Set or merge tag labels for an entity.
AI agents use set_tags 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.
The tool creates or updates tag metadata on entities in the SQLite database. This is a reversible modification (tags can be changed or removed later), fitting the Write category. Severity is medium because misuse could pollute project metadata, making it harder to organize or retrieve entities, but the effects are not irreversible or system-critical.
From the tool's definition Tool description states 'Set or merge tag labels for an entity,' which modifies existing data (tags) in a reversible manner. This is a write operation that changes entity metadata without deletion or destruction.
Attacks that exploit this kind of access
Set or merge tag labels 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 set_tags: 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.
set_tags 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 set_tags 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 set_tags. 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.
set_tags 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 →