Channels MCP Server for Mastra AIGive Mastra AI instant access to 12 tools to Create Contact, Create Webhook, Delete Contact, and more
Mastra AI is a TypeScript-native agent framework built for modern web stacks. Connect Channels through Vinkius and Mastra agents discover all tools automatically. type-safe, streaming-ready, and deployable anywhere Node.js runs.
Ask AI about this App Connector for Mastra AI
The Channels app connector for Mastra AI is a standout in the Communication Messaging category — giving your AI agent 12 tools to work with, ready to go from day one.
Vinkius delivers Streamable HTTP and SSE to any MCP client
import { Agent } from "@mastra/core/agent";
import { createMCPClient } from "@mastra/mcp";
import { openai } from "@ai-sdk/openai";
async function main() {
// Your Vinkius token. get it at cloud.vinkius.com
const mcpClient = await createMCPClient({
servers: {
"channels": {
url: "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
},
},
});
const tools = await mcpClient.getTools();
const agent = new Agent({
name: "Channels Agent",
instructions:
"You help users interact with Channels " +
"using 12 tools.",
model: openai("gpt-4o"),
tools,
});
const result = await agent.generate(
"What can I do with Channels?"
);
console.log(result.text);
}
main();
* 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 Channels MCP Server
Connect your Channels (Channels.app) account to any AI agent and take full control of your cloud-based phone system and customer communication workflows through natural conversation.
Mastra's agent abstraction provides a clean separation between LLM logic and Channels tool infrastructure. Connect 12 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.
What you can do
- Contact Orchestration — Sync and manage your entire customer contact directory programmatically, including creating new records and retrieving high-fidelity profile metadata
- Call Lifecycle Management — Monitor real-time incoming and outgoing call history and access high-fidelity recordings and metadata for every interaction
- Performance Intelligence — Retrieve aggregate call statistics and performance metrics to understand your team's throughput and customer engagement
- Team Coordination — Access directories of organization users to coordinate call routing and maintain an organized team structure directly through your agent
- Operational Monitoring — Configure and manage real-time webhooks for call events and retrieve account-level metadata for instant operational reporting
The Channels MCP Server exposes 12 tools through the Vinkius. Connect it to Mastra AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
All 12 Channels tools available for Mastra AI
When Mastra AI connects to Channels through Vinkius, your AI agent gets direct access to every tool listed below — spanning cloud-phone, call-tracking, live-chat, and more. Every call is secured with network, filesystem, subprocess, and code evaluation entitlements inside a sandboxed runtime. Beyond a simple connection, you get a full AI Gateway with real-time visibility into agent activity, enterprise governance, and optimized token usage.
Create a new contact
Create a new webhook
Delete a contact
Get account details
Get call recording URL
Get call statistics
Get contact details
List recent calls
List all customer contacts
List account users
List configured webhooks
Update an existing contact
Connect Channels to Mastra AI via MCP
Follow these steps to wire Channels into Mastra AI. The entire setup takes under two minutes — your credentials stay safe behind the Vinkius.
Install dependencies
npm install @mastra/core @mastra/mcp @ai-sdk/openaiReplace the token
[YOUR_TOKEN_HERE] with your Vinkius tokenRun the agent
agent.ts and run with npx tsx agent.tsExplore tools
Why Use Mastra AI with the Channels MCP Server
Mastra AI provides unique advantages when paired with Channels through the Model Context Protocol.
Mastra's agent abstraction provides a clean separation between LLM logic and tool infrastructure. add Channels 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 Channels 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
Channels + Mastra AI Use Cases
Practical scenarios where Mastra AI combined with the Channels MCP Server delivers measurable value.
Automated workflows: build multi-step agents that query Channels, process results, and trigger downstream actions in a typed pipeline
SaaS integrations: embed Channels as a first-class tool in your product's AI features with Mastra's clean agent API
Background jobs: schedule Mastra agents to query Channels on a cron and store results in your database automatically
Multi-agent systems: create specialist agents that collaborate using Channels tools alongside other MCP servers
Example Prompts for Channels in Mastra AI
Ready-to-use prompts you can give your Mastra AI agent to start working with Channels immediately.
"List all my customer contacts in Channels."
"Show the last 5 calls and their duration."
"Get the recording for call ID 'call_789'."
Troubleshooting Channels MCP Server with Mastra AI
Common issues when connecting Channels to Mastra AI through the Vinkius, and how to resolve them.
createMCPClient not exported
npm install @mastra/mcpChannels + Mastra AI FAQ
Common questions about integrating Channels MCP Server with Mastra AI.
How does Mastra AI connect to MCP servers?
MCPClient with the server URL and pass it to your agent. Mastra discovers all tools and makes them available with full TypeScript types.