telitask-mcp

Local

github.com/TelitaskCommunication1Updated 30w ago

About telitask-mcp

telitask-mcp is an MCP server for managing contacts, tasks, and calls in TeliTask from AI assistants. It also supports placing and scheduling calls, with access to call history, transcripts, and summaries.

Key features

01Place and schedule phone calls
02View call history and details
03Manage contacts
04Create and update tasks
05Verify numbers with phone codes

Use cases

01Have an AI assistant schedule calls to contacts
02Review call transcripts and summaries
03Organize contacts and tasks

MCP support

`@telitask/mcp-server` connects to MCP-compatible clients over stdio and exposes tools for managing contacts, tasks, and calls. A TeliTask account must be authenticated before connecting.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config

{
  "mcpServers": {
    "karanivincent-telitask": {
      "command": "npx",
      "args": [
        "-y",
        "@telitask/mcp-server"
      ]
    }
  }
}

Run commandnpx -y @telitask/mcp-server

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages

npm@telitask/mcp-server0.2.3stdio

Tools

Saved tool list · updated 2w ago

This tool takes no parameters.

Details

From the project README

AI-powered phone calls, task management, and contact organization

Website · npm · Report Bug · Discussions

Features

AI Voice Calls — Make and receive phone calls with AI-generated transcripts and summaries
Contact Management — Organize and manage your contacts
Task Tracking — Create, assign, and track tasks
MCP Server — Integrate with Claude Desktop, Claude Code, Cursor, and more

MCP Server

The @telitask/mcp-server package lets you manage contacts, tasks, and calls directly from your AI assistant.

Prerequisites

Node.js 18+
A TeliTask account

Step 1: Authenticate

npx @telitask/mcp-server login

This opens your browser to sign in and authorize the MCP server.

Step 2: Connect Your Client

Claude Desktop

Add to your claude_desktop_config.json:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "telitask": {
      "command": "npx",
      "args": ["-y", "@telitask/mcp-server"]
    }
  }
}

Restart Claude Desktop after saving.

Claude Code

claude mcp add telitask -- npx -y @telitask/mcp-server

Cursor

Add to .cursor/mcp.json in your project or globally:

{
  "mcpServers": {
    "telitask": {
      "command": "npx",
      "args": ["-y", "@telitask/mcp-server"]
    }
  }
}

VS Code (Copilot)

Open the Command Palette (Ctrl+Shift+P / Cmd+Shift+P)
Run MCP: Add Server
Select Command (stdio)
Enter command: npx -y @telitask/mcp-server
Name it telitask

Or add manually to .vscode/settings.json:

{
  "mcp": {
    "servers": {
      "telitask": {
        "command": "npx",
        "args": ["-y", "@telitask/mcp-server"]
      }
    }
  }
}

Windsurf

Add to your mcp_config.json:

{
  "mcpServers": {
    "telitask": {
      "command": "npx",
      "args": ["-y", "@telitask/mcp-server"]
    }
  }
}

Note: Don't see your client? Most MCP-compatible tools use the same config format. Check your client's MCP documentation and use the config above.

Available Tools

Tool	Description
`call_me`	Request a call to your phone
`make_call`	Make a call to a contact
`schedule_call`	Schedule a call for later
`cancel_call`	Cancel a scheduled call
`list_calls`	List call history
`get_call`	Get call details with transcript
`list_contacts`	List your contacts
`create_contact`	Create a new contact
`list_tasks`	List your tasks
`create_task`	Create a new task
`update_task`	Update an existing task
`send_phone_code`	Send a verification code to a phone number
`verify_phone_code`	Verify a phone number with a 6-digit code

Changelog

See CHANGELOG.md for release history.

License

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

Read the getting-started guide

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.