This record as markdown: /tools/creativelead-unclick/telegram-send.md
What telegram_send does on UnClick
AI agents use telegram_send to create or update resources in UnClick, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your UnClick environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
text | string | — | |
chat_id | string | — | |
bot_token | string | — | |
parse_mode | string | — | |
reply_to_message_id | number | — |
Parameters from the server's own tool schema.
Why telegram_send is rated Medium
Sending a message is a Write operation: it creates new data (the message) and modifies state (adds to conversation history), but is reversible (messages can be deleted). Severity is medium because an AI agent misusing this could spam users, send malicious content, or impersonate the account holder, causing reputational or operational harm, but without financial loss or permanent data destruction.
From the tool's definition Tool name is 'telegram_send' and description states 'Send a Telegram message' — this creates/transmits a message, a reversible action with side effects.
Attacks that exploit this kind of access
The rule that runs telegram_send safely
PolicyLayer is an MCP gateway: it sits between your AI agents and UnClick, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For telegram_send, this is the rule to start with:
telegram_send stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect UnClick, apply this rule, and every telegram_send call is checked against it from then on.
Questions about telegram_send
Send a Telegram message. It is categorised as a Write tool in the UnClick MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
telegram_send accepts 5 parameters: text, chat_id, bot_token, parse_mode, reply_to_message_id. The full parameter table on this page comes from the server's own tool schema.
Register the UnClick MCP server in PolicyLayer and add a rule for telegram_send: 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 UnClick. Nothing to install.
telegram_send 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 telegram_send 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 telegram_send. 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.
telegram_send is provided by the UnClick MCP server (creativelead/unclick). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on UnClick, and thousands of servers like it.
This server
Across the catalogue