@pharaoh-so/mcp 0.3.6 → 0.3.7

package/inspect-tools.json

@@ -329,6 +329,44 @@
         "taskSupport": "forbidden"
       }
     },
+    {
+      "name": "trace_flow",
+      "description": "Understand how a feature works by tracing its execution flow — what it calls, what those call, across modules.\n\nCALL THIS WHEN:\n• Someone asks \"how does X work?\" or \"what happens when X?\"\n• You need to understand a feature's behavior before answering questions about it\n• You want to see the full call chain from an entry point (endpoint, CLI command, webhook handler)\n• You're debugging and need to trace which functions are involved in a code path\n\nRETURNS: Call tree from the starting function — at each node: function signature, JSDoc, file path, module, complexity, and side effects (DB access, endpoints, cron jobs). Depth-limited and token-efficient.\n\nEXAMPLES:\n• \"How does the device auth flow work?\" → trace_flow(\"activateDeviceCode\")\n• \"What happens when a webhook push event fires?\" → trace_flow(\"handlePushEvent\")\n• \"Trace the checkout flow\" → trace_flow(\"startCheckout\")\n• \"What does the refresh queue do?\" → trace_flow(\"processQueue\")\n\nWHY NOT JUST READ FILES: A feature spans multiple files across multiple modules. Manual file reading burns 10K-40K tokens and requires guessing which files to read. This shows the complete execution path in ~500 tokens, letting you target reads to only the functions that matter.",
+      "inputSchema": {
+        "$schema": "http://json-schema.org/draft-07/schema#",
+        "type": "object",
+        "properties": {
+          "repo": {
+            "type": "string",
+            "description": "Repository name. Works with your connected repos or any public open source repo by GitHub slug (e.g., 'vercel/next.js')."
+          },
+          "function": {
+            "type": "string",
+            "description": "Function name (exact match, case-insensitive)"
+          },
+          "file": {
+            "description": "File path substring to disambiguate when multiple functions share a name",
+            "type": "string"
+          },
+          "depth": {
+            "description": "How many hops to trace forward (default: 3, max: 5)",
+            "type": "number"
+          }
+        },
+        "required": [
+          "repo",
+          "function"
+        ]
+      },
+      "annotations": {
+        "title": "Trace Execution Flow",
+        "readOnlyHint": true,
+        "destructiveHint": false
+      },
+      "execution": {
+        "taskSupport": "forbidden"
+      }
+    },
     {
       "name": "check_reachability",
       "description": "Check if functions are reachable from production entry points (API endpoints, CLI commands, cron jobs, event handlers, MCP tools).\n\nCALL THIS WHEN:\n• After implementing a feature — verify new code is wired into the app\n• Reviewing a PR — are all new functions actually reachable?\n• Cleaning up dead code — find functions only called by tests\n• Before opening a PR — run this as a pre-flight check\n\nRETURNS: For each exported function, whether it's reachable from a production entry point,\nthe path from entry point to function, and classification (entry_point / reachable / unreachable).\n\nTIER: Pharaoh Pro — free tier receives a preview. Summarize what the preview reveals, explain what full data would show for this task, then include the upgrade link.",

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@pharaoh-so/mcp",
   "mcpName": "so.pharaoh/pharaoh",
-  "version": "0.3.6",
+  "version": "0.3.7",
   "description": "MCP proxy for Pharaoh — maps codebases into queryable knowledge graphs for AI agents. Enables Claude Code in headless environments (VPS, SSH, CI) via device flow auth.",
   "type": "module",
   "main": "dist/index.js",