Bland AI Connector for AI agents.
10 live capabilities
Manage enterprise-grade telephony and conversational voice workflows from your workspace.
Waiting for input…
Why people use Bland AI
Bland AI for Automated Outbound Calling
With this Connector, you can skip the manual data entry entirely. Your AI client can trigger bulk campaigns, pull the goal status of every call, and log the results directly into your system. You get a clear view of your outreach without the busy work.
What Vinkius changes
You get a direct remote control for your voice AI infrastructure.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
High-volume outbound sales
A manager asks the agent to blast 1,000 calls to a new lead list using send_batch to hit daily targets.
- Real-world use case 02
QA Audit
A supervisor asks the agent to pull recordings for the last 50 calls to check for script adherence and tone.
- Real-world use case 03
Lead Qualification
A salesperson asks the agent to check if a specific customer was interested in a demo using analyze_call.
Complete set · 10capabilities
The complete Bland AI capability set.
These are the exact actions your AI can choose when you ask it to work with Bland AI.
01—04
4 capabilities in this set.
Part of 10 available through Bland AI.
- 01 Capability
Analyze call
Query an active recording to see if the caller met a specific goal. This helps you qualify leads or check success rates.
- 02 Capability
End call
Force an immediate disconnect to stop a live AI conversation. Use this to kill a call that's going in the wrong direction.
- 03 Capability
Get batch
View the status of concurrent calls within a bulk batch. This gives you a high-level look at your campaign progress.
- 04 Capability
Get call details
Get the exact transcript logic and variables from a finished call. Use it to see how the agent handled specific questions.
05—07
3 capabilities in this set.
Part of 10 available through Bland AI.
- 05 Capability
List calls
Pull the full historical log of all your AI phone calls. This lets you see every interaction in one organized view.
- 06 Capability
Get recording
Grab native MP3 or WAV links for your CRM or quality logs. This lets you save the actual audio for manual review.
- 07 Capability
Create web call
Spawn a decoupled internet-based WebRTC signaling socket. Use this to bridge audio directly into a web browser.
08—10
3 capabilities in this set.
Part of 10 available through Bland AI.
- 08 Capability
List inbound
See which inbound phone numbers are currently bridged to your agent. Use this to manage your available phone lines.
- 09 Capability
Send batch
Dispatch multiple AI agents at once to scale bulk telecom arrays. Use this to reach thousands of people in a single campaign.
- 10 Capability
Send call
Send an automated conversational AI agent to a specific phone number. This helps you start outbound conversations without manual dialing.
Set up in minutes
One URL. Then ask Bland AI to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Bland AI from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_2KRrzGgsG5orAZiaTSS9H8zOQ0vQUrOu27n5CWqf/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Bland AI, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Bland AI for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_2KRrzGgsG5orAZiaTSS9H8zOQ0vQUrOu27n5CWqf/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Bland AI URL.
- Step 03
Save and start
Save the connection and enable Bland AI in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"bland-ai": {
"url": "https://edge.vinkius.com/vk_preview_2KRrzGgsG5orAZiaTSS9H8zOQ0vQUrOu27n5CWqf/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Bland AI
Open Agent mode in chat and ask: "Using Bland AI, help me...". 10 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"bland-ai": {
"url": "https://edge.vinkius.com/vk_preview_2KRrzGgsG5orAZiaTSS9H8zOQ0vQUrOu27n5CWqf/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Bland AI
Ask Copilot: "Using Bland AI, help me...". 10 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"bland-ai": {
"url": "https://edge.vinkius.com/vk_preview_2KRrzGgsG5orAZiaTSS9H8zOQ0vQUrOu27n5CWqf/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Bland AI
Open Cascade and ask: "Using Bland AI, help me...". 10 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"bland-ai": {
"url": "https://edge.vinkius.com/vk_preview_2KRrzGgsG5orAZiaTSS9H8zOQ0vQUrOu27n5CWqf/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Bland AI
Ask Cline: "Using Bland AI, help me...". 10 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add bland-ai --transport http "https://edge.vinkius.com/vk_preview_2KRrzGgsG5orAZiaTSS9H8zOQ0vQUrOu27n5CWqf/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Bland AI
Ask Claude: "Using Bland AI, show me...". 10 tools are ready
Where the request belongs
Work Bland AI can move forward.
The sales manager who needs to hit outbound targets without hiring a massive call center. The support lead who wants to audit thousands of hours of voice interactions without listening to every single one.
Sales Development Rep (SDR)
Uses this to fire off 500 outbound lead calls in a single batch during the afternoon.
QA Analyst
Pulls recordings and transcripts to check if the voice agent is following the correct script.
Ops Engineer
Manages inbound routing and debugs WebRTC signaling sockets to keep the phone lines running.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsBland AI
Deploy AI phone agents that handle inbound and outbound calls with natural conversation for sales and customer support.
Thoughtly
Deploy AI voice agents to make or receive calls, manage CRM contacts, and access call histories instantly.
MiiTel
Analyze phone conversations with AI that scores call quality, identifies sentiment, and provides coaching insights for sales teams.
Vapi
Command Voice AI assistants directly from your chat. Make outbound phone calls, update personas, and retrieve full transcripts via Vapi.
Goodcall
Answer business phone calls with an AI receptionist that schedules appointments, takes messages, and never puts callers on hold.
8x8
Power your cloud communications with AI-driven call management, voicemail access, and team messaging across every channel.
Bring your own AI
Change the model, client or framework. Keep Bland AI connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Bland AI.
The practical details behind the request, access and result.
How can I use Bland AI MCP for automated calling?
You can use it to trigger individual calls or launch large-scale outbound campaigns directly from your AI client. It handles the dialing and conversation for you.
Can Bland AI MCP handle bulk outbound campaigns?
Yes, it supports bulk telecom arrays, allowing you to reach thousands of people at once rather than one by one.
How do I get transcripts from my calls with Bland AI MCP?
The Connector can pull the full text of past conversations, making it easy to see exactly what was said during any interaction.
Can I stop a live call using Bland AI MCP?
Yes, you can force an immediate disconnect on any active conversation if it's going in the wrong direction.
Does Bland AI MCP support inbound phone numbers?
It allows you to identify and manage purchased PSTN numbers that are currently bridged to your AI agent for incoming calls.
How do I get audio recordings with Bland AI MCP?
You can retrieve native MP3 or WAV links for any call, which is perfect for logging into your CRM or doing quality checks.
Can I check if a lead is qualified using Bland AI MCP?
Yes, you can query specific goal completion statuses from past recordings to see if a lead met your requirements.
Can my agent determine if a sales phone call was successful?
Yes. By providing the specific Call ID and a structured goal query (e.g., 'Did they buy?'), your AI agent triggers the 'analyze_call' capability, running a targeted LLM pass exactly over that transcript to extract the explicit boolean outcome.
What if a voice agent goes off-script on a live call?
You can instruct your agent to forcefully disrupt the conversation. Using the 'end_call' capability, it will immediately pass an interrupt flag and drop the active telecom connection without waiting for the other party.
Can I make AI agent calls directly through the browser instead of standard telephony?
Absolutely. Your agent can execute the 'create_web_call' capability, which bypasses PSTN billing entirely and opens a pure WebRTC signaling socket for direct in-app or browser audio interactions.
One connection away
Give your agent a direct line to Bland AI.
Connect Bland AI once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available