ssis-adf-agent
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AZURE_CLIENT_ID | No | Azure Service Principal application (client) ID for deployment authentication. | |
| AZURE_TENANT_ID | No | Azure Active Directory tenant ID for deployment authentication. | |
| AZURE_CLIENT_SECRET | No | Azure Service Principal secret for deployment authentication. | |
| AZURE_OPENAI_API_KEY | No | Azure OpenAI API key. Required for LLM-powered Script Task translation. | |
| AZURE_OPENAI_ENDPOINT | No | Your Azure OpenAI resource URL (e.g., https://my-resource.openai.azure.com/). Required for LLM-powered Script Task translation. | |
| AZURE_OPENAI_DEPLOYMENT | No | Azure OpenAI model deployment name. | gpt-4o |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| scan_ssis_packagesA | Discover all SSIS packages (.dtsx files) from a given source. Returns a JSON list of found packages with name, path, and basic metadata. source_type must be one of: 'local', 'git', 'sql'. |
| analyze_ssis_packageA | Analyze a single SSIS package (.dtsx file) and return a detailed report including: complexity score (0-100), effort estimate (Low/Medium/High/Very High), component inventory, gap analysis (items needing manual work), cross-database/linked server references, CDM pattern detection, ESI reuse candidates, and dependency execution order. |
| convert_ssis_packageA | Convert a single SSIS package (.dtsx file) to Azure Data Factory JSON artifacts. Generates: pipeline JSON, linked service JSONs, dataset JSONs, mapping data flow JSONs, trigger JSONs, and Azure Function stubs for Script Tasks. Supports Self-Hosted IR, Key Vault secrets, Microsoft Recommended linked service format, schema remapping, ESI reuse detection, CDM pattern flagging, and cross-package dedup. Returns a summary of generated files and any warnings. |
| validate_adf_artifactsA | Validate ADF JSON artifacts in a directory for structural correctness. Checks that required fields (name, properties, activities) are present. Returns a list of validation issues found, or a success message if all artifacts are valid. |
| deploy_to_adfA | Deploy ADF JSON artifacts from a local directory to an Azure Data Factory instance. Deploys in correct dependency order: linked services → datasets → data flows → pipelines → triggers. Triggers are deployed in Stopped state and must be activated manually. Uses DefaultAzureCredential (az login, managed identity, or service principal env vars). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Each tool has a distinct and non-overlapping purpose: analyze_ssis_package examines SSIS packages for metrics and insights, convert_ssis_package transforms them to ADF JSON, deploy_to_adf deploys those artifacts, scan_ssis_packages discovers packages, and validate_adf_artifacts checks JSON validity. The descriptions clearly differentiate their functions, eliminating any ambiguity in tool selection.
All tool names follow a consistent snake_case pattern with clear verb_noun structure: analyze_ssis_package, convert_ssis_package, deploy_to_adf, scan_ssis_packages, and validate_adf_artifacts. The naming is predictable and aligns well with the actions each tool performs, making the set easy to navigate and understand.
With 5 tools, this server is well-scoped for its purpose of migrating and managing SSIS packages to Azure Data Factory. Each tool serves a critical step in the workflow—discovery, analysis, conversion, validation, and deployment—without being overly sparse or bloated, making the count ideal for the domain.
The tool set provides complete coverage for the SSIS to ADF migration lifecycle: it starts with scanning and analyzing packages, converts them to ADF artifacts, validates the output, and deploys to Azure. There are no obvious gaps, as it supports the entire process from source discovery to deployment, ensuring agents can handle the migration end-to-end.