Get recent incoming messages/updates for a bot. Uses short polling.
AI agents call get_updates to retrieve information from Mcp Telegram without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads existing messages/updates from a Telegram bot without modifying, deleting, or executing any operations. While it accesses message content, the data is already received by the bot and the tool merely retrieves it. The blast radius of misuse is low—an agent reading recent messages poses minimal risk compared to sending messages, deleting data, or executing commands. Classification: Read.
From the tool's definition Tool retrieves 'recent incoming messages/updates' with no side effects. The description explicitly indicates a query operation ('Get...for a bot') using polling to fetch data.
Attacks that exploit this kind of access
Get recent incoming messages/updates for a bot. Uses short polling. It is categorised as a Read tool in the Mcp Telegram MCP Server, which means it retrieves data without modifying state.
Register the Mcp Telegram MCP server in PolicyLayer and add a rule for get_updates: 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 Mcp Telegram. Nothing to install.
get_updates 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_updates 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_updates. 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_updates is provided by the Mcp Telegram MCP server (paulofroes/mcp-telegram). 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 →