Which integrations are available for this server?

Provides WhatsApp marketing and messaging functionality including template creation, template management, bulk messaging, and conversation management for business communications within and outside the 24-hour messaging window.

How do I use Titanmind WhatsApp MCP?

1. Click on "Install 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., "@Titanmind WhatsApp MCP get recent conversations from the last 24 hours" 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.

Titanmind WhatsApp MCP

by TitanmindAGI

Overview Schema Related Servers Score Discussions

Python

Hybrid

Titanmind WhatsApp MCP

A WhatsApp marketing and messaging tool MCP (Model Control Protocol) service using Titanmind. Handles free-form messages (24hr window) and template workflows automatically

Related MCP server: whatsapp-mcp-server

Overview

This service provides all the WhatsApp marketing and messaging functionalities using Titanmind. Includes features like template creation and registration with all components header, body, CTAs.., template broadcast to phone numbers in bulk. Read and send messages in an active conversation.

This MCP utilizes Titanmind. Titanmind Account is a requirement to use this MCP.
Titanmind enhances WhatsApp communication by providing powerful features such as conversation management, scheduling, agentic conversations, content generation etc.

Features

Conversation Management

Get Recent Conversations

Retrieve all conversations with messages sent or received in the last 24 hours
Returns conversation data with recent activity

Get Conversation Messages

Fetch all messages from a specific conversation
Requires: conversation_id (alphanumeric conversation identifier)

Send WhatsApp Message

Send a message to an existing WhatsApp conversation
Requires: conversation_id and message content

Template Management

Create Message Template

Register new WhatsApp message templates for approval
Configure template name (single word, underscores allowed only)
Set language (default: "en") and category (MARKETING, UTILITY, AUTHENTICATION)
Structure message components including:
- BODY (required): Main text content
- HEADER (optional): TEXT, VIDEO, IMAGE, or DOCUMENT format
- FOOTER (optional): Footer text
- BUTTONS (optional): QUICK_REPLY, URL, or PHONE_NUMBER actions

Get Templates

Retrieve all created templates with approval status
Optional filtering by template name

Send Bulk Messages

Send messages to multiple phone numbers using approved templates
Requires: template_id and list of contacts
Contact format: country code alpha (e.g., "IN"), country code (e.g., "91"), and phone number

Installation

Prerequisites

Python 3.10 or higher
API Key and Business Code from Titanmind

Usage with MCP Client

In any MCP Client like Claude or Cursor, Titanmind whatsapp MCP config can be added following ways:

Using Titanmind WhatsApp MCP Python package

1. Install pipx to install the python package globally

# terminal

# Install pipx first
brew install pipx  # on macOS
# or
sudo apt install pipx  # on Ubuntu/Debian

# Then install Titanmind WhatsApp MCP Python package 
pipx install titanmind-whatsapp-mcp

# Make sure '/[HOME_DIR_OR_USER_PRFILE]/.local/bin' is on your PATH environment variable. Use pipx ensurepath to set it.
pipx ensurepath

2. Set the MCP Config python package script in the MCP Client's MCP Configs Json file.

{
  "mcpServers": {
    "TitanMindMCP": {
      "command": "/[HOME_DIR_OR_USER_PRFILE]/.local/bin/titan-mind-mcp",
      "args": [
      ],
      "env": {
        "api-key": "XXXXXXXXXXXXXXXXXXXXXXXX",
        "bus-code": "XXXXXX"
      }
    }
  }
}

Use Remote Titanmind MCP server config

1. Make sure npx is installed in the system
2. Then just add the MCP config

{
  "mcpServers": {
    "TitanMindMCP": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://mcp.titanmind.so/whatsapp/mcp/",
        "--header",
        "api-key:XXXXXXXXXXXXXXXXXXXXXXX",
        "--header",
        "bus-code:XXXXXX"
      ]
    }
  }
}

Use local python project config

1. First Setup project using instructions mentioned in the Setup Project section.
2. Then add the MCP config

{
  "mcpServers": {
    "TitanMindMCP": {
      "type": "stdio",
      "command": "uv",
      "args": [
        "run",
        "--directory",
        "/[PATH_TO_THE_PROJECT]",
        "python",
        "main.py"
      ],
      "env": {
        "api-key": "XXXXXXXXXXXXXXXXXXXX",
        "bus-code": "XXXXXX"
      }
    }
  }
}

Manual Installation for custom purpose or development

Install package from PyPI for package use

pip install titanmind-whatsapp-mcp

Or use uv:

uv pip install titanmind-whatsapp-mcp

Setup Project for development use

1. Clone the repository:

git clone https://github.com/TitanmindAGI/titanmind-whatsapp-mcp
cd titanmind-whatsapp-mcp

2. Install dependencies:

pip install -e .
# Or
uv pip install -e .

3. Set the auth keys

export api-key="your-titanmind-api-key"
export bus-code="your-titanmind-business-code"

How it Works

TitanMind's WhatsApp messaging system operates under two distinct messaging modes based on timing and conversation status:

Free-Form Messaging (24-Hour Window)

When Available: Only after a user has sent a message within the last 24 hours
Content Freedom: Any content is allowed without pre-approval
Use Case: Ongoing conversations and immediate responses

Template Messaging (Outside 24-Hour Window)

When Required: For new conversations or when the 24-hour window has expired
Content Structure: Pre-approved, structured message templates only
Use Case: Initial outreach and re-engagement campaigns

Messaging Workflow Process

Check Messaging Window Status
- Verify if receiver's phone number is within the free-form messaging window
- A receiver is eligible for free-form messaging if:
  - A conversation with their phone number already exists AND
  - The receiver has sent a message within the last 24 hours
Choose Messaging Method
- Free-Form: Send directly if within 24-hour window
- Template: Register and use approved template if outside window
Template Approval Process (if needed)
- Submit template for WhatsApp approval
- Wait for approval confirmation
- Template becomes available for bulk messaging
Send Message
- Execute message delivery using appropriate method
- Monitor delivery status
Verify Delivery
- Check conversation to confirm receiver successfully received the message
- Track message status and engagement

Usage Notes

All tools integrate with Titanmind's WhatsApp channel messaging functionality
Templates require approval before they can be used for bulk messaging
For more help contact us through https://www.titanmind.so/

License

MIT License - See LICENSE file

Available Tools

6 tools

get_conversations_from_the_last_dayD

ParametersJSON Schema

Name	Required	Description	Default
`phone_without_dialer_code`	No		None

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_the_messages_of_a_conversation_D

ParametersJSON Schema

Name	Required	Description	Default
`conversation_id`	Yes

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_the_templatesD

ParametersJSON Schema

Name	Required	Default
`template_name`	No	None
`page`	No
`page_size`	No

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

register_msg_template_for_approvalB

creates and registers a new whatsapp message template for approval.
Args:
    template_name (str): name of the whatsapp message template, It only accepts a single word without no special characters except underscores
    language (str): language of the whatsapp message template (default is "en")
    category (str): category of the whatsapp message template (default is "MARKETING"), other possible values are "UTILITY", "AUTHENTICATION"
    message_content_components (dict): the message content that needs to be sent. It needs to be structured like the below example, 
    components are required to have BODY component at least, like this: {"type": "BODY", "text": "lorem body text"}, BODY component is for the simple text.
    All other components are optional. 
    HEADER component can have any of the below format, but only one format at a time can be used.: TEXT(the header component with TEXT needs to be like this
    {
    "type": "HEADER",
    "format": "TEXT",
    "text": "lorem header text"
    }
    ), VIDEO(the header component with VIDEO needs to be like this
    {
     "type":"HEADER",
     "format":"VIDEO",
     "example":{
        "header_handle":[
           "https://sample_video_url.jpg"
        ]
     }
    }
    )
    , IMAGE(the header component with IMAGE needs to be like this 
    {
     "type":"HEADER",
     "format":"IMAGE",
     "example":{
        "header_handle":[
           "https://sample_image_url.jpg"
        ]
     }
    }),
   DOCUMENT (the header component with DOCUMENT needs to be like this 
    {
     "type":"HEADER",
     "format":"DOCUMENT",
     "example":{
        "header_handle":[
           "https://sample_document_url"
        ]
     }
  }),
    message_content_components value with all other type of components is mentioned below.
        [
                {
                    "type": "HEADER",
                    "format": "TEXT",
                    "text": "lorem header text"
                },
                {
                    "type": "BODY",
                    "text": "lorem body text"
                },
                {
                    "type": "FOOTER",
                    "text": "lorem footer text"
                },
                {
                    "type": "BUTTONS",
                    "buttons": [
                        {
                            "type": "QUICK_REPLY",
                            "text": "lorem reply bt"
                        },
                        {
                          "type": "URL",
                          "text": "cta",
                          "url": "https:sample.in"
                        },
                        {
                          "type": "PHONE_NUMBER",
                          "text": "call ",
                          "phone_number": "IN328892398"
                        }
                    ]
                }
            ]
    Buttons need to follow order of first QUICK_REPLY, then URL, and then PHONE_NUMBER.

ParametersJSON Schema

Name	Required	Default
`template_name`	Yes
`message_content_components`	Yes
`language`	No	en
`category`	No	MARKETING

TDQS

B3.1/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden for behavioral disclosure. While it describes the creation/registration action, it doesn't mention important behavioral aspects like: whether this requires specific permissions, what happens after approval, whether templates can be modified later, rate limits, or error conditions. The description covers the basic operation but lacks critical behavioral context for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is excessively long and poorly structured. It buries the core purpose in a wall of text with repetitive formatting examples. While the parameter information is valuable, it could be organized more efficiently. The description lacks front-loading of critical information and contains redundant examples that don't earn their place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 4-parameter mutation tool with no annotations and no output schema, the description provides excellent parameter documentation but lacks other critical context. It doesn't explain what happens after registration, what the approval process entails, what permissions are needed, or what the tool returns. The parameter coverage is strong, but overall completeness is compromised by missing behavioral and operational context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description compensates excellently by providing detailed semantic information for all 4 parameters. It explains template_name restrictions, language and category defaults/enums, and provides extensive examples and formatting rules for message_content_components. The description adds substantial value beyond the bare schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool 'creates and registers a new whatsapp message template for approval', specifying both the action (creates/registers) and resource (whatsapp message template). However, it doesn't differentiate from sibling tools like 'get_the_templates' or 'send_msg_to_multiple_num_using_approved_template', which prevents a perfect score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. There's no mention of prerequisites, when this tool is appropriate compared to sibling tools, or any exclusions. The only implied usage is for creating WhatsApp templates, but no contextual boundaries are established.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

send_msg_to_multiple_num_using_approved_templateD

ParametersJSON Schema

Name	Required	Description	Default
`template_id`	Yes
`contacts`	Yes

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

send_whatsapp_message_to_a_conversationD

ParametersJSON Schema

Name	Required	Description	Default
`conversation_id`	Yes
`message`	Yes

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

D1.7/5.0

Disambiguation3/5

The tools have distinct purposes (get conversations, get messages, get templates, register template, send template messages, send direct messages), but some ambiguity exists between 'send_msg_to_multiple_num_using_approved_template' and 'send_whatsapp_message_to_a_conversation' since both involve sending messages. The lack of descriptions for most tools exacerbates this overlap.

Naming Consistency2/5

Naming is inconsistent with mixed conventions: some use snake_case with underscores (e.g., 'get_conversations_from_the_last_day'), others have trailing underscores (e.g., 'get_the_messages_of_a_conversation_'), and verbs vary (e.g., 'get' vs. 'register'). While all names are descriptive, the lack of a uniform pattern reduces predictability.

Tool Count4/5

With 6 tools, the count is reasonable for a WhatsApp-focused server, covering core operations like retrieving conversations/messages/templates, registering templates, and sending messages. It's slightly lean but not overly sparse, allowing for basic functionality without being overwhelming.

Completeness3/5

The server covers key WhatsApp operations (read conversations/messages, manage templates, send messages), but there are notable gaps: no tools for updating or deleting templates, managing conversation participants, or handling message statuses. The surface supports basic workflows but lacks full lifecycle management for templates and conversations.

Maintenance

ActivityInactive

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

TopMessage
com.topmessage
Send and schedule SMS and WhatsApp messages, manage contacts and templates, and track delivery.
Communication App Automation
1
DripRaven WhatsApp campaigns
com.dripraven
Run WhatsApp Business campaigns from any AI assistant: contacts, segments, and broadcasts.
Communication Marketing
1
chatflow
io.github.Yersat
WhatsApp CRM for AI agents: search contacts, read chats, manage the sales pipeline, send messages.
CRM Communication
2
kontato A
ai.kontato
Give your AI agents a real WhatsApp number to send and receive messages.
Communication Autonomous Agents
92

Related MCP Servers

WhatsApp MCP Server
Communication App Automation Marketing
ampcome-mcps
A
license
B
quality
D
maintenance
Enables sending WhatsApp Business messages including text, media, interactive lists/buttons, and template management through the WhatsApp Business API via Nango integration.
Updated a year ago (2025-07-03 11:02 UTC)
11
MIT
whatsapp-mcp-server
Communication App Automation Customer Support
FredShred7
A
license
A
quality
D
maintenance
Connects AI assistants to the official Meta WhatsApp Cloud API for managing conversations and sending various message types through natural language. It provides tools for media management, template messages, and real-time webhook processing without the risk of account bans.
Updated 3 months ago (2026-06-07 00:59 UTC)
18
47
23
MIT
WhatsApp Business API MCP
Communication Customer Support Marketing
mattcoatsworth
A
license
Not graded
quality
D
maintenance
Enables sending messages, managing templates, uploading media, and configuring webhooks for WhatsApp Business via the MCP protocol.
Updated a year ago (2025-04-03 11:49 UTC)
12
5
MIT
Wasapi MCP Server
Communication Customer Support
Vinix-Code-Dev
A
license
B
quality
A
maintenance
Enables managing WhatsApp Business accounts through natural language, including sending messages, managing contacts, and querying conversations.
Updated a month ago (2026-08-08 20:22 UTC)
62
16
ISC

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/TitanmindAGI/titanmind-whatsapp-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server