Allows deploying AI sales chatbots to WhatsApp, enabling customer interaction and lead qualification through WhatsApp messaging.
Click on "Install 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., "@AutoManus MCP Server Create a sales agent for Stripe"
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.
Create AI sales agents instantly from Claude Desktop, Cursor, or any MCP-compatible AI tool.
AutoManus MCP Server lets you build and deploy AI sales chatbots to WhatsApp and Webchat in seconds - all from your favorite AI coding assistant.
Instant Agent Creation - Just say "create a sales agent for [company]" and it's done
Auto Website Research - Analyzes the company website and populates knowledge base automatically
WhatsApp + Webchat - Agents deploy to both channels immediately
No Code Required - Works entirely through natural language with Claude/Cursor
Free Tier - 100 free credits to get started, no credit card required
Related MCP server: Arara MCP
Add to your Claude Desktop config file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"automanus": {
"command": "npx",
"args": ["-y", "@automanus/mcp-server"]
}
}
}Restart Claude Desktop, then try:
"Create an AI sales agent for Stripe"
Add to ~/.cursor/mcp.json:
{
"mcpServers": {
"automanus": {
"command": "npx",
"args": ["-y", "@automanus/mcp-server"]
}
}
}Add to ~/.claude/mcp.json:
{
"mcpServers": {
"automanus": {
"command": "npx",
"args": ["-y", "@automanus/mcp-server"]
}
}
}Once installed, just talk to Claude naturally:
"Create a sales agent for my startup TechCo using techco.com as the knowledge source""Build an AI sales chatbot for Vercel""I need a customer service bot for my cleaning business at sparkclean.com"Claude will:
Ask for your email (to send the agent claim link)
Research the website automatically
Create the agent with knowledge base
Deploy to WhatsApp and Webchat
Send you an email with links to manage everything
No configuration required! Claude will ask for your email when creating an agent.
If you want to skip the email prompt:
{
"mcpServers": {
"automanus": {
"command": "npx",
"args": ["-y", "@automanus/mcp-server"],
"env": {
"AUTOMANUS_EMAIL": "your-email@example.com"
}
}
}
}With an API key, agents are created directly under your account:
{
"mcpServers": {
"automanus": {
"command": "npx",
"args": ["-y", "@automanus/mcp-server"],
"env": {
"AUTOMANUS_API_KEY": "ak_your_api_key_here"
}
}
}
}Get your API key from automanus.io/dashboard/settings/api.
When you create an agent, you receive:
Feature | Description |
AI Sales Agent | Trained on the company's website content |
WhatsApp Number | Shareable link for customers to chat |
Webchat Widget | Embed code for your website |
Knowledge Base | Auto-populated from website research |
Dashboard Access | Manage, train, and customize your agent |
Sales Teams - Qualify leads 24/7 on WhatsApp and website
Startups - Add AI customer service without hiring
Agencies - Build chatbots for clients in minutes
E-commerce - Answer product questions automatically
SaaS - Handle trial user questions and demos
Plan | Credits | Features |
Free | 100 | WhatsApp + Webchat, Basic KB |
Starter | 1,000/mo | Priority support, Analytics |
Pro | 5,000/mo | Custom branding, API access |
Discord - Get help, share feedback, and connect with other users
GitHub Issues - Report bugs
Email: hello@automanus.io
MIT
Add a knowledge base item to an existing AI sales agent. Use this to provide product info, FAQs, policies, or other information the agent should know.
| Name | Required | Description | Default |
|---|---|---|---|
| agent_id | Yes | The ID of the agent to add knowledge to (returned from create_sales_agent) | |
| title | Yes | Title of the knowledge item | |
| content | Yes | The content/body of the knowledge item | |
| item_type | No | Type of knowledge item (default: faq) | |
| category | No | Category for organizing (e.g., "Pricing", "Products", "Company Info") |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden for behavioral transparency. The description only states the basic action without disclosing important behavioral traits such as whether adding knowledge is append-only, if duplicates are handled, if there are limits on number of items or content length, or any authentication requirements. This leaves significant gaps for the agent to infer behavior.
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 concise with just two sentences. The first sentence states the main action and object, and the second sentence provides examples of use. Every sentence adds value without redundancy, making it easy for an agent to quickly grasp the tool's function.
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 the tool's moderate complexity (5 parameters, 3 required, no output schema), the description covers the basic use case but lacks completeness. It does not explain the effect of adding knowledge (e.g., whether it overwrites or appends), the maximum length of content, or any constraints. More context would be needed for a fully self-contained definition.
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 description coverage is 100%, so the baseline is 3. The description adds some context by mentioning examples of knowledge content but does not provide additional semantics beyond what the input schema already specifies for each parameter. It adds marginal value.
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's purpose: 'Add a knowledge base item to an existing AI sales agent.' It lists specific types of information (product info, FAQs, policies), making the action concrete. The tool is well-distinguished from siblings (create_sales_agent and generate_qr_code), which have entirely different functions.
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 provides clear usage guidance: 'Use this to provide product info, FAQs, policies, or other information the agent should know.' It directly tells the agent when to invoke the tool. However, it does not explicitly mention when not to use it or suggest alternatives among siblings, which would slightly improve the score.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Create an AI sales agent for a business. Researches the website automatically and deploys to WhatsApp and Webchat. Ask the user for their email if not provided.
| Name | Required | Description | Default |
|---|---|---|---|
| No | User email address for account creation and receiving the agent claim link. Ask the user for this. | ||
| company_name | Yes | Business/company name | |
| website_url | No | Website URL to research. We analyze it to populate knowledge base. | |
| agent_name | No | Custom agent name (optional, defaults to "{company} Assistant") |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses that the tool researches the website automatically and deploys to WhatsApp and Webchat, which are key behaviors. However, it does not mention side effects (e.g., overwriting existing agents), authentication requirements, rate limits, or error conditions, leaving gaps.
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 two sentences, front-loaded with the main purpose and a practical usage hint. Every word contributes meaning with no redundancy or filler.
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?
With no output schema, the description should cover return values. It states deployment targets but does not explain what the user receives (e.g., agent ID, claim link), though the schema's email description partially covers that. Overall, it is sufficient for basic use but could be more 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?
The input schema has 100% description coverage, so the baseline is 3. The description adds the note 'Ask the user for their email if not provided,' which reinforces the email parameter but does not provide significant new semantics beyond what the schema already describes.
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 creates an AI sales agent, with specific actions: 'Researches the website automatically and deploys to WhatsApp and Webchat.' This differentiates it from siblings add_knowledge and generate_qr_code, which have distinct purposes.
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 implicitly indicates usage when creating a sales agent, and adds guidance to 'Ask the user for their email if not provided.' However, it does not explicitly state when to use this tool versus alternatives, nor does it provide exclusions or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Generate a QR code for a URL or WhatsApp link. Returns a URL to the QR code image that can be opened in a browser or downloaded.
| Name | Required | Description | Default |
|---|---|---|---|
| url | No | Direct URL to encode in the QR code (e.g., https://example.com) | |
| phone | No | WhatsApp phone number with country code, no + sign (e.g., 16506053956). Used if url is not provided. | |
| message | No | Pre-filled WhatsApp message text. Used with phone parameter. | |
| size | No | QR code size in pixels (100-1000, default 300) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits. It states the tool returns a URL to the image, implying no side effects, but does not explicitly clarify that it is read-only or stateless, nor mention rate limits or authorization.
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, no wasted words, front-loaded with purpose and return type.
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 output schema, the description should clarify parameter relationships (e.g., url vs phone+message). It does not, and size parameter is omitted. Fairly complete for a simple tool but with gaps.
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% with descriptions for each parameter. The description adds context about URL vs WhatsApp usage but does not significantly augment the schema's meaning. Baseline score of 3 is appropriate.
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 it generates a QR code for a URL or WhatsApp link and returns a URL to the image. This distinguishes it from siblings like add_knowledge and create_sales_agent, which are unrelated.
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 its use for QR code generation, but provides no explicit guidance on when to use or not use it, nor alternatives. However, siblings are unrelated, so minimal guidance is acceptable.
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. Dates show when Glama detected each change.
v1.2.6add_knowledgecreate_sales_agentgenerate_qr_codeEach tool targets a distinct action: adding knowledge to an agent, creating an agent, and generating a QR code. No overlap in purpose.
All tool names follow a consistent verb_noun pattern (add_knowledge, create_sales_agent, generate_qr_code), making the API predictable.
Three tools is a small set, but it may be appropriate for a focused initial release. However, the server's purpose likely requires more tools for full agent management.
Missing essential CRUD operations: no update or delete for agents, no list or remove for knowledge items, and no management features for deployed agents or QR codes.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
WhatsApp AI sales agent on your own number via QR, no Meta API: audit chats, edit playbook, orders.
Lets AI agents get leads on the phone: call, send SMS, and schedule callbacks for sales teams.
Build, deploy, and sell AI agents for local-service businesses - from your IDE.
Build and host full-stack apps from a prompt, with agents that reach you on WhatsApp and email.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/automanus-io/mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
