AI agents use send_file to create or update resources in Tgmcp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tgmcp environment.
This tool creates new data (a message with file) in a chat, which is reversible (messages can be deleted). It does not execute code, delete data irreversibly, or move money. While sending files could potentially be misused (e.g., spam, malware distribution), the action itself is a standard write/create operation.
From the tool's definition Tool name and description indicate 'Send a file to a chat' - a write operation that creates/uploads content to a Telegram chat, modifying chat state by adding a new message with file attachment.
Attacks that exploit this kind of access
Send a file to a chat. It is categorised as a Write tool in the Tgmcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Tg 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 Tgmcp. 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 Tg MCP server (oevortex/tgmcp). 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 →