SAP Integration Content MCP
Enables managing SAP Cloud Integration iFlows, packages, configurations, deployments, and runtime artifacts via natural language through the OData API.
README
mcp-ci-pyton — SAP Integration Content MCP
Servidor MCP em Python para a SAP Cloud Integration Content OData API.
Expõe ferramentas para gerenciar Integration Flows (iFlows), pacotes, configurações, recursos, deploy e endpoints de runtime.
Estrutura do Projeto
mcp-ci-pyton/
├── pyproject.toml
├── .env.example
├── README.md
└── src/sap_integration_mcp/
├── server.py # Entry point MCP
├── config.py # Configuração via variáveis de ambiente
├── auth/
│ └── oauth.py # OAuth 2.0 Client Credentials
├── client/
│ └── integration_content.py # Cliente OData HTTP
└── tools/
├── packages.py # IntegrationPackages
├── iflows.py # IntegrationDesigntimeArtifacts
├── deploy.py # DeployIntegrationDesigntimeArtifact
├── runtime.py # IntegrationRuntimeArtifacts
└── endpoints.py # ServiceEndpoints
Tools Disponíveis
Pacotes (Design)
| Tool | Operação OData |
|---|---|
list_integration_packages |
GET /IntegrationPackages |
get_integration_package |
GET /IntegrationPackages('{Id}') |
create_integration_package |
POST /IntegrationPackages |
delete_integration_package |
DELETE /IntegrationPackages('{Id}') |
copy_integration_package |
POST /CopyIntegrationPackage |
list_package_iflows |
GET /IntegrationPackages('{Id}')/IntegrationDesigntimeArtifacts |
Integration Flows (Design)
| Tool | Operação OData |
|---|---|
get_integration_flow |
GET /IntegrationDesigntimeArtifacts(Id,Version) |
create_integration_flow |
POST /IntegrationDesigntimeArtifacts |
update_integration_flow |
PUT /IntegrationDesigntimeArtifacts(Id,Version) |
delete_integration_flow |
DELETE /IntegrationDesigntimeArtifacts(Id,Version) |
download_integration_flow |
GET .../$value (ZIP base64) |
save_integration_flow_version |
POST /IntegrationDesigntimeArtifactSaveAsVersion |
get_iflow_configurations |
GET .../Configurations |
update_iflow_configuration |
PUT .../$links/Configurations('{key}') |
list_iflow_resources |
GET .../Resources |
get_iflow_resource |
GET .../Resources(...)/$value |
update_iflow_resource |
PUT .../$links/Resources(...) |
execute_iflow_design_guidelines |
POST /ExecuteIntegrationDesigntimeArtifactsGuidelines |
get_iflow_guideline_results |
GET .../DesignGuidelineExecutionResults |
Deploy & Runtime (Monitor)
| Tool | Operação OData |
|---|---|
deploy_integration_flow |
POST /DeployIntegrationDesigntimeArtifact |
get_deploy_status |
GET /BuildAndDeployStatus(TaskId) |
list_runtime_artifacts |
GET /IntegrationRuntimeArtifacts |
get_runtime_artifact |
GET /IntegrationRuntimeArtifacts('{Id}') |
undeploy_integration_artifact |
DELETE /IntegrationRuntimeArtifacts('{Id}') |
Endpoints
| Tool | Operação OData |
|---|---|
list_service_endpoints |
GET /ServiceEndpoints |
Instalação
cd C:\Workspace\mcps\mcp-ci-pyton
python -m venv .venv
# Windows
.venv\Scripts\activate
# Linux/macOS
source .venv/bin/activate
pip install -e .
cp .env.example .env
# Edite .env com suas credenciais
Configuração
Tenant SAP Cloud Integration (produção)
SAP_CPI_BASE_URL=https://<tenant>-tmn.hci.<region>.hana.ondemand.com
SAP_CPI_TOKEN_URL=https://<subaccount>.authentication.<region>.hana.ondemand.com/oauth/token
SAP_CPI_CLIENT_ID=<client-id>
SAP_CPI_CLIENT_SECRET=<client-secret>
Crie um OAuth Client no BTP Subaccount com grant type client_credentials e atribua a role AuthGroup.IntegrationDeveloper (ou equivalente).
SAP API Business Hub (sandbox)
SAP_CPI_BASE_URL=https://sandbox.api.sap.com/cpi
SAP_CPI_API_KEY=<sua-api-key>
Registre-se em api.sap.com para obter a API Key.
Uso no Cursor
Adicione ao .cursor/mcp.json (ou configuração global do Cursor):
{
"mcpServers": {
"sap-integration-content": {
"command": "python",
"args": ["-m", "sap_integration_mcp.server"],
"cwd": "C:/Workspace/mcps/mcp-ci-pyton",
"env": {
"SAP_CPI_BASE_URL": "https://your-tenant-tmn.hci.eu10.hana.ondemand.com",
"SAP_CPI_TOKEN_URL": "https://your-subaccount.authentication.eu10.hana.ondemand.com/oauth/token",
"SAP_CPI_CLIENT_ID": "your-client-id",
"SAP_CPI_CLIENT_SECRET": "your-client-secret"
}
}
}
}
Ou usando o entry point instalado:
{
"mcpServers": {
"sap-integration-content": {
"command": "mcp-ci-pyton",
"envFile": "C:/Workspace/mcps/mcp-ci-pyton/.env"
}
}
}
Exemplos de Uso pelo Agente
"Liste todos os pacotes de integração"
→ list_integration_packages
"Mostre os iFlows do pacote EmployeeCentral"
→ list_package_iflows(package_id="EmployeeCentral")
"Obtenha as configurações externalizadas do iFlow X"
→ get_iflow_configurations(iflow_id="MyFlow", version="active")
"Atualize o parâmetro endpoint_url para https://api.example.com"
→ update_iflow_configuration(iflow_id="MyFlow", version="1.0.0", parameter_key="endpoint_url", parameter_value="https://api.example.com")
"Faça deploy do iFlow MyFlow versão active"
→ deploy_integration_flow(iflow_id="MyFlow", version="active")
"Liste todos os artefatos deployados com status STARTED"
→ list_runtime_artifacts(odata_query="$filter=Status eq 'STARTED'")
"Quais endpoints REST estão expostos?"
→ list_service_endpoints(odata_query="$expand=EntryPoints&$filter=Protocol eq 'REST'")
Referências
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.