Does Retell handle the telephone lines, or do I need my own Twilio/carrier?

Retell AI is designed to integrate seamlessly into telephony workflows but generally focuses on the conversational agent side. They provide features to list and attach numbers (`list_phone_numbers`), but you often purchase those numbers or link a custom SIP trunk through Retell accounts. You can run `list_phone_numbers` to see your currently available direct lines.

How do I create an outbound call programmatically with my assistant?

Simply ask your assistant to "Call X using my Y agent." Behind the scenes, the AI relies on the `create_phone_call` tool, transmitting a JSON payload supplying the `from_number` (a Retell registered phone number), `to_number` (destination), and an `override_agent_id` parameter to assign your voice agent correctly.

Can the AI initiate voice calls in a web browser instead of over the phone?

Yes. Use the `register_web_call` tool to create a browser-based voice session. This returns a connection URL and access token that your frontend application can use to start a real-time WebRTC conversation with a Retell voice agent, without requiring any phone line.

Retell AI MCP Server for CrewAI 10 tools — connect in under 2 minutes

Name: Retell AI
Availability: InStock
Author: Vinkius

docs.crewai.com/mcp/overview

Built by Vinkius GDPR 10 Tools Framework

Connect your CrewAI agents to Retell AI through Vinkius, pass the Edge URL in the `mcps` parameter and every Retell AI tool is auto-discovered at runtime. No credentials to manage, no infrastructure to maintain.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

from crewai import Agent, Task, Crew

agent = Agent(
    role="Retell AI Specialist",
    goal="Help users interact with Retell AI effectively",
    backstory=(
        "You are an expert at leveraging Retell AI tools "
        "for automation and data analysis."
    ),
    # Your Vinkius token. get it at cloud.vinkius.com
    mcps=["https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"],
)

task = Task(
    description=(
        "Explore all available tools in Retell AI "
        "and summarize their capabilities."
    ),
    agent=agent,
    expected_output=(
        "A detailed summary of 10 available tools "
        "and what they can do."
    ),
)

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

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Retell AI MCP Server

Connect your conversational assistant directly to Retell AI, a powerful platform for building voice-driven conversational agents. Empower your AI to orchestrate, analyze, and automate phone calls or web-based voice interactions seamlessly via simple text commands. From provisioning intelligent voice agents to placing outbound calls to customers, this integration brings the full telecommunication stack directly to your chat interface.

When paired with CrewAI, Retell AI becomes a first-class tool in your multi-agent workflows. Each agent in the crew can call Retell AI tools autonomously, one agent queries data, another analyzes results, a third compiles reports, all orchestrated through Vinkius with zero configuration overhead.

What you can do

Automate Phone Calls — Command your assistant to initiate outbound voice interactions on your behalf (create_phone_call) or register active sessions for web browser integration (register_web_call).
Build and Manage Voice Agents — Dynamically orchestrate AI agent personalities (create_agent, update_agent) and configure their underlying conversational brain (create_llm) with specific system instructions and models.
Analyze Telemetry — Keep track of your infrastructure by querying historical call logs (list_calls), investigating specific conversations for transcripts and sentiment analysis (get_call_details), surveying available text-to-speech voices (list_voices), and reviewing provisioned communication lines (list_phone_numbers and list_agents).

The Retell AI MCP Server exposes 10 tools through the Vinkius. Connect it to CrewAI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Retell AI to CrewAI via MCP

Follow these steps to integrate the Retell AI MCP Server with CrewAI.

Install CrewAI

Run pip install crewai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Customize the agent

Adjust the role, goal, and backstory to fit your use case

Run the crew

Run python crew.py. CrewAI auto-discovers 10 tools from Retell AI

Why Use CrewAI with the Retell AI MCP Server

CrewAI Multi-Agent Orchestration Framework provides unique advantages when paired with Retell AI through the Model Context Protocol.

Multi-agent collaboration lets you decompose complex workflows into specialized roles, one agent researches, another analyzes, a third generates reports, each with access to MCP tools

CrewAI's native MCP integration requires zero adapter code: pass Vinkius Edge URL directly in the `mcps` parameter and agents auto-discover every available tool at runtime

Built-in task delegation and shared memory mean agents can pass context between steps without manual state management, enabling multi-hop reasoning across tool calls

Sequential and hierarchical crew patterns map naturally to real-world workflows: enumerate subdomains → analyze DNS history → check WHOIS records → compile findings into actionable reports

Retell AI + CrewAI Use Cases

Practical scenarios where CrewAI combined with the Retell AI MCP Server delivers measurable value.

Automated multi-step research: a reconnaissance agent queries Retell AI for raw data, then a second analyst agent cross-references findings and flags anomalies. all without human handoff

Scheduled intelligence reports: set up a crew that periodically queries Retell AI, analyzes trends over time, and generates executive briefings in markdown or PDF format

Multi-source enrichment pipelines: chain Retell AI tools with other MCP servers in the same crew, letting agents correlate data across multiple providers in a single workflow

Compliance and audit automation: a compliance agent queries Retell AI against predefined policy rules, generates deviation reports, and routes findings to the appropriate team

Retell AI MCP Tools for CrewAI (10)

These 10 tools become available when you connect Retell AI to CrewAI via MCP:

create_agent

Creates a new AI voice agent

create_llm

Configures a Retell-hosted LLM

create_phone_call

Provide a JSON payload with "from_number" and "to_number". Initiates an outbound phone call

get_call_details

Retrieves details for a specific call

list_agents

Lists all configured AI voice agents

list_calls

Lists all historical and active calls

list_phone_numbers

Lists all phone numbers associated with the account

list_voices

Lists all available text-to-speech voices

register_web_call

Registers a new web-based call

update_agent

Updates an existing AI voice agent

Example Prompts for Retell AI in CrewAI

Ready-to-use prompts you can give your CrewAI agent to start working with Retell AI immediately.

"Can you show me the transcripts for call ID `c_f3a123`?"

"List all available agents I can use."

"We are testing out new numbers. Please use 'from_number' `+18005551234` and dial `+14085551234` assigning my 'agent_555'."

Troubleshooting Retell AI MCP Server with CrewAI

Common issues when connecting Retell AI to CrewAI through the Vinkius, and how to resolve them.

MCP tools not discovered

Ensure the Edge URL is correct. CrewAI connects lazily when the crew starts. check console output.

Agent not using tools

Make the task description specific. Instead of "do something", say "Use the available tools to list contacts".

Timeout errors

CrewAI has a 10s connection timeout by default. Ensure your network can reach the Edge URL.

Rate limiting or 429 errors

Vinkius enforces per-token rate limits. Check your subscription tier and request quota in the dashboard. Upgrade if you need higher throughput.

Retell AI + CrewAI FAQ

Common questions about integrating Retell AI MCP Server with CrewAI.

How does CrewAI discover and connect to MCP tools?

CrewAI connects to MCP servers lazily. when the crew starts, each agent resolves its MCP URLs and fetches the tool catalog via the standard tools/list method. This means tools are always fresh and reflect the server's current capabilities. No tool schemas need to be hardcoded.

Can different agents in the same crew use different MCP servers?

Yes. Each agent has its own mcps list, so you can assign specific servers to specific roles. For example, a reconnaissance agent might use a domain intelligence server while an analysis agent uses a vulnerability database server.

What happens when an MCP tool call fails during a crew run?

CrewAI wraps tool failures as context for the agent. The LLM receives the error message and can decide to retry with different parameters, fall back to a different tool, or mark the task as partially complete. This resilience is critical for production workflows.

Can CrewAI agents call multiple MCP tools in parallel?

CrewAI agents execute tool calls sequentially within a single reasoning step. However, you can run multiple agents in parallel using process=Process.parallel, each calling different MCP tools concurrently. This is ideal for workflows where separate data sources need to be queried simultaneously.

Can I run CrewAI crews on a schedule (cron)?

Yes. CrewAI crews are standard Python scripts, so you can invoke them via cron, Airflow, Celery, or any task scheduler. The crew.kickoff() method runs synchronously by default, making it straightforward to integrate into existing pipelines.