AI agents use import_contacts to create or update resources in Tgmcp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tgmcp environment.
The tool creates new contact records in the user's Telegram account. While reversible (fitting Write rather than Destructive), it modifies user data and could be misused to pollute contact lists or add unwanted entries.
From the tool's definition Tool description states 'Import a list of contacts' — a create/add operation that modifies the contact list by adding new entries. This is a reversible write operation (contacts can be deleted via delete_contact).
Attacks that exploit this kind of access
Import a list of contacts. Each contact should be a dict with phone, first_name, last_name. It is categorised as a Write tool in the Tgmcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Tg MCP server in PolicyLayer and add a rule for import_contacts: 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 Tgmcp. Nothing to install.
import_contacts 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 import_contacts 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 import_contacts. 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.
import_contacts is provided by the Tg MCP server (oevortex/tgmcp). 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 →