WHAT IT CONNECTS
intersective practera mcp server 为 AI Agent 提供什么
- Server-Sent Events (SSE) transport for MCP
- AWS Lambda deployment support
- GraphQL integration with Practera API
- Region-specific endpoints
- API key authentication
- OAuth 2.1 support for secure access
- Node.js 18+
- npm
- AWS account (for deployment)
- Practera API key
- OAuth client credentials (for OAuth authentication)
- Clone this repository
- Install dependencies:
- Start the server in development mode:
- The server will be available at `http://localhost:3000/sse`
- OAuth endpoints will be accessible at `http://localhost:3000/oauth/*`
- Make sure you have [AWS CLI](https://aws.amazon.com/cli/) installed and configured.
- Set up your OAuth configuration parameters:
- Deploy using the Serverless Framework:
- `apikey` parameter in each tool call
- `region` parameter to specify the Practera region
- Redirect users to `/oauth/authorize` for authorization
- Exchange authorization code for access token at `/oauth/token`
- Access the MCP server endpoints using the bearer token
- Revoke tokens if needed at `/oauth/revoke`
- `mcp_practera_get_project` - Get details about a Practera project
- `mcp_practera_get_assessment` - Get details about a Practera assessment
- API key for Practera authentication (if using API key auth)
- Region for the Practera API (usa, aus, euk or p2-stage)
- OAuth configuration (if using OAuth authentication)
SECURITY
MCP 收录不等于安全审核
MCP 服务器可能获得模型上下文、凭据、本地文件或调用外部系统的权限。连接 Agent 前,请检查代码、环境变量、网络行为、软件包来源与维护状态。