The Unipile MCP Server enables seamless communication and message management across multiple messaging platforms through a standardized interface. With this server, you can:
Access Messages: Retrieve messages from platforms like WhatsApp, LinkedIn, Instagram, Messenger, and Telegram
Account Management: Get details of connected messaging accounts, including IDs, names, and creation dates
Recent Messages: Fetch recent messages from all chats with pagination support
Email Access: Retrieve recent emails with details such as subject, body, sender, recipients, and attachments
AI Integration: Interact with messages using AI models like Claude
Cross-Platform Support: Works with Mobile, Mail, WhatsApp, LinkedIn, Slack, Twitter, Telegram, Instagram, and Messenger
Allows interaction with Instagram direct messages, enabling message retrieval and management through the Unipile messaging platform.
Provides access to Facebook Messenger conversations, allowing retrieval and management of messages through Unipile's platform.
Supports retrieval and management of Slack messages through the Unipile messaging platform.
Enables interaction with Telegram chats and messages through the Unipile unified messaging platform.
Provides tools for accessing and managing WhatsApp chats and messages through the Unipile messaging platform.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Unipile MCP Server get recent messages from my LinkedIn chat with John"
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.
MCP server for using Unipile to access messages across multiple messaging platforms.
A Model Context Protocol (MCP) server implementation that provides integration with the Unipile messaging platform. This server enables AI models to interact with messages from various messaging platforms (Mobile, Mail, WhatsApp, LinkedIn, Slack, Twitter, Telegram, Instagram, Messenger) through a standardized interface.
For more information about the Model Context Protocol and how it works, see Anthropic's MCP documentation.
Related MCP server: iMessage Max
To use the Unipile services, a subscription is required. I am not paid by Unipile to do this; I am simply a user who loves using Unipile because it works effectively. For more details on the subscription and features, visit the Unipile Messaging API page.
With Unipile, you can communicate seamlessly across a wide range of social platforms. This includes popular messaging services such as:
LinkedIn: Engage with professional contacts, send messages, and manage your LinkedIn interactions directly through the Unipile interface.
WhatsApp: Send and receive messages, manage chats, and stay connected with your contacts.
Instagram: Interact with followers, respond to direct messages, and manage your Instagram communications.
Messenger: Communicate with friends and family through Facebook Messenger.
Telegram: Access your Telegram chats and messages effortlessly.
Unipile's integration with these platforms allows for a unified communication experience, making it easier to manage interactions across different services. This is particularly beneficial for users who rely on LinkedIn for professional networking, as it enables them to leverage AI capabilities, such as Claude, to enhance their communication strategies.
The server exposes the following resources:
unipile://messages: A dynamic resource that provides access to messages from connected messaging platforms
Get all messages from a chat:
Get all messages from chat ID "chat_123"The server offers several tools for accessing Unipile data:
unipile_get_chat_messages
Retrieve all messages from a specific chat with pagination support
Input: chat_id (required), batch_size (optional, default: 100)
Returns: Array of message objects
You'll need a Unipile DSN and API key. You can obtain these from your Unipile dashboard.
UNIPILE_DSN: Your Unipile DSN (e.g. api8.unipile.com:13851)
UNIPILE_API_KEY: Your Unipile API key
Note: Keep your API key secure and never commit it to version control.
You can either build the image locally or pull it from Docker Hub. The image is built for the Linux platform.
Linux/amd64
Linux/arm64
Linux/arm/v7
docker pull buryhuang/mcp-unipile:latestdocker build -t mcp-unipile .Run the container:
docker run \
-e UNIPILE_DSN=your_dsn_here \
-e UNIPILE_API_KEY=your_api_key_here \
buryhuang/mcp-unipile:latestTo publish the Docker image for multiple platforms, you can use the docker buildx command. Follow these steps:
Create a new builder instance (if you haven't already):
docker buildx create --useBuild and push the image for multiple platforms:
docker buildx build --platform linux/amd64,linux/arm64,linux/arm/v7 -t buryhuang/mcp-unipile:latest --push .Verify the image is available for the specified platforms:
docker buildx imagetools inspect buryhuang/mcp-unipile:latest{
"mcpServers": {
"unipile": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"UNIPILE_DSN=your_dsn_here",
"-e",
"UNIPILE_API_KEY=your_api_key_here",
"buryhuang/mcp-unipile:latest"
]
}
}
}To set up the development environment:
pip install -e .This project is licensed under the MIT License.
Get all connected messaging accounts from supported platforms: Mobile, Mail, WhatsApp, LinkedIn, Slack, Twitter, Telegram, Instagram, Messenger. Returns account details including connection parameters, ID, name, creation date, signatures, groups, and sources.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It indicates a read operation and lists return fields, but does not mention authentication, rate limits, or how 'all' accounts are determined (e.g., pagination or scope). The behavioral transparency is adequate but incomplete.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that front-loads the main action and includes a list of platforms and return fields. It is concise but could be slightly more streamlined; however, it is not overly verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no parameters and no output schema, the description adequately explains what the tool does and what it returns. It does not mention limits or behavior under different conditions, but for a simple read-only list operation, it is fairly complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are no parameters (schema coverage 100%), so the baseline is 4. The description adds meaning by explaining the return value in detail, which compensates for the lack of parameter information.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and the resource 'all connected messaging accounts', listing specific platforms. It distinguishes itself from sibling tools like unipile_get_emails and unipile_get_recent_messages by focusing on accounts rather than emails or messages.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not explicitly state when to use this tool vs alternatives, but the sibling tools' names imply different resources (emails vs messages vs accounts). The context is clear enough for an agent to infer appropriate usage, though explicit guidance would improve the score.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get recent emails from a specific account. Returns email details including subject, body, sender, recipients, attachments, and metadata.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of emails to return (default: 10) | |
| account_id | Yes | The ID of the account to get emails from |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description carries full burden. It lists returned fields (subject, body, sender, recipients, attachments, metadata) and mentions 'recent'. This adds value beyond the schema, but does not cover pagination, rate limits, or permissions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence with clear verb and resource, front-loaded, no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple list tool with 2 parameters and no output schema, the description covers purpose and return fields adequately. Could mention pagination or error handling, but not essential.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% (both parameters have descriptions). The description only adds 'recent' and 'specific account' context, which is marginal. Baseline 3 is appropriate since schema already documents parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Get recent emails from a specific account' with a specific verb and resource, and it distinguishes from siblings like unipile_get_accounts and unipile_get_recent_messages.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives, nor any exclusions or prerequisites. It is implied to use when needing emails from an account, but lacks direct comparison.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get recent messages from all chats associated with a specific account. Supports messages from: Mobile, Mail, WhatsApp, LinkedIn, Slack, Twitter, Telegram, Instagram, Messenger. Returns message details including text content, sender info, timestamps, attachments, reactions, quoted messages, and metadata.
| Name | Required | Description | Default |
|---|---|---|---|
| account_id | Yes | The one source ID of of the account to get messages from. It is the id of the source objects in the account's sources array. | |
| batch_size | No | Number of messages to fetch per chat (default: 20) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It details return fields (text, sender, timestamps, attachments, etc.), but lacks disclosure on side effects, rate limits, idempotency, or reading permissions. The 'get' action implies read-only but is not stated.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences with no superfluous text. First sentence states core action, second enumerates supported platforms and return details. Front-loaded and efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no output schema, the description explains return details adequately. However, it omits pagination behavior, ordering of messages, and does not mention the default batch size (schema covers it). Minor gap in complete context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers both parameters with descriptions (100% coverage), so baseline is 3. The description adds context about supported platforms but does not elaborate on parameter usage beyond schema. No new semantic value for parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves recent messages from all chats for a specific account, listing supported platforms. It distinguishes itself from sibling tools (unipile_get_accounts, unipile_get_emails) by focusing on messages across chat platforms.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for fetching recent messages but does not explicitly specify when to use versus alternatives or provide any exclusions. No guidance on prerequisite actions or when not to use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.1unipile_get_accountsunipile_get_emailsunipile_get_recent_messagesScored across 3 tools
Each tool targets a distinct resource: accounts, emails, and messages. The descriptions clearly separate emails (from a specific account) from recent messages (from all chats), so no ambiguity.
All tool names follow the consistent pattern 'unipile_get_<resource>', using snake_case and the same verb prefix, making them predictable.
With 3 tools, the server is focused on read operations for accounts, emails, and messages. This is appropriate for a read-only interface, though it is slightly minimal.
The server covers basic read operations but lacks common features like searching, filtering, or fetching specific messages by ID. For a messaging platform, missing send/delete is acceptable if intended as read-only, but the surface is still limited.
Unified inbox MCP for WhatsApp, Telegram, Email, voice — read/send messages, search, AI agents.
Unified messaging MCP server: WhatsApp, Instagram, Telegram, SMS, Messenger & email support inbox
Pass messages between AI agents with cleaning, metadata enrichment, and metered billing.
Instagram, WhatsApp and Messenger DMs through official Meta Business APIs.
