ChanlChanl
Universal Integration

Connect to Claude, VAPI, Retell — via MCP

The Model Context Protocol gives any AI platform access to Chanl's agents, tools, memory, and knowledge base. One protocol, every platform.

Comienza GratisVer Demo

MCP Protocol

Standard Model Context Protocol support. Connect any MCP-compatible AI tool to your Chanl workspace with a single URL.

Any-Platform Connection

Works with Claude Desktop, Cursor, VAPI, Retell, and any platform that supports MCP. No custom integration needed.

Live Tool Access

Your agents' tools, memory, and knowledge base are accessible in real-time via MCP. Build once, connect everywhere.

Claude Desktop Integration

Connect Claude to your agents and tools

Add your Chanl workspace to Claude Desktop as an MCP server. Claude gets access to your agents, tools, knowledge base, and customer data — instantly.

  • One-click setup with Claude Desktop
  • Access all agent tools and knowledge bases
  • Customer data and memory available in Claude
  • Secure API key authentication
mcp-config.json
Live
{
"mcpServers":
{
"chanl":
{
"url": "https://acme.chanl.dev/mcp",
"transport": "sse",
"apiKey": "sk-chanl-...a4f2"
}
}
}
Tools
12 connected
Memory
Active
Knowledge
3 sources
Platform Connections

VAPI, Retell, and beyond

Any AI platform that supports MCP can connect to Chanl. Your agents get persistent memory, tools, and knowledge — regardless of where they run.

  • VAPI and Retell native MCP support
  • Custom platform integration via SSE transport
  • Workspace-level access control
  • Per-agent tool and memory scoping

VAPI

Connected

Voice agent platform with full MCP tool access

Retell

Connected

Conversational AI with real-time memory sync

ElevenLabs

Pending

Voice synthesis with knowledge base integration

SSE Transport

Real-time, streaming protocol

Server-Sent Events transport for low-latency, real-time tool execution. Your agents get responses as they stream — no polling, no delays.

  • SSE-based streaming for real-time responses
  • Automatic reconnection and error handling
  • Multi-tenant workspace isolation
  • Health monitoring and uptime tracking
mcp-stream
[09:41:12]connectionTransport: SSE | Status: Connected
[09:41:13]tool_list12 tools registered
[09:41:14]tool_callmemory.search({ query: 'billing...' })
[09:41:15]tool_result{ matches: 3, relevance: 0.94 }
[09:41:16]tool_callknowledge.query({ topic: 'refund...' })
[09:41:17]tool_result{ documents: 2, confidence: 0.91 }
[09:41:18]heartbeatlatency: 12ms
>
Platform

Explore More
Features

Build

Every channel, one brain

Run one agent or many across voice, chat, and SMS, all working from the same customer record.

Build

Takes real action

Agents call your APIs and databases to finish the customer's request.

Build

Remembers every customer

Persistent memory follows the customer across channels, so nobody repeats themselves.

Build

Knows your business

RAG-powered answers from your docs, FAQs, and knowledge base.

Build

Change it safely

Track prompt changes, compare versions, and roll back safely.

Build

Connects to anything

Connect any tool via Model Context Protocol. Open standard.

Test

Test before customers

Test with 25+ AI personas across edge cases before customers do.

Test

Every call graded

Custom scorecards evaluate accuracy, compliance, and tone.

Test

Realistic test callers

25+ personas with unique emotions, accents, and conversation patterns.

Test

Catch breaks early

Catch regressions before they reach customers. Run tests on every change.

Test

Stays on script

Verify your agent follows policies, scripts, and regulatory requirements.

Observe

Monitor AI live

Live dashboards show every conversation and where each customer stands.

Observe

Watch and step in

Watch conversations live and take over before a customer is lost.

Observe

Full transcripts

Every conversation with speaker labels, timestamps, and sentiment analysis.

Observe

Know when it breaks

Get notified when agents fail or sentiment drops, before customers feel it.

Observe

Know your spend

Track spend per agent, per channel, and per conversation.

Aprende IA agéntica

Aprende a crear agentes que funcionan

Hombre y mujer espalda con espalda en una oficina - Foto por Vitaly Gariev en Unsplash
Operations19 mar

Los agentes de IA son geniales. Hasta que no lo son. Cuando devolver el control a los humanos

Dos hombres filmando una escena al aire libre con obras de arte. - Foto por Luke Thornton en Unsplash
Testing & Evaluation19 mar

Zero-Shot o sin oportunidad? Como los agentes de IA manejan llamadas que nunca han visto

Codigo en la pantalla de una computadora. - Foto de Rob Wingate en Unsplash
Knowledge & Memory18 mar

Tu agente de IA no aprende de produccion. Esto es lo que te esta costando.

Enfoque selectivo de un cuadricoptero blanco y negro - Foto de Kenny Eliason en Unsplash
Agent Architecture13 mar

IA Conversacional vs. IA Agentiva: Cual es la diferencia y por que importa para equipos de CX

Dashboard moderno de pruebas de IA mostrando resultados de A/B testing, cobertura de unit tests y metricas de pruebas en vivo para la evaluacion de preparacion de agentes de IA conversacional
Testing & Evaluation11 mar

Tu agente de IA, esta realmente listo para produccion? Las 3 pruebas que la mayoria de los equipos se saltan

Ilustracion en acuarela de nodos de memoria interconectados formando una red de conocimiento en tonos verde salvia y oliva
Knowledge & Memory10 mar

Memoria de Agentes de IA: Del contexto de sesion al conocimiento a largo plazo

Ver todos los artículos

El briefing de Signal

Un email por semana. Cómo los equipos líderes de CS, ingresos e IA están convirtiendo conversaciones en decisiones. Benchmarks, playbooks y lo que funciona en producción.

500+ líderes de CS e ingresos suscritos

Preguntas Frecuentes