Leximo Ai Call Assistant Mcp Server

io.github.Leximo-AIPublished by GitHub account Leximo-AIv1.0.1Updated Oct 24, 2026

Schedule AI phone calls, manage assignments, and check credits from Claude.

Overview

AI-generated overview

Lets an assistant schedule and manage AI phone-call assignments, browse calling agents, and check credits and subscriptions in a Leximo account.

What you can do
Connects Claude Desktop or Claude Code to a Leximo account so the assistant can create, list, view, and delete AI phone-call assignments, and read a call's results and transcript. It also lists available calling agents, returns AI-generated suggestions for improving a task description, and reports credit balance, usage history, subscription details, available plans, and notifications. A checkout-session tool returns a URL for subscribing to a plan.
When to use it
Useful when you already use Leximo for AI phone calls and want to start, review, or clean up assignments and check credits from the assistant instead of the web app. Also handy for comparing calling agents or getting wording suggestions before placing a call.
Requirements
Runs locally over stdio, typically via npx, so Node.js is needed. Requires a Leximo account and the LEXIMO_API_TOKEN environment variable, described as a JWT access token copied from the account profile page. Network access to Leximo services is implied.
Before you install
The LEXIMO_API_TOKEN is a required secret placed in the client configuration; anyone with it can act on the account, so keep it out of shared files. Tools can create and delete assignments and start a checkout session, which may lead to a paid subscription. Call transcripts and account data are read from and sent to Leximo's service.

Installation

In SourceWeft

  1. Open Leximo Ai Call Assistant Mcp Server in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Leximo AI Call Assistant — MCP Server

[npm version] [Node >=18] [MCP] [License: MIT]

An MCP (Model Context Protocol) server that lets you schedule AI phone calls and manage Leximo assignments directly from Claude Desktop or Claude Code — no app switching needed.


Quick Install

Claude Code (one command)

bash
claude mcp add leximo -e LEXIMO_API_TOKEN=your-token -- npx -y leximo-ai-call-assistant-mcp-server

Replace your-token with your API token from concierge.leximo.ai/profile.

Claude Code (plugin marketplace)

/plugin marketplace add leximo-ai/leximo-ai-call-assistant-mcp-server

Then install the plugin:

/plugin install leximo-ai-call-assistant

Manual Setup

1. Get your API token

  1. Go to concierge.leximo.ai and sign in
  2. Open your profile page
  3. Copy your JWT access token

2. Configure Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

json
{  "mcpServers": {    "leximo": {      "command": "npx",      "args": ["-y", "leximo-ai-call-assistant-mcp-server"],      "env": {        "LEXIMO_API_TOKEN": "your-token"      }    }  }}

3. Configure Claude Code (manual)

Add to your Claude Code MCP settings:

json
{  "mcpServers": {    "leximo": {      "command": "npx",      "args": ["-y", "leximo-ai-call-assistant-mcp-server"],      "env": {        "LEXIMO_API_TOKEN": "your-token"      }    }  }}

Features

  • Assignments — Create, list, view, and delete AI phone call assignments
  • AI Agents — Browse available calling agents and pick the right one
  • Task Proposals — Get AI-generated improvements for your call instructions
  • Credits — Check your credit balance and usage history
  • Subscriptions — View your plan, browse available plans, and subscribe
  • Notifications — View call completion events and system notifications

Available Tools

ToolDescription
get_profileGet your user profile and account details
get_creditsCheck credit balance, usage history, and subscription summary
get_subscriptionView active subscription details
get_plansList available subscription plans with pricing
create_checkout_sessionGet a checkout URL to subscribe to a plan
list_agentsList available AI calling agents
get_agentGet details of a specific agent
list_assignmentsList all your assignments (paginated)
get_assignmentView a specific assignment with results and transcript
create_assignmentCreate a new phone call assignment
delete_assignmentDelete an assignment
get_assignment_proposalsGet AI suggestions to improve your task description
list_notificationsGet call completion events and notifications

Example Prompts

Once configured, ask Claude things like:

  • "Show me my Leximo assignments"
  • "Create a call to +1234567890 to book a restaurant for 2 at 7pm Friday"
  • "How many credits do I have left?"
  • "What subscription plans are available?"
  • "Show me the transcript from my last call"
  • "What agents are available and which one is best for restaurant bookings?"

Development

bash
npm installnpm run build      # Compile TypeScriptnpm start          # Run compiled servernpm run dev        # Run with tsx (hot reload)

Test with MCP Inspector

bash
LEXIMO_API_TOKEN=your-token npx @modelcontextprotocol/inspector node dist/index.js

Environment Variables

VariableRequiredDescription
LEXIMO_API_TOKENYesJWT token from concierge.leximo.ai/profile

Copy .env.example to .env for local development.


License

MIT © Leximo

Source: README.md at commit a2b6e07

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.1LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts