@sassoftware/sas-score-mcp-serverjs 1.0.1-31 → 1.0.1-32

package/.skills/agents/sas-score-mcp-serverjs-agent.md

@@ -156,7 +156,7 @@ Always append a **Strategy Summary** to responses:
 **Workflow**:
 1. Classify: Score request with inline scenario
 2. Verify: Find job "simplejob" → Found ✓
-3. Execute: `sas-score-run-jobdef({ name: "simplejob", scenario: { a: 1, b: 2 } })`
+3. Execute: `sas-score-run-job({ name: "simplejob", scenario: { a: 1, b: 2 } })`
 4. Format: Return `{ a: 1, b: 2, c: 3 }`
 
 ### Example 2: Read + Aggregate

package/.skills/copilot-instructions.md

@@ -3,24 +3,27 @@
 You are a SAS Viya expert agent for GitHub Copilot.
 
 
-Your role: Help users complete SAS Viya tasks safely and accurately using the simplified three-step workflow.
+Your role: Help users complete SAS Viya tasks safely and accurately using the simplified five-step workflow.
 
 **High-Level Decision Framework:**
-1. Identify the user's intent (Find, Read, Score, List)
-2. Verify resources if required
-3. Select the appropriate tool based on intent and resource type
-4. Execute and format the result
+1. Identify the user's intent (Find, Read, Score, Run, List)
+2. Identify the resources involved (libraries, tables, models, jobs, jobdefs, scr, src)
+3. Verify resources exist using find-resources tools 
+4. Select the appropriate tool based on intent and resource type
+5. Execute and format the result
 
 
 ---
 
 ## Operating Model
 
-### Every Request Follows Three Steps
+### Every Request Follows Five Steps
 
-1. **VERIFY** — Use find-resources to verify target resources exist
-2. **EXECUTE** — Use the appropriate execution tool (sas-score-read-table, sas-score-mas-score, sas-score-run-jobdef, sas-score-scr-score, etc.)
-3. **FORMAT** — Merge results and return to user
+1. **IDENTIFY** — Determine the user's intent and the resources involved
+2. **VERIFY** — Use find-resources to verify target resources exist
+3. **SELECT** — Choose the appropriate tool based on intent and resource type
+4. **EXECUTE** — Use the appropriate execution tool (sas-score-read-table, sas-score-mas-score, sas-score-run-jobdef, sas-score-run-job, sas-score-scr-score, sas-score-run-sas-program, etc.)
+5. **FORMAT** — Merge results and return to user
 
 ### Request Classification
 
@@ -30,9 +33,9 @@ When you receive a SAS request, classify it using request-routing skill:
 |---|---|---|---|
 | Find | "find", "locate", "exists" | find-resources | sas-score-find-library, sas-score-find-table, etc. |
 | 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 |
+| Score | "score", "predict", "run model", "run mas model", "run job model", "run jobdef model", "run scr model" | score-strategy | sas-score-mas-score, sas-score-run-job, sas-score-run-jobdef, sas-score-scr-score, sas-score-run-sas-program |
+| List | "list", "show all" | — | sas-score-list-libraries, sas-score-list-tables, sas-score-list-mas (MAS models), sas-score-list-jobs (job models), sas-score-list-jobdefs (jobdef models) |
+| Describe | "describe", "what inputs", "show schema", "metadata", "information" | detail-strategy | sas-score-mas-info, sas-score-job-info, sas-score-jobdef-info, sas-score-scr-info, sas-score-table-info |
 
 ---
 
@@ -40,12 +43,12 @@ When you receive a SAS request, classify it using request-routing skill:
 
 ### 1. Always Verify Before Executing
 
-Exception: SCR models can score without pre-verification.
+**Exception** - List operations do not require pre-verification. They can be executed directly to explore available resources.
 
 ```
 Verify resources exist (find-resources)
   ↓
-Execute action (sas-score-read-table, sas-score-mas-score, sas-score-run-jobdef, sas-score-scr-score, etc.)
+Execute action (sas-score-read-table, sas-score-mas-score, sas-score-run-jobdef, sas-score-run-job, sas-score-scr-score, sas-score-run-sas-program, etc.)
   ↓
 Merge and format results
 ```
@@ -56,16 +59,37 @@ Every table operation must explicitly determine whether the table is in CAS or S
 - CAS tables: Caslib.table (Casuser, Public, Samples, Formats, etc.)
 - SAS tables: LIBREF.table (SASHELP, WORK, SASUSER, etc.)
 
-Use find-resources to determine server if not specified by user.
+Use find-resources skill to determine server if not specified by user.
+
+**DO NOT** use list-resources to find a resource. This is prone to errors and inefficient. Always use find-resources for verification.
 
 ### 3. Explicit Model Type
 
-If model type is ambiguous, use MAS as a predefined fallback policy (this is an explicit exception to the 'never invent' rule):
-- `score with model X` → MAS (default)
-- `score with model X.mas` → MAS
-- `score with model X.job` → Job
-- `score with model X.jobdef` → JobDef
-- `score with model X.scr` → SCR (no pre-verification)
+Model type can be expressed as a **dot-suffix** (`X.mas`) or as an **adjective form** (`mas model X`). Both are equivalent and should be handled the same way:
+
+```
+# Dot-suffix form
+score with model X           → MAS (default)
+score with model X.mas       → MAS
+score with model X.job       → Job
+score with model X.jobdef    → JobDef
+score with model X.scr       → SCR (no pre-verification)
+run model X                  → MAS (default)
+run model X.mas              → MAS
+run model X.job              → Job
+run model X.jobdef           → JobDef
+run model X.scr              → SCR (no pre-verification)
+
+# Adjective form (equivalent)
+score with mas model X       → MAS
+score with job model X       → Job
+score with jobdef model X    → JobDef
+score with scr model X       → SCR (no pre-verification)
+run mas model X              → MAS
+run job model X              → Job
+run jobdef model X           → JobDef
+run scr model X              → SCR (no pre-verification)
+```
 
 ### 4. No Invention
 
@@ -77,10 +101,10 @@ Never invent resource names, identifiers, servers, or model types. Always verify
 
 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)
+- **model**: Can refer to a MAS model, Job model, JobDef model, or SCR model. Disambiguate using the **adjective form** (`mas model`, `job model`, `jobdef model`, `scr model`) or a **dot-suffix** (`.mas`, `.job`, `.jobdef`, `.scr`). Default to MAS when no type is given.
+- **score/scoring/run**: Running a scoring model on data, or running a SAS program?
 - **table**: CAS table or SAS dataset? Which library?
-- **resource**: Library, table, model, job,jobdef, scr?
+- **resource**: Library, table, model (which type?), job, jobdef, scr?
 - **read/query**: Raw row read or aggregation?
 
 When ambiguous, ask one focused clarifying question.

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

@@ -8,10 +8,12 @@ description: >
 
 Use this strategy when the user requests information about a resource.
 
-**Supported resource types**: MAS model, Job model, JobDef model, SCR model, or table.
+**Supported resource types**: MAS model, Job model, JobDef 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?").
 
+**Model**: If user just says "model X" without specifying type, default to MAS model (this is an explicit exception to the 'never invent' rule, but it is a predefined convention in SAS).
+
 Verification vs Retrieval (simplified)
 
 - We separate the workflow into two clear, sequential phases to reduce branching and cognitive load:
@@ -32,21 +34,31 @@ Determine resource type from context/naming conventions:
 
 | 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         |
+| `mas X` or `X.mas`       | MAS model  X   |
+| `mas model X`            | MAS model  X   |
+| `scr X` or `X.scr`       | SCR model X    |
+| `scr model X`            | SCR model  X   |
+| `job model X`            | Job model  X   |
+| `jobdef X` or `X.jobdef` | JobDef model  X |
+| `jobdef model X`         | JobDef model  X |
+| `table X in library Y`   | Table  X in library Y |
+| `model X.mas`            | MAS model  X   |
+| `model X.job`            | Job model  X   |
+| `model X.jobdef`         | JobDef model  X |
+| `model X.scr`            | SCR model  X   |
+| `model X` (ambiguous)    | Default to MAS model (explicit convention) |
 
 If resource is ambiguous, ask user for clarification.
 
 ### Phase 2: Verify Resource Exists (Skip for SCR Models)
 
+**IMPORTANT**: Strip the suffix if user included it, use base name for lookup (e.g. "churnRisk.mas" → "churnRisk") to avoid lookup failures.
+
 For each resource type, use the appropriate verification tool:
 
 | Resource Type | Tool              |
 |---------------|-------------------|
-| MAS model     | sas-score-find-model |
+| MAS model     | sas-score-find-mas |
 | Job model     | sas-score-find-job   |
 | JobDef model  | sas-score-find-jobdef |
 | Table         | sas-score-find-table  |
@@ -62,13 +74,16 @@ If verification fails, inform the user and ask for additional details or correct
 
 ### Option A: MAS Model Details
 
-**Trigger phrases**: "what inputs does model X need", "describe model X", "show variables for model X", "model X metadata", "model X information"
+**Trigger phrases**: "what inputs does mas model X need", "describe mas X", "show variables for model mas X, describe X.mas",
+"mas model X metadata", "mas model X information", "describe model X" (default to MAS),
+"what inputs does mas X need", "describe mas X"
 
-**Tool**: `sas-score-model-info`
+**Tool**: `sas-score-mas-info`
 
 **Parameters**:
 ```
-sas-score-model-info({
+
+sas-score-mas-info({
   model: "<model name>"
 })
 ```
@@ -81,10 +96,10 @@ sas-score-model-info({
 
 **Example**:
 ```
-User: "What inputs does model churnRisk need?"
+User: "What inputs does mas model churnRisk need?"
 
 1. Find: sas-score-find-model({ name: "churnRisk" })
-2. Get info: sas-score-model-info({ model: "churnRisk" })
+2. Get info: sas-score-mas-info({ model: "churnRisk" })
 3. Return: { inputs: [...], outputs: [...], description: "..." }
 ```
 
@@ -92,7 +107,8 @@ User: "What inputs does model churnRisk need?"
 
 ### Option B: SCR Model Details
 
-**Trigger phrases**: "what does SCR model X need", "describe SCR model X", "SCR model X inputs", "SCR model X schema"
+**Trigger phrases**: "what does SCR model X need", "describe SCR model X", "scr model X inputs",
+"scr model X schema", "what inputs does scr model X need", "describe scr X"
 
 **Tool**: `sas-score-scr-info`
 
@@ -151,7 +167,9 @@ 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"
+**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",
+"what inputs does job X need", "describe job X"
 
 **Tool**: `sas-score-job-info`
 
@@ -179,8 +197,8 @@ User: "What inputs does job model churnRisk need?"
 ```
 User requests information/details
   ├─ About a MAS model?
-  │   → Verify: sas-score-find-model
-  │   → Call: sas-score-model-info
+  │   → Verify: sas-score-find-mas
+  │   → Call: sas-score-mas-info
   │
   ├─ About a SCR model?
   │   → Call: sas-score-scr-info (skip verification; validate URL first)

package/.skills/skills/find-resources/SKILL.md

@@ -64,43 +64,50 @@ Do **not** use list tools for verifying or finding specific resources. List tool
 
 ---
 
-### 3. Find MAS Model
+### 3. Find Scoring Model
 
-**Trigger**: "find model X", "does model X exist", "locate model X"
+**Trigger**: "find model X", "find mas model X", "find job model X", "find jobdef model X",
+"find scr model X", "does model X exist", "locate model X", "find job X", "does job X exist",
+"find jobdef X", "does jobdef X exist"
 
-**Tool**: `sas-score-find-model`
+**Routing** — use the model type to pick the right find tool:
 
-**Logic**: Strip `.mas` suffix if present, use base name
-- `sas-score-find-model({ name: "<model>" })`
+| User phrase / suffix                           | Model type | Find Tool              |
+|------------------------------------------------|------------|------------------------|
+| `find mas model X` / `X.mas` / `mas X`         | MAS        | `sas-score-find-model` |
+| `find job model X` / `X.job` / `job X`         | Job        | `sas-score-find-job`   |
+| `find jobdef model X` / `X.jobdef` / `jobdef X`| JobDef     | `sas-score-find-jobdef`|
+| `find scr model X` / `X.scr` / `scr X`         | SCR        | *(no tool — ask for URL)*|
+| `find model X` (no type)                       | MAS (default) | `sas-score-find-model` |
 
----
+#### MAS Model
 
-### 4. Find Job
+**Tool**: `sas-score-find-model`
 
-**Trigger**: "find job X", "does job X exist", "locate job X"
+**Logic**: Strip `.mas` suffix if present, use base name.
+```
+sas-score-find-model({ name: "<model>" })
+```
 
-**Tool**: `sas-score-find-job`
+#### Job Model
 
-**Logic**:
-- `sas-score-find-job({ name: "<job>" })`
-
----
+**Tool**: `sas-score-find-job`
 
-### 5. Find JobDef
+**Logic**: Strip `.job` suffix if present, use base name.
+```
+sas-score-find-job({ name: "<job>" })
+```
 
-**Trigger**: "find jobdef X", "does jobdef X exist", "locate jobdef X"
+#### JobDef Model
 
 **Tool**: `sas-score-find-jobdef`
 
-**Logic**:
-- `sas-score-find-jobdef({ name: "<jobdef>" })`
-
----
-
-### 6. Find SCR Model
-
-**Trigger**: "find scr model X", "does scr model X exist"
+**Logic**: Strip `.jobdef` suffix if present, use base name.
+```
+sas-score-find-jobdef({ name: "<jobdef>" })
+```
 
+#### SCR Model
 
 **Action**: Ask user for the SCR URL/endpoint. SCR models do not have a pre-verification tool.
 If the SCR URL/endpoint is invalid or missing, prompt the user to provide a valid URL.
@@ -112,15 +119,15 @@ If the SCR URL/endpoint is invalid or missing, prompt the user to provide a vali
 
 ## Generic Model Type Inference
 
-If user says "find model X" without a type suffix, infer the type:
+If user says "find model X" without a type qualifier, infer the type from the suffix or adjective form:
 
-| Suffix | Type | Find Tool |
-|---|---|---|
-| `.mas` | MAS model | `sas-score-find-model` |
-| `.job` | SAS Job | `sas-score-find-job` |
-| `.jobdef` | SAS JobDef | `sas-score-find-jobdef` |
-| `.scr` | SCR model | Skip (no find) |
-| (none) | Default to MAS | `sas-score-find-model` |
+| Pattern                              | Type    | Find Tool               |
+|--------------------------------------|---------|-------------------------|
+| `X.mas` / `mas model X` / `mas X`    | MAS     | `sas-score-find-model`  |
+| `X.job` / `job model X` / `job X`    | Job     | `sas-score-find-job`    |
+| `X.jobdef` / `jobdef model X` / `jobdef X` | JobDef | `sas-score-find-jobdef` |
+| `X.scr` / `scr model X` / `scr X`    | SCR     | Skip (no find tool)     |
+| (none)                               | Default to MAS | `sas-score-find-model` |
 
 ---
 

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

@@ -12,13 +12,16 @@ Use this strategy to list available resources (libraries, tables, models, jobs,
 
 ## 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
 ```

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

@@ -33,13 +33,14 @@ 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 |
-| 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 |
+| 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
@@ -218,7 +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/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sassoftware/sas-score-mcp-serverjs",
-  "version": "1.0.1-31",
+  "version": "1.0.1-32",
   "description": "A mcp server for SAS Viya",
   "author": "Deva Kumar <deva.kumar@sas.com>",
   "license": "Apache-2.0",

package/scripts/plot_msrp_usa.py

@@ -0,0 +1,49 @@
+import matplotlib
+matplotlib.use('Agg')
+import matplotlib.pyplot as plt
+from pathlib import Path
+
+data = [
+    ("Cadillac", 50474.375),
+    ("Hummer", 49995.0),
+    ("Lincoln", 42875.555556),
+    ("Buick", 30537.777778),
+    ("GMC", 29560.5),
+    ("Mercury", 27972.777778),
+    ("Chrysler", 27252.0),
+    ("Chevrolet", 26587.037037),
+    ("Dodge", 26253.846154),
+    ("Jeep", 24518.333333),
+    ("Pontiac", 24156.363636),
+    ("Ford", 24015.869565),
+    ("Oldsmobile", 23763.333333),
+    ("Saturn", 17234.375),
+]
+
+# Sort by value descending
+data.sort(key=lambda x: x[1], reverse=True)
+makes = [d[0] for d in data]
+values = [d[1] for d in data]
+
+out_dir = Path('outputs')
+out_dir.mkdir(parents=True, exist_ok=True)
+out_file = out_dir / 'make_avg_msrp_usa.png'
+
+plt.figure(figsize=(12, 6))
+bars = plt.bar(makes, values, color='tab:blue')
+plt.title('Average MSRP by Make (Origin = USA)')
+plt.ylabel('Average MSRP')
+plt.xticks(rotation=45, ha='right')
+plt.tight_layout()
+
+# Annotate bars
+for bar in bars:
+    height = bar.get_height()
+    plt.annotate(f'{height:,.0f}',
+                 xy=(bar.get_x() + bar.get_width() / 2, height),
+                 xytext=(0, 3),
+                 textcoords='offset points',
+                 ha='center', va='bottom', fontsize=8)
+
+plt.savefig(out_file)
+print(f'Plot saved to {out_file}')

package/src/toolHelpers/_findMas.js

@@ -0,0 +1,12 @@
+/*
+ * Copyright © 2025, SAS Institute Inc., Cary, NC, USA.  All Rights Reserved.
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import _listMas from './_listMas.js';  
+async function _findMas(params) {
+    let r = await _listMas(params);
+    console.log ("findMas result:" , r);
+    return r;
+}
+export default _findMas;

package/src/toolHelpers/{_listModels.js → _listMas.js}

@@ -5,7 +5,7 @@
 
 import restaf from '@sassoftware/restaf';
 
-async function _listModels(params) {
+async function _listMas(params) {
   let { limit, start , name, _appContext} = params;;
   // setup
 
@@ -27,9 +27,9 @@ async function _listModels(params) {
     }
     let result = await store.apiCall(microanalyticScore.links('modules'), payload);
     if (result.itemsList().size === 0) {
-      return { content: [{ type: 'text', text: `No models exist in MAS server` }]};
+      return { content: [{ type: 'text', text: `No MAS exist in MAS server` }]};
     }
-    let list = {models: result.itemsList().toJS()};
+    let list = {mas: result.itemsList().toJS()};
     return { content: [{ type: 'text', text: JSON.stringify(list) }],
       structuredContent: list
     };
@@ -38,4 +38,4 @@ async function _listModels(params) {
   }
 }
 
-export default _listModels;
+export default _listMas;

package/src/toolSet/findJobdef.js

@@ -3,7 +3,7 @@
  * SPDX-License-Identifier: Apache-2.0
  */
 import { z } from 'zod';
-import _findJobdeg from '../toolHelpers/_findJobdef.js';
+import _findJobdef from '../toolHelpers/_findJobdef.js';
 function findJobdef(_appContext) {
   let llmDescription= {
   "purpose": "Map natural language requests to find a jobdef (job definition) in SAS Viya and return structured results.",

package/src/toolSet/findMas.js

@@ -0,0 +1,59 @@
+/*
+ * Copyright © 2025, SAS Institute Inc., Cary, NC, USA.  All Rights Reserved.
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { z } from 'zod';
+import _findmas from '../toolHelpers/_findmas.js';
+
+
+function findMas(_appContext) {
+  let description = `
+find-mas — locate a specific MAS mas deployed to MAS server 
+
+USE when: find mas, does mas exist, is mas deployed, lookup mas, verify mas exists
+DO NOT USE for: list mass (use list-mass), mas info/variables (use mas-info), score mas (use mas-score), find table/job/lib (use respective tools), scr mass (use scr-info/scr-score)
+
+PARAMETERS
+- name: string (required) — mas name to locate; if multiple supplied, use first
+
+ROUTING RULES
+- "find mas <name>" → { name: "<name>" }
+- "does mas <name> exist" → { name: "<name>" }
+- "is mas <name> deployed" → { name: "<name>" }
+- "lookup/verify mas <name>" → { name: "<name>" }
+- "find mas" with no name → ask "Which mas name would you like to find?"
+- "find all mass / list mass" → use list-mass instead
+- "describe mas / mas info" → use mas-info instead
+
+EXAMPLES
+- "find mas mymas" → { name: "mymas" }
+- "does mas churn_score exist" → { name: "churn_score" }
+- "is mas riskmas deployed" → { name: "riskmas" }
+- "lookup mas claims_fraud_v1" → { name: "claims_fraud_v1" }
+
+NEGATIVE EXAMPLES (do not route here)
+- "list mass" (use list-mass)
+- "score mas mymas" (use mas-score)
+- "mas info for churnRisk" (use mas-info)
+
+ERRORS
+Returns { mass: [] } if not found; { mass: [name, ...] } if found. Never hallucinate mas names.
+  `;
+
+  let spec = {
+    name: 'find-mas',
+    description: description,
+    inputSchema: z.object({
+      name: z.string()
+    }),
+    handler: async (params) => { 
+      let r = await _findmas(params);
+      return r;
+    }
+  }
+  return spec;
+}
+
+export default findMas;
+

package/src/toolSet/{listModels.js → listMas.js}

@@ -4,14 +4,14 @@
  */
 
 import { z } from 'zod';
-import _listModels from '../toolHelpers/_listModels.js';
+import _listMas from '../toolHelpers/_listMas.js';
 
-function listModels(_appContext) {
+function listMas(_appContext) {
   let description = `
-list-models — enumerate models published to MAS.
+list-mas — enumerate models published to MAS.
 
-USE when: list models, show models, browse models, next page
-DO NOT USE for: find model, model metadata, score model, list jobs/tables/libraries
+USE when: list models, show models, list mas, show mas next page
+DO NOT USE for: find model, find mas, model metadata, score model, list jobs/tables/libraries
 
 PARAMETERS
 - limit: number (default: 10) — page size
@@ -21,10 +21,15 @@ ROUTING RULES
 - "list models" → { start:1, limit:10 }
 - "list 25 models" → { start:1, limit:25 }
 - "next models" → { start: start+limit, limit:10 }
+- "list mas" → { start:1, limit:10 }
+- "list 25 mas" → { start:1, limit:25 }
+- "next mas" → { start: start+limit, limit:10 }
 
 EXAMPLES
 - "list models" → { start:1, limit:10 }
 - "list 25 models" → { start:1, limit:25 }
+- "list mas" → { start:1, limit:10 }
+- "list 25 mas" → { start:1, limit:25 }
 
 NEGATIVE EXAMPLES (do not route here)
 - "find model X" (use find-model)
@@ -37,14 +42,14 @@ Returns empty array if no models found.
   `;
 
   let spec = {
-    name: 'list-models',
+    name: 'list-mas',
     description: description,
     inputSchema: z.object({
       limit: z.number().optional(),
       start: z.number().optional()
     }),
     handler: async (params) => { 
-      let r  = await _listModels(params);
+      let r  = await _listMas(params);
       return r;
     }
   }
@@ -52,5 +57,5 @@ Returns empty array if no models found.
   return spec;
 }
 
-export default listModels;
+export default listMas;
 

package/src/toolSet/makeTools.js

@@ -3,22 +3,28 @@
  * SPDX-License-Identifier: Apache-2.0
  */
 
-import listModels from './listModels.js';
-import listTables from './listTables.js';
-import modelScore from './modelScore.js';
-import modelInfo from './modelInfo.js';
+import listMas from './listMas.js';
+
+
+import masScore from './masScore.js';
+import masInfo from './masInfo.js';
+import findMas from './findMas.js';
+
 import findLibrary from './findLibrary.js';
-import readTable from './readTable.js';
-import tableInfo from './tableInfo.js';
 import listLibraries from './listLibraries.js';
 
+import listTables from './listTables.js';
+import findTable from './findTable.js';
+import tableInfo from './tableInfo.js';
+import readTable from './readTable.js';
+
 import scrInfo from './scrInfo.js';
 import scrScore from './scrScore.js';
 
 import devaScore from './devaScore.js';
 
-import findTable from './findTable.js';
-import findModel from './findModel.js';
+
+
 import runProgram from './runProgram.js';
 import runMacro from './runMacro.js';
 import runJob from './runJob.js';
@@ -40,11 +46,11 @@ function makeTools(_appContext) {
 
   // get the tool definitions and handler 
   let list = [
-    listModels(_appContext),
+    listMas(_appContext),
     
-    findModel(_appContext),
-    modelInfo(_appContext),
-    modelScore(_appContext),
+    findMas(_appContext),
+    masInfo(_appContext),
+    masScore(_appContext),
 
     scrInfo(_appContext),
     scrScore(_appContext),

package/src/toolSet/{modelInfo.js → masInfo.js}

@@ -8,9 +8,9 @@ import debug from 'debug';
 import _masDescribe from '../toolHelpers/_masDescribe.js';
 const log = debug('tools');
 
-function modelInfo(_appContext) {
+function masInfo(_appContext) {
   let description = `
-model-info — return detailed information about a specific MAS model, including its inputs, outputs, and metadata.
+mas-info — return detailed information about a specific MAS model, including its inputs, outputs, and metadata.
 
 USE when: what inputs does model need, describe model, show variables for model, model inputs/outputs
 DO NOT USE for: find model, list models, score model, table/job operations
@@ -19,26 +19,26 @@ PARAMETERS
 - model: string — model name (required, exact match)
 
 ROUTING RULES
-- "what inputs does model X need?" → { model: "X" }
-- "describe model Y" → { model: "Y" }
-- "show variables for Z" → { model: "Z" }
+- "what inputs does mas X need?" → { model: "X" }
+- "describe mas Y" → { model: "Y" }
+- "show variables for mas Z" → { model: "Z" }
 
 EXAMPLES
-- "What inputs does model churnRisk need?" → { model: "churnRisk" }
-- "Describe model creditScore" → { model: "creditScore" }
+- "What inputs does mas churnRisk need?" → { model: "churnRisk" }
+- "Describe mas creditScore" → { model: "creditScore" }
 - "Show variables for myModel" → { model: "myModel" }
 
 NEGATIVE EXAMPLES (do not route here)
-- "list models" (use list-models)
-- "find model X" (use find-model)
-- "score with model X" (use model-score)
+- "list mas" (use list-models)
+- "find mas X" (use find-model)
+- "score with mas X" (use model-score)
 
 ERRORS
 Returns model metadata: inputs (name, type, role), outputs (name, type, possible_values), model_type, description.
   `;
 
   let spec = {
-    name: 'model-info',
+    name: 'mas-info',
     description: description,
     inputSchema: z.object({
       model: z.string()
@@ -51,5 +51,5 @@ Returns model metadata: inputs (name, type, role), outputs (name, type, possible
   return spec;
 }
 
-export default modelInfo;
+export default masInfo;
 

package/src/toolSet/{modelScore.js → masScore.js}

@@ -8,7 +8,7 @@ import debug from 'debug';
 import _masScoring from '../toolHelpers/_masScoring.js';
 const log = debug('tools');
 
-function modelScore(_appContext) {
+function masScore(_appContext) {
   let description = `
 mas-score — score data using a deployed model on MAS.
 
@@ -74,7 +74,7 @@ Returns predictions, probabilities, scores merged with input data. Returns error
         params.model = params.model.substring(0, params.model.lastIndexOf('.'));
       }
   
-      log('modelScore params', params);
+      log('masScore params', params);
       // Check if the params.scenario is a string and parse it
       let r = await _masScoring(params)
       return r;
@@ -83,5 +83,5 @@ Returns predictions, probabilities, scores merged with input data. Returns error
   return spec;
 }
 
-export default modelScore;
+export default masScore;
 

package/src/toolHelpers/_findModel.js

@@ -1,12 +0,0 @@
-/*
- * Copyright © 2025, SAS Institute Inc., Cary, NC, USA.  All Rights Reserved.
- * SPDX-License-Identifier: Apache-2.0
- */
-
-import _listModels from './_listModels.js';  
-async function _findModel(params) {
-    let r = await _listModels(params);
-    console.log ("findModel result:" , r);
-    return r;
-}
-export default _findModel;

package/src/toolSet/findModel.js

@@ -1,60 +0,0 @@
-/*
- * Copyright © 2025, SAS Institute Inc., Cary, NC, USA.  All Rights Reserved.
- * SPDX-License-Identifier: Apache-2.0
- */
-
-import { z } from 'zod';
-import _findModel from '../toolHelpers/_findModel.js';
-
-
-function findModel(_appContext) {
-  let description = `
-find-model — locate a specific MAS model deployed to MAS server 
-
-USE when: find model, does model exist, is model deployed, lookup model, verify model exists
-DO NOT USE for: list models (use list-models), model info/variables (use model-info), score model (use model-score), find table/job/lib (use respective tools), scr models (use scr-info/scr-score)
-
-PARAMETERS
-- name: string (required) — model name to locate; if multiple supplied, use first
-
-ROUTING RULES
-- "find model <name>" → { name: "<name>" }
-- "does model <name> exist" → { name: "<name>" }
-- "is model <name> deployed" → { name: "<name>" }
-- "lookup/verify model <name>" → { name: "<name>" }
-- "find model" with no name → ask "Which model name would you like to find?"
-- "find all models / list models" → use list-models instead
-- "score model <name>" → use model-score instead
-- "describe model / model info" → use model-info instead
-
-EXAMPLES
-- "find model myModel" → { name: "myModel" }
-- "does model churn_score exist" → { name: "churn_score" }
-- "is model riskModel deployed" → { name: "riskModel" }
-- "lookup model claims_fraud_v1" → { name: "claims_fraud_v1" }
-
-NEGATIVE EXAMPLES (do not route here)
-- "list models" (use list-models)
-- "score model myModel" (use model-score)
-- "model info for churnRisk" (use model-info)
-
-ERRORS
-Returns { models: [] } if not found; { models: [name, ...] } if found. Never hallucinate model names.
-  `;
-
-  let spec = {
-    name: 'find-model',
-    description: description,
-    inputSchema: z.object({
-      name: z.string()
-    }),
-    handler: async (params) => { 
-      let r = await _findModel(params);
-      return r;
-    }
-  }
-  return spec;
-}
-
-export default findModel;
-