Aircall MCP Server

Aircall MCP Server

MCP server providing 83 tools to manage Aircall calls, transcriptions, AI insights, contacts, SMS, users, teams, and more via the Aircall Public API, compatible with Claude Desktop and other MCP clients.

Category
Visit Server

README

Aircall MCP Server

License: MIT MCP TypeScript

MCP server for the Aircall Public API — 83 tools for calls, transcriptions, AI insights, contacts, SMS, users, teams, and more. Works with Claude Desktop, Claude Code, Cursor, and any MCP-compatible AI assistant. Maintained by Cassia Research.

Every tool is verified against the official Aircall API reference. Tools carry MCP annotations (readOnlyHint, destructiveHint, titles), so clients like Claude Desktop can group read-only tools and gate destructive ones.

Not an official Aircall product. This is a community server built and maintained by Cassia Research.

Installation

Claude Desktop — one-click extension (recommended)

This is our default integration path. No Node.js or config-file editing required for end users — Claude Desktop runs the server on its own bundled runtime.

Build the extension:

npm install
npm run bundle   # builds TypeScript and packs aircall-mcp.mcpb

Install it:

  1. Share aircall-mcp.mcpb with your team (Slack, Drive, or this repo's Releases).
  2. Double-click it (or Claude Desktop → Settings → Extensions → Advanced settings → Install extension…).
  3. Enter your Aircall API ID and API Token — created in the Aircall Dashboard under Integrations & API → API Keys. The token is stored in your OS keychain.
  4. Optionally enable Read-only mode to expose only the 36 read tools.

To ship an update: bump the version (see CLAUDE.md), run npm run bundle again, and have users double-click the new file — it updates in place, keeping their saved credentials.

Claude Desktop / Cursor — manual config

{
  "mcpServers": {
    "aircall": {
      "command": "npx",
      "args": ["-y", "@cassiaresearch/aircall-mcp-server"],
      "env": {
        "AIRCALL_API_ID": "your_api_id",
        "AIRCALL_API_TOKEN": "your_api_token"
      }
    }
  }
}

CLI

npx @cassiaresearch/aircall-mcp-server --api-id=xxx --api-token=yyy

# Read-only mode
npx @cassiaresearch/aircall-mcp-server --api-id=xxx --api-token=yyy --read-only

# Only specific categories
npx @cassiaresearch/aircall-mcp-server --api-id=xxx --api-token=yyy --tools=calls,contacts

Tools (83)

Category Tools Highlights
Calls 24 list/search calls, transcription, AI summary, sentiments, topics, action items, predicted CSAT, custom summary, playbook results, evaluations, comments, tags, archive/unarchive, transfer, recording controls, insight cards, AI Voice Agent outbound calls
Contacts 12 CRUD plus phone number and email management
Users 10 CRUD, availability, start call, dial, user numbers (API v2)
Teams 6 CRUD and membership
Numbers 5 list/get/update, music & messages, A2P registration status
Tags 5 CRUD
Webhooks 5 CRUD
Messages 5 send SMS/MMS, agent-conversation send, number messaging configuration
Dialer 6 per-user power dialer campaigns
Company 5 ping (connectivity test), company info, integration enable/disable

Full per-tool documentation with parameters: docs/tools/README.md (generated from the server itself via npm run docs).

Configuration

Option Env var Description
--api-id AIRCALL_API_ID Aircall API ID (required)
--api-token AIRCALL_API_TOKEN Aircall API token (required)
--read-only AIRCALL_READ_ONLY=true Expose only read tools (36)
--tools=... AIRCALL_TOOLS Comma-separated tools or categories; all (default) or read

Notes:

  • Authentication is HTTP Basic with the org-level api_id:api_token pair.
  • Requests are rate-limited client-side to respect Aircall's 60 req/min limit.
  • Conversation Intelligence tools (transcription, summary, sentiments, topics, action items, CSAT, playbooks, evaluations) require the corresponding Aircall AI add-ons on your account — without them the API returns 403/404.

Development

npm install
npm run build        # compile TypeScript to dist/
npm run lint         # eslint
npm run docs         # regenerate docs/tools/README.md from the built server
npm run bundle       # build + pack aircall-mcp.mcpb (Claude Desktop extension)

License

MIT — see LICENSE.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured
E2B

E2B

Using MCP to run code via e2b.

Official
Featured