How to Use the Bland AI MCP in CrewAI

Q: How do I prevent CrewAI from making unauthorized Bland AI calls?

You can use MCPServerHTTP from the CrewAI package to filter tools. By exposing only listrecentcalls, you let CrewAI agents monitor calls without giving them Bland AI dialing permissions.

Run autonomous phone agent operations with CrewAI multi-agent teams managing your outbound Bland AI calls.

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 CrewAI

Create your Vinkius account to connect Bland AI to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent phone triage using CrewAI teams

Let specialized CrewAI agents collaborate on your Bland AI voice campaigns. A CrewAI Researcher agent scans lead lists, while a Caller agent uses `send_phone_call` to dial prospects with customized Bland AI context. This division of labor keeps your CrewAI operations autonomous. While one CrewAI agent runs the dialer, another monitors the queue using `list_recent_calls` to manage Bland AI pacing.

Autonomous agent configuration via CrewAI MCP Server

Your CrewAI crew can dynamically build and refine its own Bland AI voice representatives using this MCP Server. A CrewAI Writer agent drafts scripts, while a Manager agent calls `create_voice_agent` to launch the Bland AI persona. If Bland AI performance metrics dip, a CrewAI Moderator agent uses `update_agent_config` to tweak prompts. The CrewAI crew optimizes its own Bland AI voice setup without human intervention.

Post-call analysis and automatic escalation

Set up a dedicated CrewAI quality assurance crew for your Bland AI voice operations. After a call, a CrewAI Analyst agent runs `get_call_details` and `analyze_call_transcript` to evaluate Bland AI performance. If the CrewAI analyst flags a critical issue, it escalates to a CrewAI Supervisor agent. The CrewAI supervisor can instantly execute `stop_active_call` on any matching active Bland AI lines.

Setup guide

Set up Bland AI MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Bland AI tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Bland AI Analyst",
    goal="Access and analyze Bland AI data via MCP.",
    backstory="Expert analyst with direct Bland AI access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Bland AI transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Bland AI Analyst",
        goal="Access and analyze Bland AI data via MCP.",
        backstory="Expert analyst with direct Bland AI access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Bland AI transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

You pass the Bland AI server URL directly in your CrewAI Agent definition using the `mcps` parameter. This limits tool access so only your designated CrewAI Caller agent can trigger `send_phone_call`.

Yes, CrewAI agents share memory. Once a CrewAI Analyst agent gets data via `analyze_call_transcript`, the CrewAI Writer agent can read that analysis to draft a follow-up Bland AI campaign.

You can use `MCPServerHTTP` from the CrewAI package to filter tools. By exposing only `list_recent_calls`, you let CrewAI agents monitor calls without giving them Bland AI dialing permissions.

Yes, the CrewAI integration supports stdio, SSE, and Streamable HTTP for Bland AI connections. Vinkius manages these transport layers automatically so your CrewAI python script connects without manual socket configuration.

Your Bland AI phone numbers and call transcript data are protected by zero-trust ephemeral environments. Every MCP tool call executes in an isolated sandbox, ensuring your CrewAI conversation logs are never leaked.

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