How to Use the Bland AI MCP in Cursor

Q: How does the Bland AI MCP integration work inside Cursor?

You add the MCP server to your .cursor/mcp.json file. When you enter Agent mode, Cursor gains access to tools like sendphonecall and can write code using live telephony data.

Q: Can Cursor create new Bland AI agents during a chat session?

Yes. Cursor uses createvoiceagent to build new agent profiles based on the requirements in your code. It can also clean up temporary test profiles using deletevoiceagent.

Q: How do I debug Bland AI voice configurations in Cursor?

You ask Cursor to inspect your settings using getagentconfig. The editor analyzes the active parameters and helps you write the correct JSON payload to update them.

Q: Can I list my active phone lines inside the editor?

Yes, the listphonenumbers tool retrieves all your active lines. Cursor uses this list to help you bind specific outbound numbers to your agent configurations.

Build and test voice agent integrations in Cursor using live call data instead of dummy mocks.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Bland AI MCP to Cursor

Create your Vinkius account to connect Bland AI to Cursor and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Bland AI with Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Test outbound calls directly from Cursor

The `send_phone_call` tool initiates real phone calls while you write your application logic in Cursor. Instead of guessing how your webhook handles call endings, you trigger a live test call and watch the payload come in. If the test call gets stuck in a loop, you run `stop_active_call` to kill the connection instantly. This tight feedback loop lets you debug telephony code in seconds.

Build voice agent code with this MCP Server

The `get_agent_config` tool pulls the exact system prompts and parameters of your active phone agents into your editor. Cursor reads this live JSON payload to generate matching database schemas or frontend configuration panels. When you need to push updates, `update_agent_config` modifies the remote agent behavior directly from your workspace. You do not need to copy-paste prompts back and forth between your browser and your codebase.

Refine system prompts using real transcripts

The `analyze_call_transcript` tool processes call logs to find where users got confused or hung up. Cursor reads these analysis reports alongside `get_call_details` to suggest specific prompt improvements. You can also pull a list of recent executions using `list_recent_calls` to feed real-world conversation data into your test suites. This makes your voice agents more robust before you ship them to production.

Setup guide

Set up Bland AI MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Bland AI MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Bland AI transactions." If the MCP tools are loaded correctly, Cursor will call the Bland AI tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "bland-ai-alternative-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Bland AI. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Bland AI now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Bland AI MCP in Cursor

You add the MCP server to your `.cursor/mcp.json` file. When you enter Agent mode, Cursor gains access to tools like `send_phone_call` and can write code using live telephony data.

Yes. Cursor uses `create_voice_agent` to build new agent profiles based on the requirements in your code. It can also clean up temporary test profiles using `delete_voice_agent`.

You ask Cursor to inspect your settings using `get_agent_config`. The editor analyzes the active parameters and helps you write the correct JSON payload to update them.

Yes, the `list_phone_numbers` tool retrieves all your active lines. Cursor uses this list to help you bind specific outbound numbers to your agent configurations.

Your credentials are kept secure within the Vinkius vault and never exposed to the LLM or stored in your local repository. The MCP server only handles the specific transit of voice configurations and call metadata.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript