Self-hosted server that connects agents to a SAS Viya environment to run SAS code, train AutoML projects and manage models and scoring.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add sas-viya --env VIYA_ENDPOINT='<VIYA_ENDPOINT>' -- docker run -i --rm -e VIYA_ENDPOINT ghcr.io/sassoftware/sas-mcp-server:1.18.0~/.codex/config.toml
[mcp_servers.sas-viya]
command = "docker"
args = ["run", "-i", "--rm", "-e", "VIYA_ENDPOINT", "ghcr.io/sassoftware/sas-mcp-server:1.18.0"]
env = { VIYA_ENDPOINT = "<VIYA_ENDPOINT>" }
# codex mcp add sas-viya --env VIYA_ENDPOINT='<VIYA_ENDPOINT>' -- docker run -i --rm -e VIYA_ENDPOINT ghcr.io/sassoftware/sas-mcp-server:1.18.0~/.cursor/mcp.json
{
"mcpServers": {
"sas-viya": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"VIYA_ENDPOINT",
"ghcr.io/sassoftware/sas-mcp-server:1.18.0"
],
"env": {
"VIYA_ENDPOINT": "<VIYA_ENDPOINT>"
}
}
}
}.vscode/mcp.json
{
"servers": {
"sas-viya": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"VIYA_ENDPOINT",
"ghcr.io/sassoftware/sas-mcp-server:1.18.0"
],
"env": {
"VIYA_ENDPOINT": "<VIYA_ENDPOINT>"
}
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"sas-viya": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"VIYA_ENDPOINT",
"ghcr.io/sassoftware/sas-mcp-server:1.18.0"
],
"env": {
"VIYA_ENDPOINT": "<VIYA_ENDPOINT>"
}
}
}
}claude_desktop_config.json
{
"mcpServers": {
"sas-viya": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"VIYA_ENDPOINT",
"ghcr.io/sassoftware/sas-mcp-server:1.18.0"
],
"env": {
"VIYA_ENDPOINT": "<VIYA_ENDPOINT>"
}
}
}
}.trae/mcp.json
{
"mcpServers": {
"sas-viya": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"VIYA_ENDPOINT",
"ghcr.io/sassoftware/sas-mcp-server:1.18.0"
],
"env": {
"VIYA_ENDPOINT": "<VIYA_ENDPOINT>"
}
}
}
}Environment variables
VIYA_ENDPOINT
Replace the placeholders with your own credentials and keep them out of version control.