AI agents use send_file to create or update resources in MCP-Communicator-Telegram — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP-Communicator-Telegram environment.
The tool creates messages/artifacts in an external system (Telegram) by transmitting files. While not destructive or reversible in the classical sense, it represents data creation/modification with side effects that could expose sensitive information if misused by an AI agent (e.g., sending confidential files to unintended recipients).
From the tool's definition Tool name 'send_file' and description 'Send a file to the user via Telegram' indicate the tool transmits/uploads file content to an external service (Telegram) and the user.
Documented attack patterns abuse exactly the kind of access send_file gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP-Communicator-Telegram, and nothing reaches the server without passing your rules. This is the rule we recommend for send_file:
{
"version": "1",
"default": "deny",
"tools": {
"send_file": {
"limits": [
{
"counter": "send_file_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}send_file 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.
Free to start. No card required.
Send a file to the user via Telegram. It is categorised as a Write tool in the MCP-Communicator-Telegram MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP-Communicator-Telegram MCP server in PolicyLayer and add a rule for send_file: 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-Communicator-Telegram. Nothing to install.
send_file 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_file 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_file. 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_file is provided by the MCP-Communicator-Telegram MCP server (qpd-v/mcp-communicator-telegram). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 4 MCP-Communicator-Telegram tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4 MCP-Communicator-Telegram tools catalogued and risk-classified — across an index of 42,500+ MCP servers.