Upload vectors to a collection
AI agents use upsert_vectors to create or update resources in Qdrant MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Qdrant MCP Server environment.
This tool creates or modifies vector records in the Qdrant database. Upsert operations are reversible (can be overwritten or deleted later), making this a Write rather than Destructive action. The severity is medium because misuse could corrupt or pollute the vector store with incorrect embeddings, affecting downstream search quality, but the impact is scoped to the database and reversible.
From the tool's definition Tool name 'upsert_vectors' and description 'Upload vectors to a collection' indicate data modification. Upsert is a database operation that creates or updates records. No deletion, financial impact, or code execution involved.
Attacks that exploit this kind of access
Upload vectors to a collection. It is categorised as a Write tool in the Qdrant MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Qdrant MCP Server MCP server in PolicyLayer and add a rule for upsert_vectors: 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 Qdrant MCP Server. Nothing to install.
upsert_vectors 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 upsert_vectors 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 upsert_vectors. 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.
upsert_vectors is provided by the Qdrant MCP Server MCP server (jimmy974/qdrant-mcp-server). 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 →