Sas MCP Server

Unclaimed

by sassoftware

A self-hosted Model Context Protocol (MCP) server that connects to your SAS Viya environment and provides tools across the analytics lifecycle.

sas-aimlsas-osp

Install

$docker run -e VIYA_ENDPOINT=https://your-viya-server.com -p 8134:8134 ghcr.io/sassoftware/sas-mcp-server:latest

Unclaimed listing

Is this your MCP server?

This listing was auto-indexed from the public record. Claim it to edit the page, set compatibility and unlock growth tools. Takes under two minutes.

Claim this server

Tools (40)

apply_report_operations

The authoring workhorse — apply an ordered batch of native VA operations (addData, addPage, addObject, updateObject, setParameterValue, updateData, changeData, applyDataView) to a report. Give a page a title with addPage's title field (a text band at the top of the page body — VA headers are control

catalog_download_table_profile

Download a table's data dictionary and column profile as CSV, identified by either instanceid or resourceuri.

catalog_find_instance

Resolve the catalog instance for a source-asset resourceuri, bridging a search hit to the profiling and download tools without handling an instance id by hand.

catalog_get_adhoc_analysis

Poll a profiling job and cross-check the target instance, reporting profileready once results have landed on the asset — so a download isn't fired too early.

catalog_get_agent_history

Inspect an agent's run history — status and how much metadata each run enumerated/added/updated/removed.

catalog_list_agents

List the catalog's discovery agents (the crawlers that populate metadata).

catalog_run_adhoc_analysis

Submit an ad-hoc profiling job for a table. NLP enrichment (language, sentiment, semantic IDs) is on by default, populating informationPrivacy, nlpTerms, nlpTags, and mostImportantFields.

catalog_run_agent

Start a discovery agent run (asynchronous) to crawl its data source and refresh catalog metadata.

catalog_search

Search the catalog for assets (tables, columns, reports, …) using the SAS catalog search grammar (free text, facets like AssetType:Report, ranges). Each hit carries a resourceuri you can hand to the matching tool (e.g. getreport, getcastabledata).

catalog_search_helper

Discover how to query the catalog — list the available facets, or the valid values for one facet — so you can build precise catalogsearch queries.

copy_report

Copy a report to a new one (optionally renaming/refoldering). Pairs with a changeData operation for the copy-and-replace pattern.

create_report

Create a Visual Analytics report and return its id. Optionally pass an operations array to build the whole report in one atomic call; the result carries the created page/object names+labels and a verify hint.

delete_report

Delete a report and its content.

describe_report_objects

Discover what a report can contain — the eight report operations and every addable object (bar chart, list table, geo map, key value, …) with a one-line purpose, its data roles, common options, and an example payload. Call with no arguments for the catalog (including an intent→object map, placement

download_file

Download file content

execute_sas_code

Execute SAS code snippets and retrieve execution results (log and listing output). Runs in a reusable, per-user compute session that is kept warm across calls, so SAS state (WORK tables, macro variables, assigned librefs) persists between successive calls — use resetcomputesession to start fresh.

export_report

export a report (or specific report objects) in any format the VA service supports — package (zip), pdf, png, svg, csv, tsv, xlsx, or summary. Text formats come back inline, png as image content, and binary formats (package/pdf/xlsx) as an embedded file with the right MIME type.

get_castable_columns

Get column names, types, labels, formats

get_castable_data

Fetch sample rows from a CAS table

get_castable_info

Get table metadata (row count, columns, size)

get_job_status

Check job state

get_report

Get report metadata and definition

get_report_outline

Read a report's structure back — pages → objects with the handles the other tools need (object name for placement/updateObject targets, label for exportreport, page label for page placement).

list_cas_servers

List available CAS servers

list_caslibs

List CAS libraries on a server

list_castables

List tables in a CAS library

list_compute_columns

List the columns of a table in a SAS library

list_compute_contexts

List available compute contexts

list_compute_libraries

List the SAS libraries (librefs) assigned in a compute context

list_compute_tables

List the tables in a SAS library within a compute context

list_files

List files in the Viya Files Service

list_reports

List Visual Analytics reports

list_source_tables

List source tables not yet loaded into memory (candidates for promotion)

promote_table_to_memory

Load a source table into memory at global scope (idempotent)

query_data

Run a FedSQL SELECT against CAS or compute data and get the rows back — one SQL surface over both storage tiers. Pick the tier with target (cas for caslib.table, compute for libref.table); joins, subqueries, aggregation, and UNION all work, and the row cap is applied server-side by the tool (a LIMIT

reset_compute_session

Delete the cached compute session for a context, discarding its SAS state and forcing a fresh session on the next call

submit_batch_job

Submit a SAS job for async execution

upload_data

Upload a data file into a CAS table — read server-side so the data never passes through the model's context — from filepath (the server reads it off disk) or url (the server fetches it and converts it to the multipart upload the endpoint requires). Ingests the formats the casManagement uploadTable A

upload_file

Upload a file to the Viya Files Service, optionally into a Content folder (parentfolderuri). Content comes from exactly one of content (inline text), filepath (read server-side, binary-safe — xlsx, zip, images — gated by ALLOWLOCALFILEUPLOAD), or url (server-side fetch)

upload_inline_data

Create a small CAS table from inline csv/tsv text passed as a string (a lookup/mapping table the model builds on the fly, or a quick test table). The payload travels through the model's context, so it's for tiny tables only — use uploaddata for files or anything larger.