AI agents use flowise_upsert_vector to create or update resources in Flowise — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Flowise environment.
Upsert is a reversible write operation (insert or update). Without a description, confidence is reduced, but the name strongly indicates data modification in a vector store or database. Severity is medium because vector data corruption could impact ML/RAG pipelines, but effects are typically recoverable and scoped to the Flowise instance.
From the tool's definition Tool name 'flowise_upsert_vector' uses 'upsert' which is a standard database operation that creates or updates records. No description provided to confirm exact behavior.
Attacks that exploit this kind of access
flowise_upsert_vector. It is categorised as a Write tool in the Flowise MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Flowise MCP server in PolicyLayer and add a rule for flowise_upsert_vector: 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 Flowise. Nothing to install.
flowise_upsert_vector 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 flowise_upsert_vector 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 flowise_upsert_vector. 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.
flowise_upsert_vector is provided by the Flowise MCP server (julidir/flowise-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 →