How to Use the Bland AI MCP in Windsurf

Q: How do I set up Bland AI inside Windsurf?

Open your mcpconfig.json file in Windsurf and add this MCP Server under your servers list. You can also do this through the Cascade settings UI. Once saved, Cascade immediately discovers all twelve voice tools.

Q: How do I debug voice agent prompts using Bland AI and Windsurf?

You can ask Cascade to fetch your current setup using getagentconfig. Write your prompt changes in a file, and Cascade will push the updates to Bland AI using updateagentconfig in one go.

Q: What happens if a call gets stuck during a run?

You can tell your editor to run stopactivecall to kill the connection instantly. This keeps your testing budget safe from long, runaway calls.

Trigger outbound calls and analyze transcripts right from Windsurf with the Bland AI MCP Server.

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 Windsurf

Create your Vinkius account to connect Bland AI to Windsurf 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 Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run autonomous phone campaigns from Windsurf

The `send_phone_call` tool kicks off outbound calls directly from Cascade without you needing to manually trigger each contact. You give Windsurf a list of numbers, and it uses `list_phone_numbers` to select an active line and dial. Cascade handles the queue autonomously. It keeps track of who answered, updates your local files with the status, and moves to the next lead without stopping for permission.

Build and tweak voice agents on the fly

You use `create_voice_agent` to build a custom voice profile and write its prompt right inside your IDE. Cascade handles the heavy lifting, checking your configuration with `get_agent_config` to make sure the instructions are tight. If a test run sounds off, Windsurf updates the prompt using `update_agent_config` and retries. You don't have to copy-paste between a browser and your editor; Cascade edits the agent's behavior directly.

Pull and analyze call logs inside Windsurf

The `list_recent_calls` tool fetches your history so Cascade can inspect what happened on recent dials. Once it finds a call that needs attention, it grabs the dialogue log using `get_call_details` and runs `analyze_call_transcript` to extract action items. This gives your editor the ability to write code based on real phone conversations. Cascade reads the analysis, flags bugs or feature requests mentioned by users, and opens the relevant files to start fixing them.

Setup guide

Set up Bland AI MCP in Windsurf

Prerequisites

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

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
2

Add the Bland AI MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Bland AI payment history." If connected, Cascade will call the Bland AI tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.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 Windsurf

Open your `mcp_config.json` file in Windsurf and add this MCP Server under your servers list. You can also do this through the Cascade settings UI. Once saved, Cascade immediately discovers all twelve voice tools.

Yes, Cascade can chain these tools together without you having to click run for every single step. It can grab numbers, trigger the dialer, and wait for the callback to analyze the result.

You can ask Cascade to fetch your current setup using `get_agent_config`. Write your prompt changes in a file, and Cascade will push the updates to Bland AI using `update_agent_config` in one go.

You can tell your editor to run `stop_active_call` to kill the connection instantly. This keeps your testing budget safe from long, runaway calls.

All phone numbers and voice agent configs remain secure on Vinkius's isolated MCP runtime. The connection uses secure transport, ensuring your private phone records and transcripts are never exposed to public networks.

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