Upload a file to a document library. Content must be base64-encoded.
AI agents use upload_file to create or update resources in SharePoint MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your SharePoint MCP Server environment.
Uploading a file is a reversible write operation—the file can be downloaded, modified, or deleted later. While it modifies SharePoint state and has side effects, it does not irreversibly destroy data (would be Destructive) or execute arbitrary code (would be Execute).
From the tool's definition Tool name 'upload_file' and description 'Upload a file to a document library' indicate the tool creates or modifies data by adding new file content to SharePoint storage.
Attacks that exploit this kind of access
Upload a file to a document library. Content must be base64-encoded. It is categorised as a Write tool in the SharePoint MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the SharePoint MCP Server MCP server in PolicyLayer and add a rule for upload_file: 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 SharePoint MCP Server. Nothing to install.
upload_file 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_file 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_file. 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_file is provided by the SharePoint MCP Server MCP server (lukassevcik/sharepoint-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 →