@sassoftware/sas-score-mcp-serverjs 1.0.1-30 → 1.0.1-32

package/.skills/skills/list-resource/SKILL.md

@@ -1,24 +1,27 @@
 ---
 name: list-resource
 description: >
-  Unified resource listing strategy. Use appropriate list tools for discovery and browsing.
-  Determines pagination parameters. Use list tools for discovery only; use find tools for verification.
+  Unified resource listing strategy. Use appropriate list tools for listing and browsing.
+  Determines pagination parameters. Use list tools for listing only; use find tools for verification of existence or discovery.
 ---
 
 # Unified Resource Listing Strategy
 
 
-Use this strategy to discover and browse available resources (libraries, tables, models, jobs, jobdefs).
+Use this strategy to list available resources (libraries, tables, models, jobs, jobdefs).
 
 ## Resource Type to Tool Mapping
 
-| Resource Type | List Tool |
-|--------------|-----------|
-| Libraries    | sas-score-list-libraries |
-| Tables       | sas-score-list-tables    |
-| Models       | sas-score-list-models    |
-| Jobs         | sas-score-list-jobs      |
-| JobDefs      | sas-score-list-jobdefs   |
+| Resource Type        | Aliases / Adjective Form               | List Tool                  |
+|----------------------|----------------------------------------|----------------------------|
+| Libraries            | library                                | sas-score-list-libraries   |
+| Tables               | table                                  | sas-score-list-tables      |
+| MAS Models           | mas model, model (default)             | sas-score-list-mas         |
+| Job Models           | job model, models of type job          | sas-score-list-jobs        |
+| JobDef Models        | jobdef model, models of type jobdef    | sas-score-list-jobdefs     |
+| SCR Models           | scr model, models of type scr          | *(no list tool available)* |
+
+When the user says "model" as an adjective (e.g. "mas model", "job model", "jobdef model", "scr model"), route to the corresponding list tool. When the model type is unspecified, default to MAS.
 
 Use this table to select the correct tool for each resource type. Then follow the logic for parameters and pagination below.
 
@@ -97,14 +100,28 @@ sas-score-list-tables({ lib: "Public", server: "cas", start: 11, limit: 10 })
 
 ---
 
-### 3. List Models
+### 3. List Scoring Models
+
+**Trigger**: "list models", "show all models", "what models are available",
+"list mas models", "list job models", "list jobdef models", "list scr models",
+"list models of type mas", "list models of type job", "list models of type jobdef",
+"list models of type scr", "show all scoring models"
+
+**Routing logic** — use the model type to pick the right tool:
 
-**Trigger**: "list models", "show all models", "browse models", "what models are available"
+| User phrase                              | Model type | Tool                   |
+|------------------------------------------|------------|------------------------|
+| "list models" (no type)                  | MAS (default) | `sas-score-list-mas` |
+| "list mas models" / "models of type mas" | MAS        | `sas-score-list-mas`   |
+| "list job models" / "models of type job" | Job        | `sas-score-list-jobs`  |
+| "list jobdef models" / "models of type jobdef" | JobDef | `sas-score-list-jobdefs` |
+| "list scr models" / "models of type scr" | SCR        | *(no list tool — inform user)* |
 
-**Tool**: `sas-score-list-models`
+#### 3a. MAS Models
 
-**Logic**: Lists all models published to the Model Administration Service (MAS).
-- No server selection required (MAS is centralized)
+**Tool**: `sas-score-list-mas`
+
+**Logic**: Lists all models published to the Model Administration Service (MAS). No server selection required.
 
 **Parameters**:
 ```
@@ -114,21 +131,68 @@ limit: <size>    # items per page (default 10)
 
 **Examples**:
 ```
-# List first 10 models
-sas-score-list-models({ start: 1, limit: 10 })
+# List first 10 MAS models
+sas-score-list-mas({ start: 1, limit: 10 })
+
+# Pagination: show next page
+sas-score-list-mas({ start: 11, limit: 10 })
+```
+
+#### 3b. Job Models
+
+**Tool**: `sas-score-list-jobs`
+
+**Logic**: Lists all SAS Viya job assets that can be used as scoring models.
+
+**Parameters**:
+```
+start: <offset>                # 1-based page number (default 1)
+limit: <page size>             # items per page (default 10)
+where: "<filter expression>"   # optional filter
+```
 
-# List 25 models
-sas-score-list-models({ start: 1, limit: 25 })
+**Examples**:
+```
+# List first 10 job models
+sas-score-list-jobs({ start: 1, limit: 10 })
 
 # Pagination: show next page
-sas-score-list-models({ start: 11, limit: 10 })
+sas-score-list-jobs({ start: 11, limit: 10 })
 ```
 
+#### 3c. JobDef Models
+
+**Tool**: `sas-score-list-jobdefs`
+
+**Logic**: Lists all SAS Viya job definition assets that can be used as scoring models.
+
+**Parameters**:
+```
+start: <offset>                # 1-based page number (default 1)
+limit: <page size>             # items per page (default 10)
+where: "<filter expression>"   # optional filter
+```
+
+**Examples**:
+```
+# List first 10 jobdef models
+sas-score-list-jobdefs({ start: 1, limit: 10 })
+
+# Pagination: show next page
+sas-score-list-jobdefs({ start: 11, limit: 10 })
+```
+
+#### 3d. SCR Models
+
+No list tool is available for SCR models. Inform the user and ask for a specific SCR endpoint URL if they want to work with an SCR model.
+
 ---
 
-### 4. List Jobs
+### 4. List Jobs (non-model)
+
+**Trigger**: "list jobs", "show all jobs", "what jobs are available"
 
-**Trigger**: "list jobs", "show all jobs", "browse jobs", "what jobs are available"
+> **Note**: "list job models" also routes here — jobs and job models use the same list tool.
 
 **Tool**: `sas-score-list-jobs`
 
@@ -146,18 +210,17 @@ where: "<filter expression>"   # optional filter
 # List first 10 jobs
 sas-score-list-jobs({ start: 1, limit: 10 })
 
-# List 25 jobs
-sas-score-list-jobs({ start: 1, limit: 25 })
-
 # Pagination: show next page
 sas-score-list-jobs({ start: 11, limit: 10 })
 ```
 
 ---
 
-### 5. List JobDefs
+### 5. List JobDefs (non-model)
 
-**Trigger**: "list jobdefs", "show all jobdefs", "browse jobdefs", "what jobdefs are available"
+**Trigger**: "list jobdefs", "show all jobdefs", "what jobdefs are available"
+
+> **Note**: "list jobdef models" also routes here — jobdefs and jobdef models use the same list tool.
 
 **Tool**: `sas-score-list-jobdefs`
 
@@ -175,9 +238,6 @@ where: "<filter expression>"   # optional filter
 # List first 10 jobdefs
 sas-score-list-jobdefs({ start: 1, limit: 10 })
 
-# List 25 jobdefs
-sas-score-list-jobdefs({ start: 1, limit: 25 })
-
 # Pagination: show next page
 sas-score-list-jobdefs({ start: 11, limit: 10 })
 ```
@@ -219,7 +279,7 @@ User requests to list/browse resources
 What resource type?
   ├─ Libraries? → Use sas-score-list-libraries
   ├─ Tables in library X? → Use sas-score-list-tables
-  ├─ Models? → Use sas-score-list-models
+  ├─ Models? → Use sas-score-list-mas
   ├─ Jobs? → Use sas-score-list-jobs
   └─ JobDefs? → Use sas-score-list-jobdefs
 ```
@@ -252,7 +312,7 @@ What resource type?
 
 | Aspect | Find | List |
 |---|---|---|
-| Purpose | Verify existence | Browse/discover |
+| Purpose | Verify/discover existence | List available resources |
 | Returns | Single resource or not found | Multiple resources with pagination |
-| Use case | Before execution | Exploration/discovery |
+| Use case | Before execution | Listing of resources |
 | Tool suffix | `find-*` | `list-*` |

package/.skills/skills/request-routing/SKILL.md

@@ -33,10 +33,15 @@ Once resources are verified to exist, select the appropriate execution tool:
 |---|---|---|
 | Read table rows | `sas-score-read-table` | lib, table, server (from Step 1) |
 | Query table (aggregation) | `sas-score-sas-query` | lib.table, SQL query |
-| Score with MAS model | `sas-score-mas-score` | model name, scenario data |
-| Run Job | `sas-score-run-jobdef` | job name, scenario parameters |
-| Run JobDef | `sas-score-run-jobdef` | jobdef name, scenario parameters |
-| Score with SCR model | `sas-score-scr-score` | SCR URL, scenario data |
+| Score with MAS model / `mas model X` | `sas-score-mas-score` | model name, scenario data |
+| Score with Job model / `job model X` | `sas-score-run-job` | job name, scenario parameters |
+| Score with JobDef model / `jobdef model X` | `sas-score-run-jobdef` | jobdef name, scenario parameters |
+| Score with SCR model / `scr model X` | `sas-score-scr-score` | SCR URL, scenario data |
+| Describe MAS model / `mas model X` | `sas-score-mas-info` | model name |
+| Describe Job model / `job model X` | `sas-score-job-info` | job name |
+| Describe JobDef model / `jobdef model X` | `sas-score-jobdef-info` | jobdef name |
+| Describe SCR model / `scr model X` | `sas-score-scr-info` | SCR URL |
+| Describe table | `sas-score-table-info` | lib, table, server |
 
 ---
 

package/.skills/skills/score-strategy/SKILL.md

@@ -26,12 +26,28 @@ Identify the scoring target (model type) and input source:
 
 ### Identify Model Type
 
+Model type can be expressed as a **dot-suffix** (`X.mas`) or as an **adjective form** (`mas model X`). Both are equivalent:
+
 ```
+# Dot-suffix form
 score with model X.mas       → MAS model
 score with model X.job       → Job
 score with model X.jobdef    → JobDef
 score with model X.scr       → SCR model
 score with model X (default to MAS if type is not specified) → MAS model
+
+# Adjective form (equivalent)
+score with mas model X       → MAS model
+score with job model X       → Job
+score with jobdef model X    → JobDef
+score with scr model X       → SCR model
+
+# Short form (no "model" keyword)
+score with X.mas       → MAS model
+score with X.job       → Job
+score with X.jobdef    → JobDef
+score with X.scr       → SCR model
+score with X (default to MAS if type is not specified) → MAS model
 ```
 
 ### Visual Flowchart
@@ -83,9 +99,11 @@ score results of query...    → Query results
 ```
 sas-score-mas-score({
   model: "<model name>",
-  scenario: { a: 1, b: 2 }  
+  scenario: { a: 1, b: 2 }
+})
 ```
-**Parameters** (job):                                           ):
+
+**Parameters** (job):
 ```
 sas-score-run-job({
   name: "<job name>",
@@ -216,7 +234,7 @@ If table columns don't match model input variable names:
 
 ### Example 3: Score table rows
 **Request**: "score all active customers with model risk_model and table Public.customers"
-1. Find model risk_model.mad using find-resources strategy
+1. Find model risk_model.mas using find-resources strategy
 2. Find table Public.customers using find-resources strategy
 3. Read: `sas-score-read-table({ lib: "Public", table: "customers", server: "cas", where: "status='active'" })`
 4. Score each row with risk_model

package/README.md

@@ -9,6 +9,8 @@ See [wiki](https://github.com/sassoftware/sas-score-mcp-serverjs/wiki) for the c
 
 - Agent - can be deployed as an agent
 
+- Docker image:  ghcr.io/sassoftware/sas-score-mcp-serverjs
+
 
 ## Overview
 This MCP server is designed for scoring with SAS Viya.
@@ -23,6 +25,22 @@ Some examples are:
   - job Definitions
   - jobs using SAS Studio or other interfaces
 
+## Start the mcp server
+
+If using stdio transport, most of the mcp clients will start the server automatically.
+But for http transport, the mcp server must be started. 
+
+If running locally
+```sh
+npx @sassoftware/sas-score-mcp-serverjs@latest
+```
+
+The mcp is also available as a docker image. Add or remove the env variables as needed.
+
+```sh
+docker run -p 8080:8080 --name sasscore -e VIYA_SERVER=<yourviyaserver> -e AUTHFLOW=oauth ghcr.io/sassoftware/sas-score-mcp-serverjs:latest
+```
+
 ## Capabilities
 
 The tools can be grouped into these categories
@@ -56,43 +74,60 @@ Typically these are set either in the .env file or as environment variables or a
 
 ### Required Options
 
-VIYA_SERVER=<url for Viya server>
+1. VIYA_SERVER=
+   <url for Viya server>. 
 
-MCPTYPE=http|stdio
+### Options with defaults
 
-MCPHOST=<url for the mcp server = http://localhost:8080 or some remote mcp server>
+These can be customized
 
->Recommended authflow is oauth - the most secure of all the options since all oauth flow occurs in the server and the actual token is never sent to the client. Bearer authflow is useful when the mcp server is remote with its own authentication process
+1. AUTHFLOW=**oauth**|oauthclient|bearer|sascli|token|password 
+    - Authentication method. Default is oauth
 
-AUTHFLOW=oauth|oauthclient|bearer|sascli|token|password
+2. CLIENTID=**vscodemcp** 
+     - Clientid for oauth and oauthclient AUTHFlOW. Must be PKCE clientid. 
+     
 
-> Options for oauth. The clientid must have a redirect of http://localhost:8080/callback,https://localhost:8080/callback
+3. MCPTYPE=**http**|stdio  
+    - The transport protocol for the mcp server. 
 
-CLIENTID=<pkce clientid>
+4. MCPHOST=**http://localhost:8080**
+   - URL of the mcp server. If using remote mcp server, set this to remote MCP server
 
+5. PROFILE=**~/.sas**
+    - profile name used by sas-cli to store the tokens 
 
-> OauthClient Flow. Clientid with redirect appropriate for the client. Some examples are shown below. Note that the explicit port used by github copilot is not guaranteed. 
+6. PORT=**8080**
+    - set it to what fits your environment. 
 
-- github copilot: http://127.0.0.1:33418/
-- claude: https://claude.ai/api/mcp/auth_callback,https://claude.ai/api/auth/callback
+7. CASSERVER=**cas-shared-default** 
+    - Set to a valid cas server
 
-> bearer - Use this when the remote mcp server sends the token in the header.
+8. COMPUTECONTEXT=**"SAS Job Execution compute context"**
+    - Use one that is appropriate
 
+### Clientid specifications
 
-> sascli - Use sas-viya cli to create the token information. It is stored in ~/.sas folder by default
+If using remote mcp server, change the url in redirect to the remote url
 
-```env
-PROFILE=<profile name used by sas-cli to store the tokens in ~/.sas> 
+```js
+{
+  client_id: 'vscodemcp',
+  scope: [ 'openid' ],
+  resource_ids: [ 'none' ],
+  autoapprove: true,
+  authorized_grant_types: [ 'authorization_code' ],
+  access_token_validity: 86400,
+  allowpublic: true,
+  redirect_uri: [ 'http://localhost:8080/callback' ]
+}
 ```
 
-### Other options
+> OauthClient Flow. Clientid with redirect appropriate for the client. Some examples are shown below. Note that the explicit port used by github copilot is not guaranteed. 
+
+- github copilot: http://127.0.0.1:33418/
+- claude: https://claude.ai/api/mcp/auth_callback,https://claude.ai/api/auth/callback
 
-```env
-PORT=<default is 8080>
-HTTPS=FALSE
-CASSERVER=CAS server name (default: cas-shared-default)
-COMPUTECONTEXT=Compute session name or context (default: SAS Job Execution compute context) 
-```
 
 ## Agent and skills
 
@@ -110,14 +145,15 @@ The skills and related files will be written to .github or .claude
 ## Configure the mcp client for localhost
 
 The mcp configuration for oauth flow. For remote mcp, change the url to the
-appropriate url.
+remote url
 
 ```json
  "sasmcp": {
     "type": "http",
-    "url": "http://localhost:8080/mcp"``
+    "url": "http://localhost:8080/mcp"
     "oauth: {
-      "type": "oauth2"
+      "type": "oauth2",
+      "clientId: "vscodemcp"
     }
  }
 ```
@@ -126,13 +162,14 @@ For bearer authflow.
 ```json
  "sasmcp": {
     "type": "http",
-    "url": "your remote mcp server`,
+    "url": "http://localhost:8080/mcp`,
     "headers" {
       "Authorization": "bearer <tokenstring>"
       }
  }
 ```
 
+For stdio scenario
 ```json
 "sas-mcp-server": {
       "type: "stdio"
@@ -148,25 +185,7 @@ For bearer authflow.
     }
 ```
 
-#### Step 2: Start the mcp server
-
-If using stdio transport, most of the mcp clients will start the server automatically.
-But for http transport, the mcp server must be started. 
-
-If running locally
-```sh
-npx @sassoftware/sas-score-mcp-serverjs@latest
-```
-
-The mcp is also available as a docker image. Add or remove the env variables as needed.
-
-```sh
-docker run -p 8080:8080 --name sasscore -e VIYA_SERVER=<yourviayserver> -e AUTHFLOW=oauth ghcr.io/sassoftware/sas-score-mcp-serverjs:latest
-```
-
-If you want to run it in docker then use docker run:
 
-Make sure that the .env file is in the current working directory or specify the options in the command line
 
 
 ## Notes