Gravitee APIM MCP Server
Enables natural language interaction with Gravitee API Management platform, allowing management of APIs, environments, and configurations through AI assistants like Claude and Cursor.
README
Gravitee API Management (APIM) MCP Server
This repository contains a Model Context Protocol (MCP) server for the Gravitee.io API Management (APIM) platform. It allows you to interact with your Gravitee instance using natural language in AI assistants like Claude, Cursor, and other MCP-compatible clients.
The server is generated from the official Gravitee Management API v2 OpenAPI specification and exposes its functionality as a set of tools for an LLM to use.
<div align="left"> <a href="https://www.speakeasy.com/?utm_source=gravitee-apim&utm_campaign=mcp-typescript"><img src="https://www.speakeasy.com/assets/badges/built-by-speakeasy.svg" /></a> <a href="https://opensource.org/licenses/MIT"> <img src="https://img.shields.io/badge/License-MIT-blue.svg" style="width: 100px; height: 28px;" /> </a> </div>
Table of Contents
Prerequisites
- Node.js v18+
- npm (included with Node.js)
- Access to a Gravitee APIM instance (Self-hosted or Cloud)
Getting Started
Follow these steps to get the MCP server running and configured with your AI client.
1. Create a Service User and Generate a Token
The MCP server authenticates with the Gravitee Management API using a Bearer Token. For security, it is highly recommended to create a dedicated Service User for this purpose.
- Log into your Gravitee APIM Management Console.
- Self-Hosted: e.g.,
http://localhost:8084 - Cloud: e.g.,
https://<your-org>.<region>.console.gravitee.io
- Self-Hosted: e.g.,
- From the main navigation, select Organization Settings, then click on Users.
- Click the Add User button.
- In the form, select Service User as the user type, provide a meaningful name (e.g.,
mcp-server-user), and click Create. - You will be returned to the user list. Find and click on the service user you just created to open its configuration page.
- Assign Permissions. The capabilities of the AI assistant are directly determined by the permissions granted to this service user. You should assign roles based on the principle of least privilege for your intended operations.
- Organization Role: Sets permissions that apply across the entire organization.
- Environment Roles: Sets specific permissions for each environment (e.g., Development, Production).
Important: The Management API is powerful. To understand which permission is required for a specific action, please refer to the official Gravitee Management API documentation.
- Click Save to apply the roles.
- On the user's configuration page, navigate to the Tokens section and click Generate a personal token.
- Enter a descriptive name for the token (e.g.,
mcp-server-token) and click Generate. - Copy the generated token immediately and store it in a safe place. You will not be able to view it again. This token is the value you will use for the
--bearer-authargument.
2. Clone and Build the Server
# Clone the repository
git clone https://github.com/gravitee-io/gravitee-apim-mcp-server.git
cd gravitee-apim-mcp-server
# Install dependencies
npm install
# Build the project
npm run build
# The server executable is now available at ./bin/mcp-server.js
Installation
The server can be installed in any MCP-compatible client. The required arguments are --bearer-auth (the token you generated) and --server-url.
Server URL Guide
- Self-Hosted: Use the base URL of your Management API. Example:
http://localhost:8083/management/v2 - Gravitee Cloud: Use your organization-specific API URL. Example:
https://<your-org>.<region>.api.gravitee.io/management/v2
Installations in MCP Clients
<details> <summary>DXT (Desktop Extension for Claude)</summary>
Install the MCP server as a Desktop Extension using the pre-built mcp-server.dxt file.
Simply drag and drop the mcp-server.dxt file onto Claude Desktop to install the extension. The DXT package includes the MCP server and will prompt you for the required configuration values upon installation.
[!NOTE] DXT (Desktop Extensions) provide a streamlined way to package and distribute MCP servers. Learn more about Desktop Extensions.
</details>
<details> <summary>Claude Desktop (Manual Config)</summary>
- Open Claude Desktop Settings -> Developer -> Edit Config.
- Add the following JSON, replacing the placeholder values.
{
"mcpServers": {
"GraviteeApim": {
"command": "node",
"args": [
"/absolute/path/to/gravitee-apim-mcp-server/bin/mcp-server.js",
"start",
"--bearer-auth",
"YOUR_BEARER_TOKEN",
"--server-url",
"https://your-management-api-url/management/v2"
]
}
}
}
</details>
<details> <summary>Cursor</summary>
Or manually:
- Open Cursor Settings -> Tools and Integrations -> New MCP Server.
- Paste the following JSON, replacing the placeholder values.
{
"mcpServers": {
"GraviteeApim": {
"command": "node",
"args": [
"/absolute/path/to/gravitee-apim-mcp-server/bin/mcp-server.js",
"start",
"--bearer-auth",
"YOUR_BEARER_TOKEN",
"--server-url",
"https://your-management-api-url/management/v2"
]
}
}
}
</details>
<details> <summary>VS Code</summary>
Refer to the Official VS Code documentation for the latest information.
- Open the Command Palette and search for
MCP: Open User Configuration. - This will open the
mcp.jsonfile. Paste the following configuration:
{
"mcpServers": {
"GraviteeApim": {
"command": "node",
"args": [
"/absolute/path/to/gravitee-apim-mcp-server/bin/mcp-server.js",
"start",
"--bearer-auth",
"YOUR_BEARER_TOKEN",
"--server-url",
"https://your-management-api-url/management/v2"
]
}
}
}
</details>
Usage Examples
Once configured, you can interact with your Gravitee instance using natural language. For Cloud instances, remember to specify the target environment ID or HRID.
List all of my APIs in the 'dev' environment.Get the health status for the API with ID '123-abc-456'.Create a new API named "Weather API" that points to http://example.com/weather.For the "Weather API", create a keyless plan, publish it, and start the API.
Contributions
While we value contributions to this MCP Server, the code is generated programmatically. Any manual changes added to the src directory will be overwritten on the next generation.
We look forward to hearing your feedback. Feel free to open a PR with changes to the generation process or open an issue with a proof of concept, and we'll do our best to include it in a future release.
MCP Server Created by Speakeasy
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。