Create or update flexible metadata for an entity.
AI agents use upsert_attributes to create or update resources in SQLite Project Memory MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your SQLite Project Memory MCP environment.
Upsert (create or update) is a Write operation because it modifies entity metadata in a controlled, reversible manner. It ranks below Destructive (no deletion) and Execute (no code execution), but above Read (modifies state).
From the tool's definition Tool name 'upsert_attributes' indicates create-or-update semantics. Description states 'Create or update flexible metadata for an entity.' This is a reversible modification operation that does not irreversibly delete data nor execute arbitrary code.
Attacks that exploit this kind of access
Create or update flexible metadata for an entity. It is categorised as a Write tool in the SQLite Project Memory MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the SQLite Project Memory MCP server in PolicyLayer and add a rule for upsert_attributes: 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 SQLite Project Memory MCP. Nothing to install.
upsert_attributes 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_attributes 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_attributes. 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_attributes is provided by the SQLite Project Memory MCP server (webrtcgame/sqlite-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 →