SAS MCP Server
Related Servers
Alternatives to SAS MCP Server
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityFmaintenanceThis MCP server enables natural language scoring with SAS Viya, allowing users to execute prebuilt SAS code, models, and job definitions seamlessly.46 npm1Apache 2.0
- FlicenseCqualityDmaintenanceMCP server that enables deployment and management of MCP servers through a simple configuration-based interface.1-
- FlicenseNot gradedqualityBmaintenanceAn MCP server with HTTP/stdio support, a web admin panel for managing services, capabilities, and user permissions with Bearer token authentication, enabling relay and access control for MCP tools.-
- AlicenseNot gradedqualityDmaintenanceAn MCP server providing tools for read-only SQL queries, REST API calls, sandboxed Python execution, and resource lifecycle management, enabling multi-step research and data tasks.MIT
- AlicenseAqualityBmaintenanceAn MCP server for SSH/SCP operations with passwordless authentication, enabling remote command execution, file transfer, and session management.1914 npmMIT
- AlicenseAqualityDmaintenanceMCP server for SAP Analytics Cloud, enabling AI assistants to interact with SAC stories, models, data, users, and audit logs via the SAC REST API.34ISC
TDQS
Scored across 28 tools
Most tools are clearly separated by resource and action, but list_models_and_decisions and list_registered_models both list models from different repositories, and execute_sas_code vs submit_batch_job are similar (sync vs async), creating minor ambiguity.
All tool names follow a consistent lowercase verb_noun snake_case pattern (e.g., list_ml_projects, score_data, cancel_job), with no mixed conventions or vague verbs.
28 tools is on the heavy side, and the set covers many domains (AutoML, data, files, jobs, CAS, charts), but the count is justified by the platform's breadth; still, several tools could be merged (e.g., the two model listing tools).
The tool set covers core workflows for AutoML, data exploration, and job execution, but lacks update operations for ML projects and delete operations for tables/files, leaving some lifecycle gaps.