get_unread_messages

THE RISK

Low Risk

Why get_unread_messages needs a policy

This tool retrieves existing unread messages from Telegram without creating, modifying, deleting, or executing any operations. It is a straightforward read operation with minimal security risk, though sensitivity depends on the content of messages being retrieved.

From the tool's definition Tool name 'get_unread_messages' and description 'get all unread messages from a given entity id' indicate data retrieval with no modification or side effects.

Documented attack patterns abuse exactly the kind of access get_unread_messages gives an agent:

POLICY

How to control get_unread_messages

PolicyLayer is an MCP gateway — it sits between your AI agents and Telegram MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_unread_messages:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_unread_messages": {}
  }
}

get_unread_messages is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register Telegram MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Telegram MCP Server tools

Write send_message Send a message to an entity with optional markup and reply Read get_entities Get all entities in the current session Read get_entity_by_id Get an entity from the current session Read get_messages Get messages limited by a count from an entity Read get_unread_entities get entitites which have unread messages in it

All 6 Telegram MCP Server tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about get_unread_messages

What does the get_unread_messages tool do? +

get all unread messages from a given entity id. It is categorised as a Read tool in the Telegram MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_unread_messages? +

Register the Telegram MCP Server MCP server in PolicyLayer and add a rule for get_unread_messages: 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 Telegram MCP Server. Nothing to install.

What risk level is get_unread_messages? +

get_unread_messages is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit get_unread_messages? +

Yes. Add a rate_limit block to the get_unread_messages 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.

How do I block get_unread_messages completely? +

Set action: deny in the PolicyLayer policy for get_unread_messages. 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.

What MCP server provides get_unread_messages? +

get_unread_messages is provided by the Telegram MCP Server MCP server (prem-research/telegram-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Telegram MCP Server tool call.

Start from Telegram MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →