Send a message via Telegram bot
AI agents use send_telegram to create or update resources in Inkwell MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Inkwell MCP Server environment.
Sending a Telegram message is a write operation that creates data (the message) in an external communication system. It is reversible (the message can be deleted), so it does not qualify as Destructive. It has no financial component.
From the tool's definition Tool description states 'Send a message via Telegram bot' — a message transmission action that modifies state in an external system (Telegram).
Attacks that exploit this kind of access
Send a message via Telegram bot. It is categorised as a Write tool in the Inkwell MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Inkwell MCP Server MCP server in PolicyLayer and add a rule for send_telegram: 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 Inkwell MCP Server. Nothing to install.
send_telegram 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 send_telegram 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 send_telegram. 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.
send_telegram is provided by the Inkwell MCP Server MCP server (mumega-com/inkwell). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
send_telegram is one line of Inkwell MCP Server's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →