Share a file with a user/group or create a public link
AI agents use share_file to create or update resources in Mail Cal Drive — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mail Cal Drive environment.
The tool modifies access control lists and file-sharing settings, which are reversible configuration changes (Write category). Severity is high because unintended sharing could expose sensitive data to unintended recipients or the public; however, it is not Destructive since the shared file itself remains intact and permissions can be revoked.
From the tool's definition share_file: Share a file with a user/group or create a public link. This modifies file access permissions and can generate public sharing links, both of which alter data state.
Attacks that exploit this kind of access
Share a file with a user/group or create a public link. It is categorised as a Write tool in the Mail Cal Drive MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mail Cal Drive MCP server in PolicyLayer and add a rule for share_file: 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 Mail Cal Drive. Nothing to install.
share_file 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 share_file 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 share_file. 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.
share_file is provided by the Mail Cal Drive MCP server (rumbitopi/mail-cal-drive-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 →