Update or create a tile in a Slite note
AI agents use update_tile to create or update resources in Slite MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Slite MCP Server environment.
The tool creates or modifies data reversibly—tiles can be edited or removed later. It does not delete data irreversibly (Destructive), execute arbitrary code (Execute), move money (Financial), or merely read data (Read). The severity is medium because unintended tile modifications could corrupt note content or introduce misinformation into the knowledge base, but changes are reversible.
From the tool's definition Tool name 'update_tile' and description 'Update or create a tile in a Slite note' indicate the tool modifies (or creates) content within notes.
Attacks that exploit this kind of access
Update or create a tile in a Slite note. It is categorised as a Write tool in the Slite MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Slite MCP Server MCP server in PolicyLayer and add a rule for update_tile: 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 Slite MCP Server. Nothing to install.
update_tile 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 update_tile 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 update_tile. 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.
update_tile is provided by the Slite MCP Server MCP server (takeokunn/slite-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 →