Bring Voice Ai
to Mastra AI
Learn how to connect Thoughtly to Mastra AI 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 Thoughtly MCP Server?
Connect your Thoughtly voice AI platform to any text-based AI agent to seamlessly bridge the gap between text commands and real-world phone calls.
What you can do
- Trigger Phone Calls — Instantly instruct your AI Voice Agents (Interviews) to dial any contact and execute conversational phone workflows
- Contact Management — Query your Thoughtly CRM directory, register new leads with phone numbers, and manage their details
- Call Logs & Transcripts — Retrieve detailed call histories, metadata, and full transcripts of conversations conducted by your voice agents
- Agent Fleet Control — List and inspect all your active AI Voice Agents to deploy the right persona for each outbound campaign
How it works
1. Subscribe to this server
2. Enter your Thoughtly API Token and Team ID
3. Start commanding your voice agents directly from Claude, Cursor, or any MCP-compatible client
Your text agent becomes the ultimate dispatcher, effortlessly ordering your voice agents to interact with the real world through natural language.
Who is this for?
- Sales Development Reps — automate outbound qualification campaigns by triggering voice agents for new leads instantly
- Customer Support Teams — quickly query the transcript of past AI interactions without opening a dashboard
- Operations Managers — orchestrate complex communication workflows across both text and voice channels simultaneously
Built-in capabilities (11)
Optionally includes first name, last name, email. Create a new Thoughtly contact
Delete a Thoughtly contact
Get details and transcript for a specific call
Get specific Thoughtly contact details
Get details for a specific Thoughtly Voice Agent
Get Thoughtly user details
List past phone calls (Call logs)
List Thoughtly contacts
List Thoughtly Voice Agents (Interviews)
Trigger an AI outbound phone call
Update an existing Thoughtly contact
Why Mastra AI?
Mastra's agent abstraction provides a clean separation between LLM logic and Thoughtly tool infrastructure. Connect 11 tools through Vinkius and use Mastra's built-in workflow engine to chain tool calls with conditional logic, retries, and parallel execution. deployable to any Node.js host in one command.
- —
Mastra's agent abstraction provides a clean separation between LLM logic and tool infrastructure. add Thoughtly without touching business code
- —
Built-in workflow engine chains MCP tool calls with conditional logic, retries, and parallel execution for complex automation
- —
TypeScript-native: full type inference for every Thoughtly tool response with IDE autocomplete and compile-time checks
- —
One-command deployment to any Node.js host. Vercel, Railway, Fly.io, or your own infrastructure
Thoughtly in Mastra AI
Thoughtly and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Thoughtly to Mastra AI 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 Thoughtly in Mastra AI
The Thoughtly 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 Mastra AI 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
Thoughtly for Mastra AI
Every tool call from Mastra AI to the Thoughtly MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can my text AI agent command a voice agent to call a specific person?
Yes! Use the trigger_call tool by providing the Interview ID (Voice Agent) and the Contact ID. The voice AI will immediately execute the outbound call.
Is it possible to read the transcript of what the Voice AI discussed during a call?
Absolutely. By calling the get_call_history tool with a specific Call ID, your agent can extract the entire conversational transcript and analyze the outcome without leaving the interface.
Do I need to manually register contacts in the Thoughtly dashboard before calling them?
No. The integration provides the create_contact tool, allowing your AI to dynamically add new leads to the CRM and immediately initiate a phone call in one fluid workflow.
How does Mastra AI connect to MCP servers?
Create an MCPClient with the server URL and pass it to your agent. Mastra discovers all tools and makes them available with full TypeScript types.
Can Mastra agents use tools from multiple servers?
Yes. Pass multiple MCP clients to the agent constructor. Mastra merges all tool schemas and the agent can call any tool from any server.
Does Mastra support workflow orchestration?
Yes. Mastra has a built-in workflow engine that lets you chain MCP tool calls with branching logic, error handling, and parallel execution.
createMCPClient not exported
Install: npm install @mastra/mcp