Upload text content directly to the knowledge base
AI agents use upload_content to create or update resources in Gemini RAG MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gemini RAG MCP Server environment.
The tool creates new data (text content) in a persistent knowledge base system. While reversible (content can be replaced or deleted separately), it modifies the state of the knowledge base and affects what future queries will retrieve. This is a Write operation rather than Read (no retrieval) or Destructive (not irreversible by itself).
From the tool's definition Tool uploads content to knowledge base; description states 'Upload text content directly to the knowledge base', which creates/modifies data in a retrievable collection.
Documented attack patterns abuse exactly the kind of access upload_content gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Gemini RAG MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for upload_content:
{
"version": "1",
"default": "deny",
"tools": {
"upload_content": {
"limits": [
{
"counter": "upload_content_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}upload_content stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Upload text content directly to the knowledge base. It is categorised as a Write tool in the Gemini RAG MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Gemini RAG MCP Server MCP server in PolicyLayer and add a rule for upload_content: 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 Gemini RAG MCP Server. Nothing to install.
upload_content 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_content 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_content. 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_content is provided by the Gemini RAG MCP Server MCP server (masseater/gemini-rag-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Gemini RAG MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
3 Gemini RAG MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.