SAP Integration Content MCP
Allows management of SAP Cloud Integration content, including listing and creating integration packages and flows, configuring externalized parameters, managing resources, deploying and undeploying artifacts, and querying runtime artifacts and service endpoints via the Integration Content OData API.
Click on "Deploy 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., "@SAP Integration Content MCP List my integration packages"
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.
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 # ServiceEndpointsRelated MCP server: MCP Integration Suite Server
Tools Disponíveis
Pacotes (Design)
Tool | Operação OData |
| GET /IntegrationPackages |
| GET /IntegrationPackages('{Id}') |
| POST /IntegrationPackages |
| DELETE /IntegrationPackages('{Id}') |
| POST /CopyIntegrationPackage |
| GET /IntegrationPackages('{Id}')/IntegrationDesigntimeArtifacts |
Integration Flows (Design)
Tool | Operação OData |
| GET /IntegrationDesigntimeArtifacts(Id,Version) |
| POST /IntegrationDesigntimeArtifacts |
| PUT /IntegrationDesigntimeArtifacts(Id,Version) |
| DELETE /IntegrationDesigntimeArtifacts(Id,Version) |
| GET .../$value (ZIP base64) |
| POST /IntegrationDesigntimeArtifactSaveAsVersion |
| GET .../Configurations |
| PUT .../$links/Configurations('{key}') |
| GET .../Resources |
| GET .../Resources(...)/$value |
| PUT .../$links/Resources(...) |
| POST /ExecuteIntegrationDesigntimeArtifactsGuidelines |
| GET .../DesignGuidelineExecutionResults |
Deploy & Runtime (Monitor)
Tool | Operação OData |
| POST /DeployIntegrationDesigntimeArtifact |
| GET /BuildAndDeployStatus(TaskId) |
| GET /IntegrationRuntimeArtifacts |
| GET /IntegrationRuntimeArtifacts('{Id}') |
| DELETE /IntegrationRuntimeArtifacts('{Id}') |
Endpoints
Tool | Operação OData |
| 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 credenciaisConfiguração
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
Available Tools
25 toolscopy_integration_packageB
Copy an integration package from Discover to Design workspace.
Inputs: package_id (required), suffix. Returns: result
create_integration_flowB
Create/upload a new integration flow in a package.
Args: iflow_id: Unique ID for the iFlow. name: Display name. package_id: Target integration package ID. artifact_content_base64: Optional ZIP content encoded in base64.
Inputs: name (required), iflow_id (required), package_id (required), artifact_content_base64. Returns: result
create_integration_packageC
Create a new integration package in the Design workspace.
Inputs: name (required), package_id (required), short_text, description. Returns: result
delete_integration_flowC
Delete an integration flow from the Design workspace.
Inputs: version (required), iflow_id (required). Returns: result
delete_integration_packageC
Delete an integration package from the Design workspace.
Inputs: package_id (required). Returns: result
deploy_integration_flowA
Deploy an integration flow to the runtime (Monitor workspace).
Returns a task ID that can be polled with get_deploy_status.
Inputs: iflow_id (required), version. Returns: result
download_integration_flowB
Download an integration flow as a ZIP file (returns base64-encoded content).
Inputs: iflow_id (required), version. Returns: result
execute_iflow_design_guidelinesC
Execute design guidelines validation on an integration flow.
Inputs: iflow_id (required), version. Returns: result
get_deploy_statusB
Check the build and deploy status for a deployment task.
Inputs: task_id (required). Returns: result
get_iflow_configurationsC
Get externalized configuration parameters of an integration flow.
Inputs: iflow_id (required), version, odata_query. Returns: result
get_iflow_guideline_resultsC
Get design guideline execution results for an integration flow.
Inputs: iflow_id (required), version. Returns: result
get_iflow_resourceC
Download a specific resource from an integration flow.
Args: resource_type: One of edmx, groovy, jar, js, mmap, opmap, wsdl, xsd, xslt.
Inputs: version (required), iflow_id (required), resource_name (required), resource_type (required). Returns: result
get_integration_flowA
Get metadata of an integration flow by ID and version.
Use version='active' for the currently active version.
Inputs: iflow_id (required), version. Returns: result
get_integration_packageC
Get details of a specific integration package by ID.
Inputs: package_id (required). Returns: result
get_runtime_artifactC
Get details of a specific deployed runtime artifact.
Inputs: artifact_id (required). Returns: result
list_iflow_resourcesC
List all resources (Groovy scripts, XSLT, XSD, etc.) of an integration flow.
Inputs: iflow_id (required), version, odata_query. Returns: result
list_integration_packagesA
List all integration packages in the Design workspace.
Args: odata_query: Optional OData query string (e.g. "$select=Id,Name&$top=10").
Inputs: odata_query. Returns: result
list_package_iflowsA
List all integration flows (iFlows) within a specific package.
Args: package_id: The integration package ID. odata_query: Optional OData query (e.g. "$filter=Version eq 'active'").
Inputs: package_id (required), odata_query. Returns: result
list_runtime_artifactsA
List all deployed integration artifacts in the runtime (Monitor workspace).
Args: odata_query: Optional OData query (e.g. "$filter=Status eq 'STARTED'").
Inputs: odata_query. Returns: result
list_service_endpointsA
List all service endpoints exposed by deployed integration flows.
Args: odata_query: Optional OData query (e.g. "$expand=EntryPoints&$filter=Protocol eq 'REST'").
Inputs: odata_query. Returns: result
save_integration_flow_versionC
Save an integration flow as a new version.
Inputs: iflow_id (required), new_version (required), current_version (required), artifact_content_base64. Returns: result
undeploy_integration_artifactC
Undeploy a runtime integration artifact.
Inputs: artifact_id (required). Returns: result
update_iflow_configurationC
Update a single externalized configuration parameter of an iFlow.
Inputs: version (required), iflow_id (required), parameter_key (required), parameter_value (required), +1 more. Returns: result
update_iflow_resourceC
Update a resource (e.g. Groovy script) within an integration flow.
Inputs: version (required), iflow_id (required), resource_name (required), resource_type (required), +1 more. Returns: result
update_integration_flowB
Update an existing integration flow (name and/or ZIP content).
Inputs: version (required), iflow_id (required), name, artifact_content_base64. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 25 tools
Each tool targets a distinct resource and action (e.g., package vs. flow vs. runtime artifact, create vs. update vs. delete). No two tools have overlapping purposes; descriptions clearly differentiate similar operations.
Tools predominantly follow verb_noun pattern with underscores. However, there is minor inconsistency: some use 'iflow' (e.g., execute_iflow_design_guidelines) while others use 'integration_flow' (e.g., create_integration_flow). This is a small deviation from perfect uniformity.
With 25 tools, the server is on the higher end of the typical range (3-15) but still within acceptable bounds for a comprehensive integration platform. The count feels slightly heavy but not excessive.
The tool surface covers the full lifecycle: CRUD for packages and flows, deployment/undeployment, configuration, resource management, and design guidelines. Minor gaps exist (e.g., no tool for monitoring logs or error details), but core workflows are well-supported.
Related MCP Connectors
Deploy, monitor, and manage your OpenClaw AI assistants via natural language.
Query, explore, and manage your databases through natural conversation.
Manage tickets, run agents and workflows, query tables, and search workspace knowledge.
Build and run agents and automations across hundreds of apps using natural language.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceTransforms SAP S/4HANA or ECC systems into conversational AI interfaces by exposing OData services as dynamic MCP tools. Enables natural language interactions with ERP data for querying, creating, updating, and deleting business entities.69 npm1MIT
- FlicenseNot gradedqualityDmaintenanceEnables interaction with SAP Integration Suite for designing, creating, and managing integration artifacts including integration flows, message mappings, packages, and B2B trading partner relationships through AI-powered natural language commands.32-
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to manage SAP Cloud Integration (CPI) landscapes through natural language by exposing CPI OData APIs as MCP tools.13MIT
- AlicenseAqualityDmaintenanceConnects Claude to SAP Cloud Platform Integration (CPI) to diagnose failed messages, review iFlows, deploy artifacts, and check credentials directly from your conversation.136MIT