Bring Voice Ai
to CrewAI
Learn how to connect Retell AI to CrewAI and start using 11 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the Retell AI MCP Server?
Connect your Retell AI account to any AI agent and take full control of your conversational voice orchestration through natural conversation. Retell AI provides a premier platform for building human-like voice agents, and this integration allows you to create agents, initiate phone or web calls, and monitor LLM configurations directly from your chat interface.
What you can do
- Agent & Persona Orchestration — List all managed voice agents and retrieve detailed persona metadata, including creating new agents programmatically.
- Call Lifecycle Management — Initiate and monitor real-time phone or web calls and retrieve detailed call metadata including recordings and transcripts directly from the AI interface.
- LLM & Brain Control — Access and monitor your Retell LLM configurations to ensure your agents always have the correct logic and knowledge via natural language.
- Phone Number Intelligence — List available phone numbers to maintain a clear overview of your telephony infrastructure.
- Operational Monitoring — Track system responses and manage agent settings using simple AI commands to ensure your voice operations are always optimized.
How it works
1. Subscribe to this server
2. Enter your Retell AI API Key from your dashboard settings
3. Start managing your voice agents from Claude, Cursor, or any MCP-compatible client
No more manual call logs or complex agent configuration. Your AI acts as a dedicated voice operations manager or AI lead.
Who is this for?
- AI Developers & Product Managers — quickly retrieve call details and monitor agent performance without switching apps.
- Customer Support Operations — automate the management of voice personas and track call history via natural conversation.
- Operations Teams — streamline the retrieval of agent metadata and monitor organizational voice health directly within the chat.
Built-in capabilities (11)
Create a new AI voice agent
Get details for a voice agent
Get details and transcript for a call
Get metadata for a response engine
Get details for a specific phone number
List call logs and history
List internal response engines
List registered phone numbers
List all AI voice agents
Initiate an outbound phone call
Initialize a browser-based call
Why CrewAI?
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.
- —
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
mcpsparameter 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 in CrewAI
Retell AI and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Retell AI to CrewAI through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 3,400+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Retell AI in CrewAI
The Retell AI 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. All 11 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in CrewAI only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* 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
How Vinkius secures
Retell AI for CrewAI
Every tool call from CrewAI to the Retell AI MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can my AI automatically create a new phone call to a customer using a specific agent?
Yes! Use the create_phone_call tool. Provide the destination phone number and the agent_id, and your agent will trigger the outbound AI voice call instantly.
How do I list all my available Retell voice agents?
Simply ask the agent to run the list_agents action. It will retrieve the full catalog of voice agents configured in your Retell AI account.
How do I find my Retell AI API Key?
Log in to your Retell AI dashboard, navigate to Settings > API Keys, and you will find your unique secret API key there.
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.
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.