AI-powered Telegram bot for data extraction with Bright Data MCP
Needs changesWhat this workflow does
This AI workflow has 16 nodes and runs when another workflow calls it (plus 2 other triggers). Along the way it connects OpenRouter Chat Model, Telegram and MCP Client. It also calls api.telegram.org over HTTP.
How it runs
Trigger: When another workflow calls it (plus 2 other triggers).
- Typing action (Telegram): send chat action
- Set Telegram Webhook (HTTP Request): calls api.telegram.org
- AI Agent: runs an AI agent, with model: OpenRouter Chat Model; 1 tool (MCP Client); memory: Simple Memory
- Sub-workflow to trigger Typing Action (Execute Sub-workflow): calls another n8n workflow
- Wait: waits 10 seconds
- Send AI’s output to the user via Telegram (Telegram): uses Telegram
- Check if the execution in N8N is finished (n8n): get (execution)
- If: checks a condition and branches into true / false
- Check if the N8N status is success (If): checks a condition and branches into true / false
- Reply Error Message (Telegram): uses Telegram
Services it uses
HTTP calls to: api.telegram.org
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- AI Agent v1 (old agent modes) in AI Agent (v1.9): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
Rather not rewrite it? Many of these flows can be rebuilt in Make (free plan).
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) AI Agent (v1.9) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (13)
- AI Agent
@n8n/n8n-nodes-langchain.agent - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - OpenRouter Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenRouter - Manual Trigger
n8n-nodes-base.manualTrigger - HTTP Request
n8n-nodes-base.httpRequest - Webhook
n8n-nodes-base.webhook - Telegram
n8n-nodes-base.telegram - Execute Sub-workflow
n8n-nodes-base.executeWorkflow - MCP Client Tool
@n8n/n8n-nodes-langchain.mcpClientTool - n8n
n8n-nodes-base.n8n - If
n8n-nodes-base.if - Wait
n8n-nodes-base.wait - Execute Workflow Trigger
n8n-nodes-base.executeWorkflowTrigger
From the author
📌 AI Agent Template with Bright Data MCP Tool Integration This template enables natural-language-driven automation using Bright Data MCP tools. It extracts all available tools from MCP, processes the user’s query through an AI agent, then dynamically selects…