How do I use leximo-ai-call-assistant-mcp-server?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@leximo-ai-call-assistant-mcp-server Schedule a call to +1234567890 to confirm appointment" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

leximo-ai-call-assistant-mcp-server

Official

by Leximo-AI

Overview Schema Source Related Servers Discussions Admin

JavaScript

Remote

Leximo AI Call Assistant — MCP Server

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)

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

Related MCP server: hermes-mcp

Manual Setup

1. Get your API token

Go to concierge.leximo.ai and sign in
Open your profile page
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):

{
  "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:

{
  "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

Tool	Description
`get_profile`	Get your user profile and account details
`get_credits`	Check credit balance, usage history, and subscription summary
`get_subscription`	View active subscription details
`get_plans`	List available subscription plans with pricing
`create_checkout_session`	Get a checkout URL to subscribe to a plan
`list_agents`	List available AI calling agents
`get_agent`	Get details of a specific agent
`list_assignments`	List all your assignments (paginated)
`get_assignment`	View a specific assignment with results and transcript
`create_assignment`	Create a new phone call assignment
`delete_assignment`	Delete an assignment
`get_assignment_proposals`	Get AI suggestions to improve your task description
`list_notifications`	Get 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

npm install
npm run build      # Compile TypeScript
npm start          # Run compiled server
npm run dev        # Run with tsx (hot reload)

Test with MCP Inspector

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

Environment Variables

Variable	Required	Description
`LEXIMO_API_TOKEN`	Yes	JWT token from concierge.leximo.ai/profile

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

License

MIT © Leximo

Available Tools

13 tools

create_assignmentA

Create a new phone call assignment. Do NOT call this tool immediately. Follow this workflow:

Gather info: Ask the user for any missing details — phone number, desired call time, timezone, and language. Do NOT guess or fabricate values.
Select agent: Call list_agents to show available agents. Recommend one based on the task or let the user choose.
Improve task: Call get_assignment_proposals with the user's task description, then present the enhanced version for the user to approve or edit.
Confirm: Summarize all parameters (agent, name, datetime, timezone, phone number, language, task) and get user confirmation before calling this tool. Only call create_assignment after completing all steps above.

Inputs: agentId (required), name (required), datetime (required), timezone (required), +3 more.

create_checkout_sessionA

Create a Stripe checkout session to subscribe to a plan. Returns a URL the user should open in their browser to complete payment.

Inputs: priceId (required).

delete_assignmentB

Delete an assignment by its ID

Inputs: id (required).

get_agentB

Get details of a specific AI calling agent by ID

Inputs: id (required).

get_assignmentA

Get a single assignment by its ID, including call results, transcript, and recording URL

Inputs: id (required).

get_assignment_proposalsA

Get AI-generated enhancement proposals for a task description. IMPORTANT: Always call this BEFORE create_assignment to improve the task instructions. Pass the user's task description and present the enhanced suggestions to the user for approval before proceeding with assignment creation.

Inputs: task (required).

get_creditsA

Get credit balance, monthly allowance, usage history, and subscription summary for the authenticated user

Inputs: no named parameters.

get_plansA

List available subscription plans with pricing information

Inputs: no named parameters.

get_profileA

Get the authenticated user's profile information including email, credits, and account details

Inputs: no named parameters.

get_subscriptionA

Get the active Stripe subscription details for the authenticated user

Inputs: no named parameters.

list_agentsA

List all available AI calling agents. IMPORTANT: Always call this BEFORE creating an assignment. Present the returned agents to the user so they can choose which one should make the call, or recommend one based on the user's task. The agent's ID is required for create_assignment.

Inputs: no named parameters.

list_assignmentsB

List assignments (call tasks) for the authenticated user with pagination. Returns data, total, page, limit, and totalPages.

Inputs: page, limit.

list_notificationsA

Get paginated list of notifications for the current user. Includes call completion events and system notifications.

Inputs: limit, offset.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4/5.0

Scored 2026-06-22 08:25 across 13 tools

Disambiguation5/5

All 13 tools have clearly distinct purposes. There is no overlap; each tool targets a unique resource or action, such as creating vs. listing assignments, retrieving agents, or managing subscriptions.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern in snake_case (e.g., create_assignment, list_agents, get_credits). No mixing of conventions or ambiguous verbs.

Tool Count5/5

With 13 tools, the set is well-scoped for the server's purpose (AI calling assignments and subscription management). Each tool has a clear role, and there are no extraneous tools.

Completeness4/5

The tool surface covers core workflows: assignment CRUD (except update), agent management, subscription management, and notifications. Missing an update_assignment tool is a minor gap, but the design intentionally uses creation via proposals.

Maintenance

ActivityInactive

ResponsivenessLimited data

Resources

Related MCP Connectors

Artificial Wit AI
com.artificialwit
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
ERP Systems CRM Knowledge & Memory
2
https://api.artificialwit.com/mcp
Wixzel Voice
com.wixzel
Lets Claude, Cursor or any MCP client build voice agents and place real phone calls.
Speech Processing Autonomous Agents Communication
1
https://mcp.voice.wixzel.com/mcp
CallRail MCP by InsightfulPipeA
com.insightfulpipe
Hosted CallRail MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
Marketing Communication Customer Support
41
https://callrail.insightfulmcp.com/
Server4AgentA
com.server4agent
MCP server that lets your AI assistant build and deploy apps, hosting each one at a live URL.
App Automation Cloud Platforms Developer Tools
343
https://mcp.server4agent.com

Related MCP Servers

Calendly MCP Server
Calendar Management Communication
NyxToolsDev
A
license
A
quality
D
maintenance
An MCP server that connects Claude Desktop and Claude Code to your Calendly account, enabling natural-language scheduling management.
Updated 7 months ago (2026-04-06 20:59 UTC)
7
33 PyPI
MIT
hermes-mcp
Agent Orchestration Browser Automation Autonomous Agents
mlennie
A
license
Not graded
quality
C
maintenance
An MCP server that allows Claude Desktop and other MCP clients to delegate tasks to a local Hermes Agent for automation and persistent operations.
Updated a month ago (2026-09-29 19:33 UTC)
40 PyPI
69
Apache 2.0
Local Development MCP Server
Developer Tools File Systems Knowledge & Memory
lreb
A
license
Not graded
quality
D
maintenance
A local MCP server for Claude Desktop with persistent task management, file operations, document generation, and PDF indexing.
Updated 8 months ago (2026-03-19 20:49 UTC)
512 npm
1
MIT
MCP-Server
File Systems Browser Automation Developer Tools
prajna-gajendra-acharya
A
license
Not graded
quality
D
maintenance
A production-ready MCP server with file management, HTTP requests, system info, and environment variable tools, plus a management UI and dual transport for Claude Desktop and Claude.ai.
Updated 7 months ago (2026-04-08 02:24 UTC)
512 npm
MIT

Leximo AI Call Assistant — MCP Server

Quick Install

Claude Code (one command)

Claude Code (plugin marketplace)

Manual Setup

1. Get your API token

2. Configure Claude Desktop

3. Configure Claude Code (manual)

Features

Available Tools

Example Prompts

Development

Test with MCP Inspector

Environment Variables

License

Available Tools

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

Calendly MCP Server

hermes-mcp

Local Development MCP Server

MCP-Server