AI agents use store.vector-upsert to create or update resources in Mcp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp environment.
This tool performs a Write operation—it modifies data (creating or updating vectors in storage) in a reversible manner. It does not delete data (ruling out Destructive), does not execute arbitrary commands (Execute), does not move money (Financial), and is not a simple read (Read).
From the tool's definition Tool description uses 'upsert' (update/insert operation) to modify vector storage. 'Upsert' is a reversible write operation that creates or modifies data records in a vector database.
Attacks that exploit this kind of access
STORE: upsert a vector for semantic retrieval, scoped to. It is categorised as a Write tool in the Mcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP server in PolicyLayer and add a rule for store.vector-upsert: 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. Nothing to install.
store.vector-upsert 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 store.vector-upsert 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 store.vector-upsert. 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.
store.vector-upsert is provided by the MCP server (@2sio/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 →