SAS Viya
listing.by
Run SAS code and work with Compute, CAS, models, reports and decisioning on a SAS Viya environment.
listing.install
listing.local.explain
listing.local.needs listing.local.note
VIYA_ENDPOINTBase URL of your SAS Viya environment, e.g. https://viya.example.com. No trailing slash.SSL_VERIFYlisting.env.optional Set false only for a self-signed Viya certificate. Disables verification for the whole process, so prefer a trusted certificate.CLIENT_IDlisting.env.optional SASLogon OAuth client id used for the token refresh exchange.COMPUTE_CONTEXT_NAMElisting.env.optional Compute context that backs SAS code execution.MCP_TIERSlisting.env.optional Expose only some tool tiers, e.g. 0-4 or 0,1,7. Empty exposes all 92 tools. Tiers: 0 Compute, 1 Data Discovery, 2 Data Operations, 3…MCP_READ_ONLYlisting.env.optional Expose only tools that neither change server-side state nor cause server-side work (51 of 92). Composes with MCP_TIERS.
listing.share.h
listing.share.p_local
mcp.tc/i/sas-viyalisting.about
Connects an assistant to a SAS Viya environment and exposes 92 tools across the analytics lifecycle. Tools are grouped in 10 tiers: Compute, Data Discovery, Data Operations, Reports, Batch Jobs, AutoML, Models, Decisioning, Workbench and Business Glossary. It also offers prompt templates for improving SAS code and interactive views for data, SAS logs and glossary editing in clients that render them.
It is self-hosted: run the container image ghcr.io/sassoftware/sas-mcp-server, or run it from source with Python 3.12+ and uv, in HTTP or stdio mode. It needs the VIYA_ENDPOINT of your SAS Viya environment with the compute service. Users sign in through SASLogon with OAuth 2.0 PKCE, or a cached token in stdio mode.
listing.can
- Execute SAS code on a Viya Compute context
- Discover and operate on data in Compute and CAS
- Work with reports and batch jobs
- Train AutoML projects and score models
- Use decisioning and business glossary tools
- Limit exposed tools by tier or read-only mode
- View data and SAS logs in interactive views
listing.tools
listing.notools.local
listing.prompts
Run this SAS code on Viya and show me the log
List the CAS tables available in my Viya environment
Train an AutoML project on my customer churn data
Score this dataset with the model registered in Viya
listing.setup.h
listing.setup.local
Claude Code
- Run this in a terminal, in your project folder:
claude mcp add --transport stdio sas-viya --env "VIYA_ENDPOINT=<YOUR_VIYA_ENDPOINT>" -- docker run -i --rm ghcr.io/sassoftware/sas-mcp-server:1.18.0- Start Claude Code and type
/mcp. sas-viya should show as connected.
Add --scope user to make it available in every project. Replace the placeholders with your own values.
Claude Desktop
- Open Settings → Developer → Edit Config. It opens
claude_desktop_config.json. Add:
{
"mcpServers": {
"sas-viya": {
"command": "docker",
"args": [
"run",
"-e",
"VIYA_ENDPOINT",
"-i",
"--rm",
"ghcr.io/sassoftware/sas-mcp-server:1.18.0"
],
"env": {
"VIYA_ENDPOINT": "<YOUR_VIYA_ENDPOINT>"
}
}
}
}- Save the file and restart Claude Desktop. Replace the placeholders with your own values.
Needs Docker on your computer. The file lives in ~/Library/Application Support/Claude/ on macOS and %APPDATA%\Claude\ on Windows.
Cursor
Or add it by hand to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project):
{
"mcpServers": {
"sas-viya": {
"command": "docker",
"args": [
"run",
"-e",
"VIYA_ENDPOINT",
"-i",
"--rm",
"ghcr.io/sassoftware/sas-mcp-server:1.18.0"
],
"env": {
"VIYA_ENDPOINT": "<YOUR_VIYA_ENDPOINT>"
}
}
}
}Needs Docker on your computer. Replace the placeholders with your own values.
VS Code
Install in VS Code a11y.new_tab
Or from a terminal:
code --add-mcp '{"name":"sas-viya","type":"stdio","command":"docker","args":["run","-e","VIYA_ENDPOINT","-i","--rm","ghcr.io/sassoftware/sas-mcp-server:1.18.0"],"env":{"VIYA_ENDPOINT":"<YOUR_VIYA_ENDPOINT>"}}'Or commit it to the repo in .vscode/mcp.json:
{
"servers": {
"sas-viya": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-e",
"VIYA_ENDPOINT",
"-i",
"--rm",
"ghcr.io/sassoftware/sas-mcp-server:1.18.0"
],
"env": {
"VIYA_ENDPOINT": "<YOUR_VIYA_ENDPOINT>"
}
}
}
}Needs Docker on your computer.
Devin Desktop
- Add it to
~/.config/devin/mcp_config.json(macOS and Linux) or%APPDATA%\devin\mcp_config.json(Windows):
{
"mcpServers": {
"sas-viya": {
"command": "docker",
"args": [
"run",
"-e",
"VIYA_ENDPOINT",
"-i",
"--rm",
"ghcr.io/sassoftware/sas-mcp-server:1.18.0"
],
"env": {
"VIYA_ENDPOINT": "<YOUR_VIYA_ENDPOINT>"
}
}
}
}- Refresh the MCP server list in Cascade. Replace the placeholders with your own values.
Devin Desktop is the new name for Windsurf.
Codex
codex mcp add sas-viya --env "VIYA_ENDPOINT=<YOUR_VIYA_ENDPOINT>" -- docker run -i --rm ghcr.io/sassoftware/sas-mcp-server:1.18.0Or edit ~/.codex/config.toml directly:
[mcp_servers.sas-viya]
command = "docker"
args = ["run", "-i", "--rm", "ghcr.io/sassoftware/sas-mcp-server:1.18.0"]
env = { VIYA_ENDPOINT = "<YOUR_VIYA_ENDPOINT>" }Needs Docker on your computer. Replace the placeholders with your own values.
Gemini CLI
gemini mcp add -e "VIYA_ENDPOINT=<YOUR_VIYA_ENDPOINT>" sas-viya docker -- run -i --rm ghcr.io/sassoftware/sas-mcp-server:1.18.0This adds it to the current project. Add -s user to use it everywhere.
Any client
Most clients that start local servers accept this shape:
{
"mcpServers": {
"sas-viya": {
"command": "docker",
"args": [
"run",
"-e",
"VIYA_ENDPOINT",
"-i",
"--rm",
"ghcr.io/sassoftware/sas-mcp-server:1.18.0"
],
"env": {
"VIYA_ENDPOINT": "<YOUR_VIYA_ENDPOINT>"
}
}
}
}Zed puts servers under context_servers in its settings, with the same command, args and env fields.
Needs Docker on your computer. Replace the placeholders with your own values.
listing.faq
Can I paste mcp.tc/i/sas-viya into my MCP client?
No. SAS Viya runs on your own computer, started by your client, so it has no web address to connect to. The quick link is the page to share; the install command is docker run -i --rm ghcr.io/sassoftware/sas-mcp-server:1.18.0.
Does SAS Viya need an API key?
No. It reads VIYA_ENDPOINT from its environment; the setup steps show where to set it.
Is SAS Viya a remote or a local server?
Local. Your client starts it as a process on your computer with docker run -i --rm ghcr.io/sassoftware/sas-mcp-server:1.18.0, which needs Docker.
What can SAS Viya do?
You can execute SAS code on a Viya Compute context, discover and operate on data in Compute and CAS and work with reports and batch jobs.
Which clients can use it?
Any client that starts local servers: Claude Code, Claude Desktop, Cursor, VS Code, Devin Desktop, Codex, Gemini CLI, Zed and others. claude.ai and ChatGPT only connect to remote servers.
Who wrote this page?
mcp.tc's robot read SAS Viya's public metadata (its package and repository pages), and an AI model drafted the text from it. A person reviews anything the checks can't confirm. The text can still be wrong, so if you spot a mistake, use Report this listing on this page.
listing.em.h
listing.em.lead_local listing.em.how
listing.em.badge
[](https://mcp.tc/i/sas-viya)<a href="https://mcp.tc/i/sas-viya"><img src="https://mcp.tc/i/sas-viya/badge.svg" alt="SAS Viya on mcp.tc" height="20"></a>listing.em.badge_note
listing.em.widget
<script src="https://mcp.tc/w/sas-viya.js" async></script>listing.em.widget_note
iframe
<iframe src="https://mcp.tc/embed/sas-viya" title="SAS Viya on mcp.tc" width="420" height="200" loading="lazy" allow="clipboard-write" style="border:0;border-radius:8px;max-width:100%"></iframe>listing.em.iframe_note
listing.disclaimer_checked