The Chargebee MCP Server connects LLMs to Chargebee's resources, enabling you to:
Search Chargebee's knowledge base: Access documentation, FAQs, release notes, and usage guides
Get immediate answers about Chargebee products and API services
Generate context-aware code snippets tailored for specific integration needs
Create integration guides with structured code outlines and sample workflows for Chargebee APIs
Work with AI-powered tools including Cursor, Windsurf, Cline, and Claude Desktop
Enables running the Chargebee MCP server through npm's npx command, providing access to Chargebee's documentation and code generation capabilities.
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., "@@chargebee/mcp show me how to create a subscription with a trial period"
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.
⚠️ Deprecation Notice
This package is deprecated and will no longer receive updates or support. Please migrate to our new KnowledgeBase MCP Server, which provides enhanced capabilities and improved accuracy. Learn more and upgrade here: Chargebee MCP Server Documentation
Model Context Protocol (MCP) is a standardized protocol designed to manage context between large language models (LLMs) and external systems.
The Chargebee MCP Server offers a robust set of tools to improve developer efficiency. It integrates with AI-powered code editors like Cursor, Windsurf, and Cline, as well as general-purpose tools such as Claude Desktop. It is compatible with any MCP Client.
With this MCP Server, you can:
Get immediate answers about the Chargebee products and API services.
Receive context-aware code snippets tailored to your integration needs.
Access Chargebee's knowledge base, including:
Documentation
FAQs
Release notes
And much more
Node.js LTS - The Chargebee MCP server requires the Node.js LTS version to function correctly.
Related MCP server: Codinfy MCP
To run the Chargebee MCP server using Node.js npx, execute the following command:
npx -y @chargebee/mcp@latestTool | Description |
| Search Chargebee's documentation to retrieve detailed information and usage guides. |
| Generate structured code outlines and sample code for integrating Chargebee's APIs and features. |
To add this server to Cursor IDE:
Navigate to Cursor Settings > MCP.
Click + Add new Global MCP Server.
Add the following configuration to your global .cursor/mcp.json file:
{
"mcpServers": {
"chargebee": {
"command": "npx",
"args": [
"-y",
"@chargebee/mcp"
]
}
}
}Refer to the Cursor documentation for additional details. Note: You can also add this to your project-specific Cursor configuration (supported in Cursor 0.46+).
To set up MCP with Cascade:
Open Windsurf and navigate to Settings > Advanced Settings or use the Command Palette > Open Windsurf Settings Page.
Scroll to the Cascade section to add a new server, view existing servers, or access the raw JSON config file at mcp_config.json.
Click “Add custom server +” to include the Chargebee MCP server directly in mcp_config.json:
{
"mcpServers": {
"chargebee": {
"command": "npx",
"args": [
"-y",
"@chargebee/mcp"
]
}
}
}Refer to the Windsurf documentation for more information.
Install the Chargebee MCP server in VS Code using one of these buttons:
Alternatively, you can install the Chargebee MCP server using the VS Code CLI:
# For VS Code
code --add-mcp '{"name":"chargebee","command":"npx","args":["-y","@chargebee/mcp"]}'# For VS Code Insiders
code-insiders --add-mcp '{"name":"chargebee","command":"npx","args":["-y","@chargebee/mcp"]}'After installation, the Chargebee MCP server will be available for use with your GitHub Copilot agent in VS Code.
Add the following configuration to your claude_desktop_config.json file. Refer to the Claude Desktop documentation for more details:
{
"mcpServers": {
"chargebee": {
"command": "npx",
"args": [
"-y",
"@chargebee/mcp"
]
}
}
}Manually add the following JSON to your cline_mcp_settings.json file via the Cline MCP Server settings:
{
"mcpServers": {
"chargebee": {
"command": "npx",
"args": [
"-y",
"@chargebee/mcp"
]
}
}
}Access the MCP settings by selecting Edit MCP Settings in Roo Code settings or using the Roo Code: Open MCP Config command in the VS Code command palette:
{
"mcpServers": {
"chargebee": {
"command": "npx",
"args": [
"-y",
"@chargebee/mcp"
]
}
}
}To contribute to this project, refer to the contribution guide.
Use this tool for any Chargebee integration questions or implementation needs.
Always use this tool to get the accurate integration code guide for Chargebee. This is the main tool developers need when asking about implementing Chargebee functionality (like "how to update billing address", "how to create subscription", "how to handle webhooks", etc.).
This tool will take in parameters about integrating with Chargebee in their application and generates an integration workflow along with the code snippets.
It takes the following arguments:
goal (string): What is the user's goal?
language (enum): Programming language the code to be generated in. Check the user's application language.
| Name | Required | Description | Default |
|---|---|---|---|
| goal | Yes | What is the user's goal? | |
| language | No | Programming language the code to be generated in. Check the user's application language. |
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 only describes the tool as generating code but does not clarify that it is a read-only operation with no side effects or data mutations. Such information is essential for safe invocation.
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 contains redundant phrasing (e.g., 'Use this tool' and 'Always use this tool') and could be more streamlined. However, it is not excessively long and includes necessary details.
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?
The description covers the tool's inputs and high-level output (workflow and code snippets) but lacks details on the output structure, error handling, or limitations. With no output schema, more specifics would improve completeness.
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%, and the descriptions in the schema are adequate. The tool description reiterates the parameter meanings without adding new context or examples, meeting the baseline for high coverage.
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: generating integration workflows and code snippets for Chargebee. It explicitly differentiates from the sibling tool 'chargebee_documentation_search' by positioning itself as the main tool for implementation questions.
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 advises to use this tool for Chargebee integration needs and to check the user's language. It implies a context for use but does not explicitly exclude scenarios or mention alternatives beyond the sibling.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Only use this tool for general product documentation queries, NOT for implementation questions.
Do not use this tool for code generation or implementation questions. For any developer questions about implementing Chargebee functionality (like "how to update billing address", "how to create subscription", etc.), use "chargebee_code_planner" tool instead.
This tool should only be used for:
General product documentation queries about Chargebee's features and concepts
Understanding billing, payments, receivables, revenue recognition concepts
Learning about subscription management processes
Finding product feature explanations and overviews
Non-implementation related documentation queries
It takes the following arguments:
query (string): The user query to search an answer for in the Chargebee documentation.
language (enum): The programming language for the documentation. Check the user's application language.
userRequest (string): User's original request to you.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | The user query to search an answer for in the Chargebee documentation. | |
| userRequest | No | User's original request to you. | |
| language | No | The programming language for the documentation. Check the user's application language. |
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 clearly indicates this is a search tool for documentation, implying a read-only, non-destructive operation. It does not mention side effects, rate limits, or return format, but the core behavior is transparent enough for an agent.
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 well-structured, starting with critical usage boundaries, then listing use cases, then parameters. It is front-loaded with the most important information. It could be slightly more concise, but every sentence serves a clear purpose.
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 annotations and no output schema, the description does not specify what the tool returns (e.g., format, if results are snippets or full documents) or error handling. However, it covers usage boundaries and parameter semantics adequately for a search tool with a sibling distinction.
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%, so baseline is 3. The description adds value by providing usage context for each parameter (e.g., 'Check the user's application language' for language, and 'User's original request to you' for userRequest), which helps the agent set values correctly.
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 is for 'general product documentation queries' and explicitly distinguishes it from the sibling tool, naming the sibling and specifying when to use that alternative. It lists specific use cases, making the purpose highly distinct and actionable.
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 explicit when-to-use and when-not-to-use guidance, including naming the alternative tool 'chargebee_code_planner' for implementation questions. It also enumerates specific allowed query types, leaving no ambiguity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
The two tools have explicitly distinct purposes: one for implementation guidance and code generation, the other for general documentation queries. Descriptions clearly separate their use cases, eliminating ambiguity.
Both tools follow a consistent 'chargebee_<descriptive_noun>' pattern, making it easy to infer their roles. The naming is uniform and predictable.
With only two tools, the server is very focused, but that matches its specific purpose of handling integration assistance and documentation search. While minimal, the count is reasonable for the intended scope.
The tool set covers both implementation needs (code planner) and conceptual understanding (documentation search), leaving no obvious gaps for its stated goal of answering Chargebee integration questions.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
MCP server connecting AI agents to 100+ apps (Gmail, Slack, Notion, GitHub) via one-click OAuth.
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
MCP server for building and testing AI agents with multi-model experimentation and insights.
MCP server that lets AI assistants use all OneSchema features exposed via the public API.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/chargebee/agentkit'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
