@mithung/vunet-mcp-server 2.1.1 → 2.2.1

package/README.md

@@ -8,7 +8,7 @@
 
 Query metrics, traces, logs, and data models from your Vunet tenants using natural language through AI assistants like Claude, GitHub Copilot, or any MCP-compatible client.
 
-> **Latest Version:** 2.1.1 - Updated repository URLs, authentication improvements with proxy support.
+> **Latest Version:** 2.2.0 - Added `vunet_fetch_datamodels` tool for live data model discovery from the VuNet API.
 
 ---
 
@@ -135,30 +135,61 @@ If you've cloned the repository:
 ## 📊 Available MCP Tools
 
 ### 1. `vunet_get_status`
-Check authentication status and session validity.
+Check the current connection status and tenant information.
 
 ```
 Example: "Check if Vunet connection is working"
 ```
 
 ### 2. `vunet_list_data_models`
-List all available data models/metrics in the tenant.
+List common Vunet data models organised by category (APM, Infrastructure, Database, Network, etc.).
+
+**Parameters:**
+| Parameter | Required | Description |
+|-----------|----------|-------------|
+| `category` | No | Filter by category: `apm`, `infrastructure`, `database`, `network`, `business`, `all` (default: `all`) |
 
 ```
 Example: "List all available Vunet data models"
+Example: "Show me infrastructure data models in Vunet"
 ```
 
-### 3. `vunet_query_metric`
+### 3. `vunet_fetch_datamodels`
+Fetch the actual **live** DataModels (signals) configured in this VuNet tenant via `/api/vuaccel/datamodel/`. Returns real signal names, types (Metric/Event/Log), data sources, and column details. Use this to discover what data is available before querying with `vunet_query_metric`.
+
+**Parameters:**
+| Parameter | Required | Description |
+|-----------|----------|-------------|
+| `limit` | No | Number of results per page (default: 10, max: 100) |
+| `offset` | No | Pagination offset — records to skip (default: 0) |
+| `search` | No | Search keyword to filter by name (e.g., `UPI`, `CPU`, `transaction`) |
+| `signal_type` | No | Filter by type: `Metric`, `Event`, or `Log` |
+| `ordering` | No | Sort field (e.g., `signal_name`, `-creation_time`) |
+
+```
+Example: "Fetch all live data models from VuNet"
+Example: "Find data models related to UPI in VuNet"
+Example: "List all Event type data models"
+```
+
+### 4. `vunet_query_metric`
 Query a specific metric with time range and filters.
 
 **Parameters:**
 | Parameter | Required | Description |
 |-----------|----------|-------------|
 | `metric_name` | Yes | Name of the data model to query |
-| `relative_time` | No | Time range: `5m`, `15m`, `1h`, `2h`, `1d`, `1w`, `1M` |
-| `start_time` | No | Start epoch timestamp (for absolute range) |
-| `end_time` | No | End epoch timestamp (for absolute range) |
-| `filters` | No | JSON object with field:value filters |
+| `relative_time` | No | Time range: `5m`, `15m`, `1h`, `2h`, `1d`, `1w`, `1M`, `1y` |
+| `start_time` | No | Start epoch timestamp or `now`, `now-1h` (use with `end_time`) |
+| `end_time` | No | End epoch timestamp or `now` (use with `start_time`) |
+| `filters` | No | JSON object with field:value pairs for filtering |
+| `fields` | No | Comma-separated fields to include in response |
+| `exclude_fields` | No | Comma-separated fields to exclude from response |
+| `include_thresholds` | No | Include threshold data in response (default: false) |
+| `format` | No | Response format — use `lama` for Log Analytics format |
+| `compare_intervals` | No | Additional time intervals for comparison (e.g., `1h_ago`, `1d_ago`) |
+| `join_models` | No | Comma-separated additional data models to join |
+| `time_shift` | No | Time shift for comparison (e.g., `1h`, `1d`, `1w`) |
 
 ---
 
@@ -169,34 +200,58 @@ Query a specific metric with time range and filters.
 "Is the Vunet MCP server connected?"
 ```
 
-### List Available Metrics
+### Discover Live Data Models
+```
+"Fetch all available data models from VuNet"
+"Show me all Metric type data models"
+"Find data models related to UPI payments"
+"Search for CPU-related data models in VuNet"
+```
+
+### List Categorised Data Models
 ```
 "What data models are available in Vunet?"
+"Show me infrastructure data models"
+"List all APM data models"
 ```
 
 ### Query Journey Metrics
 ```
 "Show me IBMB Journey Metrics for the last 2 hours"
+"Get UPI Volume data for the last 1 hour"
+"Query CBS TAT metrics for the last 30 minutes"
 ```
 
 ### Query Alerts
 ```
 "Get all critical alerts from the last 1 hour"
+"Show warning alerts with group values for the last 15 minutes"
 ```
 
 ### Query with Filters
 ```
 "Query IBMB Journey Metrics where name equals CBS for the last 30 minutes"
+"Get Linux CPU Utilization filtered by hostname for the last 2 hours"
 ```
 
 ### Infrastructure Monitoring
 ```
 "Show CPU utilization for IBMB servers in the last hour"
+"Get memory utilization for CBS servers in the last 2 hours"
+"Show MSSQL blocking sessions for the last 30 minutes"
 ```
 
 ### RCA Analysis
 ```
 "Get Technical Decline data for IBMB in the last 2 hours"
+"Show RCA root cause data for the last 1 hour"
+"Query RCA lead indicators for the last 4 hours"
+```
+
+### Time Comparison
+```
+"Compare UPI Volume for the last 1 hour vs same time yesterday"
+"Show IBMB TAT with 1-day comparison"
 ```
 
 ---
@@ -277,6 +332,11 @@ npm list -g @mithung/vunet-mcp-server
 
 ## 📄 Changelog
 
+### v2.2.0 (2026-03-18)
+- ✅ Added `vunet_fetch_datamodels` tool — live data model discovery via `/api/vuaccel/datamodel/`
+- ✅ Supports pagination, search, signal type filter, and ordering
+- ✅ Fixed `package.json` bin entries (`npm pkg fix`)
+
 ### v2.1.1 (2026-02-18)
 - ✅ Updated repository URLs to correct GitHub organization
 - ✅ Fixed package metadata

package/index.js

@@ -222,6 +222,42 @@ class VunetMCPServer {
   /**
    * Query a metric/data model
    */
+  /**
+   * Fetch datamodels from the VuNet tenant with pagination and optional search/filter.
+   * Automatically re-authenticates on 401.
+   */
+  async fetchDataModels({ limit = 10, offset = 0, search = "", signal_type = "", ordering = "" } = {}) {
+    await this.ensureAuthenticated();
+
+    const params = new URLSearchParams({ ordering, limit, offset, search });
+    if (signal_type) params.set("signal_type", signal_type);
+
+    const url = `${this.normalizeTenantUrl(this.tenantUrl)}/api/vuaccel/datamodel/?${params.toString()}`;
+
+    try {
+      const response = await axios.get(url, {
+        headers: { Authorization: `Bearer ${this.sessionToken}` },
+        httpsAgent: this.httpsAgent,
+      });
+      return response.data;
+    } catch (error) {
+      if (error.response?.status === 401) {
+        // Token expired — re-authenticate and retry once
+        this.isAuthenticated = false;
+        await this.ensureAuthenticated();
+        const retryResponse = await axios.get(url, {
+          headers: { Authorization: `Bearer ${this.sessionToken}` },
+          httpsAgent: this.httpsAgent,
+        });
+        return retryResponse.data;
+      }
+      const errorDetails = error.response?.data
+        ? JSON.stringify(error.response.data)
+        : error.message;
+      throw new Error(`Failed to fetch datamodels: ${errorDetails}`);
+    }
+  }
+
   async queryMetric(metricName, queryParams) {
     await this.ensureAuthenticated();
 
@@ -355,6 +391,36 @@ class VunetMCPServer {
             },
           },
         },
+        {
+          name: "vunet_fetch_datamodels",
+          description: "Fetch the actual live DataModels (signals) configured in this VuNet tenant by calling /api/vuaccel/datamodel/. Returns real signal names, types (Metric/Event/Log), data sources, and column details. Use this to discover what data is available before querying with vunet_query_metric.",
+          inputSchema: {
+            type: "object",
+            properties: {
+              limit: {
+                type: "number",
+                description: "Number of results to return per page (default: 10, max: 100)",
+              },
+              offset: {
+                type: "number",
+                description: "Pagination offset — number of records to skip (default: 0)",
+              },
+              search: {
+                type: "string",
+                description: "Search keyword to filter data models by name (e.g., 'UPI', 'CPU', 'transaction')",
+              },
+              signal_type: {
+                type: "string",
+                description: "Filter by signal type: 'Metric', 'Event', or 'Log'",
+                enum: ["Metric", "Event", "Log"],
+              },
+              ordering: {
+                type: "string",
+                description: "Field to sort results by (e.g., 'signal_name', '-creation_time')",
+              },
+            },
+          },
+        },
       ],
     }));
 
@@ -373,6 +439,9 @@ class VunetMCPServer {
           case "vunet_list_data_models":
             return await this.handleListDataModels(args);
 
+          case "vunet_fetch_datamodels":
+            return await this.handleFetchDataModels(args);
+
           default:
             throw new Error(`Unknown tool: ${name}`);
         }
@@ -430,8 +499,7 @@ class VunetMCPServer {
     };
   }
 
-  async handleListDataModels(args = {}) {
-    const category = args.category || "all";
+  async handleListDataModels(args = {}) {    const category = args.category || "all";
 
     const dataModels = {
       apm: [
@@ -544,6 +612,44 @@ class VunetMCPServer {
     };
   }
 
+  async handleFetchDataModels(args = {}) {
+    const { limit = 10, offset = 0, search = "", signal_type = "", ordering = "" } = args;
+
+    const data = await this.fetchDataModels({ limit, offset, search, signal_type, ordering });
+
+    // Shape a clean, LLM-friendly summary
+    const models = (data.results || []).map((m) => ({
+      signal_id: m.signal_id,
+      signal_name: m.signal_name,
+      signal_type: m.signal_type,
+      description: m.description || "",
+      sources: m.source_names || [],
+      columns: (m.metric_column_details || []).map((c) => c.column_name || c.name || c),
+      created_by: m.created_by,
+      last_modified: m.last_modified_time,
+    }));
+
+    const result = {
+      tenant: this.tenantUrl,
+      total_count: data.count,
+      returned: models.length,
+      offset,
+      has_more: offset + models.length < data.count,
+      next_offset: offset + models.length < data.count ? offset + models.length : null,
+      tip: "Use signal_name values with the vunet_query_metric tool to fetch actual data.",
+      datamodels: models,
+    };
+
+    return {
+      content: [
+        {
+          type: "text",
+          text: JSON.stringify(result, null, 2),
+        },
+      ],
+    };
+  }
+
   async run() {
     console.error("Vunet MCP Server starting...");
     

package/package.json

@@ -1,12 +1,12 @@
 {
   "name": "@mithung/vunet-mcp-server",
-  "version": "2.1.1",
+  "version": "2.2.1",
   "description": "Model Context Protocol (MCP) Server for Vunet vuSmartMaps - Multi-tenant observability platform integration",
   "main": "index.js",
   "type": "module",
   "bin": {
-    "vunet-mcp": "./cli.js",
-    "@mithung/vunet-mcp-server": "./cli.js"
+    "vunet-mcp": "cli.js",
+    "vunet-mcp-server": "cli.js"
   },
   "scripts": {
     "start": "node index.js",
@@ -42,7 +42,7 @@
   },
   "repository": {
     "type": "git",
-    "url": "https://github.com/mithung-vunet/vunet-mcp-server.git"
+    "url": "git+https://github.com/mithung-vunet/vunet-mcp-server.git"
   },
   "bugs": {
     "url": "https://github.com/mithung-vunet/vunet-mcp-server/issues"