Infor Birst MCP Server
Enables AI-driven interaction with Infor Birst analytics platform, providing 20+ tools for querying data warehouses, managing spaces and reports, executing workflows, and converting natural language to BQL queries.
README
Infor Birst MCP Server
An MCP (Model Context Protocol) server that exposes Infor Birst's analytics platform capabilities as AI-consumable tools.
Features
20 MCP Tools enabled by default, organized in 5 tiers (up to 25 with optional features):
Tier 1: Core Query Tools (0-5 tools, optional)
These tools require additional Birst entitlements and are disabled by default:
GenAI Tools (require Birst AI entitlement - set BIRST_ENABLE_GENAI=true):
birst_generate_bql- Convert natural language to BQL queriesbirst_search_data- Search data warehouse with natural languagebirst_generate_chart- Generate chart specifications from text
ICW Tools (require application provisioning - set BIRST_ENABLE_ICW=true):
birst_execute_query- Execute BQL queries and return resultsbirst_validate_query- Validate BQL syntax before execution
Tier 2: Discovery Tools (6 tools)
birst_list_spaces- List all accessible analytical spacesbirst_get_space- Get detailed space informationbirst_list_reports- List reports in a space (with pagination)birst_list_dashboards- List dashboards in collectionsbirst_list_collections- List collections in a spacebirst_search_catalog- Search catalog entities
Tier 3: Infrastructure Tools (5 tools)
birst_list_connections- List data connectionsbirst_list_sources- List data sourcesbirst_list_variables- List space variablesbirst_list_hierarchies- List dimensional hierarchiesbirst_get_dataflow- Get data flow visualization
Tier 4: Workflow Tools (4 tools)
birst_list_workflows- List available workflowsbirst_run_workflow- Trigger workflow executionbirst_get_workflow_status- Monitor workflow statusbirst_list_workflow_runs- Get workflow execution history
Tier 5: Administration Tools (4 tools)
birst_list_users- List users in accountbirst_list_space_users- List users with space accessbirst_list_account_groups- List account groupsbirst_list_space_groups- List space groups
Installation
npm install
Configuration
Environment Variables
| Variable | Description | Default |
|---|---|---|
BIRST_ENV |
Environment to use (TST, PRD, TRN) | TST |
BIRST_IONAPI_PATH |
Custom path to .ionapi file | Auto-detected |
BIRST_LOG_LEVEL |
Log level (debug, info, warn, error) | info |
BIRST_ENABLE_GENAI |
Enable GenAI tools (requires Birst AI entitlement) | false |
BIRST_ENABLE_ICW |
Enable ICW query tools (requires app provisioning) | false |
ION API Credentials
Place your .ionapi files in the project root or credentials/ directory:
infor-birst-mcp/
├── TST.ionapi # Test environment
├── PRD.ionapi # Production environment
└── TRN.ionapi # Training environment
The .ionapi file is obtained from Infor Cloud Suite and contains OAuth2 credentials.
Usage
Development
npm run dev
Production
npm run build
npm start
Claude Code Configuration
Add to your Claude Code MCP settings:
{
"mcpServers": {
"infor-birst": {
"command": "node",
"args": ["/path/to/infor-birst-mcp/dist/index.js"],
"env": {
"BIRST_ENV": "TST"
}
}
}
}
Or for development:
{
"mcpServers": {
"infor-birst": {
"command": "npx",
"args": ["tsx", "/path/to/infor-birst-mcp/src/index.ts"],
"env": {
"BIRST_ENV": "TST"
}
}
}
}
Example Usage
Once configured, you can use the tools in Claude:
"List all my Birst spaces"
→ Uses birst_list_spaces
"Show me reports in this space"
→ Uses birst_list_reports
"What workflows are scheduled to run?"
→ Uses birst_list_workflows with filter=isScheduled
"Who has access to this space?"
→ Uses birst_list_space_users
With GenAI enabled (BIRST_ENABLE_GENAI=true):
"Show me sales by region for 2024"
→ Uses birst_generate_bql + birst_execute_query
Supported Environments
- TST - Test environment
- PRD - Production environment
- TRN - Training environment
Switch environments by setting the BIRST_ENV variable or using the default (TST).
API Coverage
This MCP server interfaces with 3 Birst APIs:
| API | Endpoints | Description |
|---|---|---|
| REST API | 156 | Space management, users, workflows |
| GenAI API | 3 | Natural language to BQL, chart generation |
| ICW API | 5 | Query execution and validation |
Security
- Credentials are stored in
.ionapifiles (gitignored) - OAuth2 tokens are automatically refreshed
- All API calls are authenticated via Bearer token
- Sensitive data is never logged
License
MIT
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。