AI agents call get_last_interaction 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 retrieves historical messaging data without altering it. Fetching the last interaction is a pure read operation that does not create, modify, delete, or execute any operations. The low severity reflects minimal risk of misuse—an AI agent obtaining a previous message poses no direct security or privacy threat beyond standard access control concerns inherent to the Telegram account.
From the tool's definition Tool description: 'Get the most recent message with a contact.' The verb 'Get' and action of retrieving a message indicates data retrieval with no modification or side effects.
Attacks that exploit this kind of access
Get the most recent message with a contact. 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_last_interaction: 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_last_interaction 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_last_interaction 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_last_interaction. 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_last_interaction 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 →