AI agents call get_contact_ids to retrieve information from Tgmcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns contact data without creating, modifying, deleting, or executing any actions. It is a simple read operation that retrieves existing information from the user's Telegram account. The severity is low because contact ID lists are generally non-sensitive metadata, and the impact of exposure is limited to information disclosure rather than data loss or system compromise.
From the tool's definition Tool name 'get_contact_ids' and description 'Get all contact IDs in your Telegram account' indicate a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Get all contact IDs in your Telegram account. It is categorised as a Read tool in the Tgmcp MCP Server, which means it retrieves data without modifying state.
Register the Tg MCP server in PolicyLayer and add a rule for get_contact_ids: 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.
get_contact_ids is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_contact_ids 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 get_contact_ids. 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.
get_contact_ids 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 →