Upload a document to the knowledge base
AI agents use upload_document to create or update resources in MCP Knowledge Base Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Knowledge Base Server environment.
Uploading a document creates new data in the knowledge base without destructive consequences. It is reversible and does not execute code, trigger external side effects beyond storage, or move money. This maps cleanly to the Write category.
From the tool's definition Tool name is 'upload_document' and description states 'Upload a document to the knowledge base'. This creates/adds new data to the knowledge base, which is reversible (documents can be deleted via the sibling 'delete_document' tool).
Attacks that exploit this kind of access
Upload a document to the knowledge base. It is categorised as a Write tool in the MCP Knowledge Base Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Knowledge Base Server MCP server in PolicyLayer and add a rule for upload_document: 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 MCP Knowledge Base Server. Nothing to install.
upload_document 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_document 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_document. 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_document is provided by the MCP Knowledge Base Server MCP server (maxsmosarski/mcp-knowledge-base). 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 →