@sassoftware/sas-score-mcp-serverjs 1.0.1-30 → 1.0.1-31

package/.skills/copilot-instructions.md

@@ -32,6 +32,7 @@ When you receive a SAS request, classify it using request-routing skill:
 | Read | "read", "show", "fetch", "query", "how many", "count by" | read-strategy | sas-score-read-table, sas-score-sas-query |
 | Score | "score", "predict", "run model" | score-strategy | sas-score-mas-score, sas-score-run-jobdef, sas-score-scr-score |
 | List | "list", "show all", "browse" | — | sas-score-list-libraries, sas-score-list-tables, sas-score-list-models, etc. |
+| Describe | "describe", "what inputs", "show schema", "metadata", "information" | detail-strategy | sas-score-model-info, sas-score-job-info, sas-score-scr-info, sas-score-table-info |
 
 ---
 
@@ -78,9 +79,8 @@ These terms are overloaded in SAS and must be clarified:
 
 - **model**: MAS, Job, JobDef, or SCR?
 - **score/scoring**: Running a model on data (not code coverage)
-- **job**: SAS Job or SAS JobDef?
 - **table**: CAS table or SAS dataset? Which library?
-- **resource**: Library, table, model, job, or jobdef?
+- **resource**: Library, table, model, job,jobdef, scr?
 - **read/query**: Raw row read or aggregation?
 
 When ambiguous, ask one focused clarifying question.
@@ -95,12 +95,15 @@ See the strategies folder:
 - **find-resources** — How to verify resources exist
 - **read-strategy** — How to read/query tables
 - **score-strategy** — How to score/predict
+- **list-resource** — How to list resources
+- **detail-strategy** — How to retrieve details about a resource
 - **sas-score-mcp-serverjs-agent** — Main orchestration agent
 
 ---
 
 ## Response Format
 
+Whenever possible format the response as a markdown table or structured JSON for easy readability.
 After completing a SAS Viya request, append a brief **Strategy Summary**:
 
 ```
@@ -157,7 +160,7 @@ Example:
 4. Result: Aggregated data by make
 
 ### Example 3: Read Rows
-**User**: "read first 20 customers from Public"
+**User**: "read first 20 customers from Public.customers"
 
 **Process**:
 1. Classify: Read request, raw row read
@@ -166,7 +169,7 @@ Example:
 4. Result: 20 customer rows
 
 ### Example 4: Score Table Rows
-**User**: "score all active customers with model risk_model"
+**User**: "score all active customers in Public.customers with model risk_model"
 
 **Process**:
 1. Classify: Score request, table rows
@@ -197,6 +200,10 @@ Example:
 | | sas-score-list-models | Browse MAS models |
 | | sas-score-list-jobs | Browse jobs |
 | | sas-score-list-jobdefs | Browse jobdefs |
+| **Detail** | sas-score-model-info | Get MAS model details |
+| | sas-score-job-info | Get Job model details |
+| | sas-score-scr-info | Get SCR model details |
+| | sas-score-table-info | Get table details |
 
 ---
 

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

@@ -1,68 +1,64 @@
 ---
 name: detail-strategy
 description: >
-  Unified detail/information retrieval strategy. Handles MAS models, SCR models, and tables.
-  Always verify resources exist using find-resources skill before retrieving details, except for SCR models (which do not require pre-verification).
+  Unified detail/information/describe retrieval strategy. Handles MAS models, Job models, JobDef models, SCR models, and tables. Verify resources exist using find-resources skill before retrieving details (except SCR models, which can be queried directly).
 ---
 
 # Detail Strategy
 
+Use this strategy when the user requests information about a resource.
 
-Use this strategy when the user requests information about a resource: model details, schema, metadata, inputs/outputs, or any descriptive information.
+**Supported resource types**: MAS model, Job model, JobDef model, SCR model, or table.
 
-If the resource type is ambiguous or cannot be determined, ask the user for clarification.
-If the resource type is not MAS, SCR, or table, respond with: "Unsupported resource type. Please specify MAS model, SCR model, or table."
+If the specified resource is ambiguous, ask the user for clarification (e.g. "Are you asking about a MAS model, a Job model, a JobDef model, a SCR model or a table?").
 
+Verification vs Retrieval (simplified)
 
-## Simplified Steps
+- We separate the workflow into two clear, sequential phases to reduce branching and cognitive load:
+  1. Verification phase — confirm the resource exists and determine its exact type and server. Use the appropriate "find" tool for all resource types except SCR models.
+  2. Retrieval phase — after successful verification, call the detail/read tool appropriate for the identified resource type to fetch metadata or content.
 
-1. Determine resource type (MAS model, SCR model, or table)
-2. If MAS model or table, verify resource exists using find-resources skill
-  - If SCR model, skip verification and proceed to retrieval
-3. Retrieve details using the appropriate tool
+- Exception for SCR models: document the exception inline — SCR models may be queried directly with `sas-score-scr-info` when the user provides a specific SCR endpoint. Even when skipping verification, still validate the endpoint/URL format before calling the tool.
 
----
+Apply this separation consistently across MAS models, Job models, JobDef models, SCR models, and tables.
 
+---
 
-## Step 1: Identify Resource Type
+## Classification & Verification Process
 
-Classify the resource based on naming convention or context:
+### Phase 1: Classify the Resource Type
 
-| Pattern                        | Resource Type |
-|--------------------------------|--------------|
-| model X.mas or "model X"       | MAS model    |
-| model X.scr                    | SCR model    |
-| table X in library Y           | Table        |
+Determine resource type from context/naming conventions:
 
-If resource type cannot be determined, ask the user for clarification.
+| Pattern                  | Resource Type |
+|--------------------------|---------------|
+| model X (or X.mas)       | MAS model     |
+| model X.scr              | SCR model     |
+| model X.job              | Job model     |
+| model X.jobdef           | JobDef model  |
+| table X in library Y     | Table         |
 
----
+If resource is ambiguous, ask user for clarification.
 
-## Step 2: Verify Resource Exists (if required)
+### Phase 2: Verify Resource Exists (Skip for SCR Models)
 
-| Resource Type | Verification Required? | How to Verify |
-|---------------|-----------------------|---------------|
-| MAS model     | Yes                   | find-model    |
-| SCR model     | No                    | —             |
-| Table         | Yes                   | find-table    |
+For each resource type, use the appropriate verification tool:
 
-If resource type is not supported, respond with: "Unsupported resource type. Please specify MAS model, SCR model, or table."
+| Resource Type | Tool              |
+|---------------|-------------------|
+| MAS model     | sas-score-find-model |
+| Job model     | sas-score-find-job   |
+| JobDef model  | sas-score-find-jobdef |
+| Table         | sas-score-find-table  |
+| SCR model     | *(no verification needed)* |
 
-### Find SCR Model
-```
-find-resources skill → find-scr
-Tool: sas-score-find-scr({ url: "<scr-endpoint>" })
-```
-
-### Find Table
-```
-find-resources skill → find-table
-Tool: sas-score-find-table({ lib: "<library>", name: "<table>", server: "<cas|sas>" })
-```
+If verification fails, inform the user and ask for additional details or corrections.
 
 ---
 
-## Step 3: Get Details
+## Detail Retrieval Process
+
+### Phase 3: Get Details
 
 ### Option A: MAS Model Details
 
@@ -153,20 +149,52 @@ User: "What columns are in the customers table in Public?"
 ```
 
 ---
+### Option D: Job Model Details
+
+**Trigger phrases**: "what inputs does job model X need", "describe job model X", "show variables for job model X", "job model X metadata", "job model X information"
+
+**Tool**: `sas-score-job-info`
+
+**Parameters**:
+```
+sas-score-job-info({
+  model: "<model name>"
+})
+```
+
+**Returns**:
+- Input variables (name, type, role)
+
+**Example**:
+```
+User: "What inputs does job model churnRisk need?"
+
+1. Find: sas-score-find-job({ name: "churnRisk" })
+2. Get info: sas-score-job-info({ model: "churnRisk" })
+3. Return: { inputs: [...] }
+```
 
 ## Decision Tree
 
 ```
 User requests information/details
   ├─ About a MAS model?
-  │   → Find model (find-resources)
+  │   → Verify: sas-score-find-model
   │   → Call: sas-score-model-info
   │
   ├─ About a SCR model?
-  │   → Call: sas-score-scr-info (can skip verification)
+  │   → Call: sas-score-scr-info (skip verification; validate URL first)
+  │
+  ├─ About a Job model?
+  │   → Verify: sas-score-find-job
+  │   → Call: sas-score-job-info
+  │
+  ├─ About a JobDef model?
+  │   → Verify: sas-score-find-jobdef
+  │   → Call: sas-score-job-info
   │
   └─ About a table?
-      → Find table (find-resources, determine server)
+      → Verify: sas-score-find-table (determine CAS or SAS server)
       → Call: sas-score-table-info
 ```
 
@@ -176,7 +204,7 @@ User requests information/details
 
 For each detail/information request:
 
-- [ ] **Classify** resource type (MAS/SCR/table)
+- [ ] **Classify** resource type (MAS / Job / JobDef / SCR / table)
 - [ ] **Verify** resource exists (use find-resources skill, except SCR)
 - [ ] **Determine** server for tables (CAS or SAS)
 - [ ] **Execute** appropriate detail tool

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

@@ -1,14 +1,14 @@
 ---
 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
 
@@ -252,7 +252,7 @@ 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

@@ -37,6 +37,10 @@ Once resources are verified to exist, select the appropriate execution tool:
 | 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 |
+| Describe MAS model | `sas-score-model-info` | model name |
+| Describe Job/JobDef | `sas-score-job-info` | job or jobdef name |
+| Describe SCR model | `sas-score-scr-info` | SCR URL |
+| Describe table | `sas-score-table-info` | lib, table, server |
 
 ---
 

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

@@ -83,9 +83,11 @@ 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>",

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