing uploaded documents.
Attacks that exploit this kind of access
通过上传 PDF 文件创建新的证据. It is categorised as a Write tool in the KnowS MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the KnowS MCP Server MCP server in PolicyLayer and add a rule for create_evidence_by_pdf: 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 KnowS MCP Server. Nothing to install.
create_evidence_by_pdf 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 create_evidence_by_pdf 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 create_evidence_by_pdf. 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.
create_evidence_by_pdf is provided by the KnowS MCP Server MCP server (pancrepal-xiaoyibao/mcp-knows-ai). 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 →