@endiagram/mcp 0.2.14 → 0.2.15

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@endiagram/mcp",
-  "version": "0.2.14",
+  "version": "0.2.15",
   "description": "MCP server for EN Diagram — deterministic structural analysis backed by named theorems",
   "type": "module",
   "main": "dist/index.js",

package/tools.json

@@ -1,5 +1,5 @@
 {
-  "instructions": "EN Diagram is a deterministic structural analysis engine. No AI inside.\n\nTo describe a system, write one statement per line:\n  actor do: action needs: input1, input2 yields: output1, output2\n\nShared names between yields and needs create connections automatically. Multi-word names work fine. Use commas to separate multiple inputs or outputs.\n\nThe engine computes structural truth from the description — the tool outputs are raw mathematical findings. Translate them into the language of the system being analyzed. If analyzing a payment flow, say 'the payment gateway is structurally isolated' not 'node X has high centrality'. Speak in the user's domain, not in graph theory.\n\nEvery tool output contains node names, values, and structural properties that can be fed directly into other tools. Read the output. Find the surprising node, the unexpected value, the structural anomaly. Then pick the tool that investigates THAT specific finding. One tool surfaces a fact. The next tool explains it. The next stress-tests it. Keep narrowing until you reach the root cause. One thread followed to completion beats ten shallow observations.\n\nDo not stop at one tool call. Do not summarize after one result. The first call reveals the structure — the real insight comes from the second, third, fourth call that digs into what the first one found.\n\nIMPORTANT: Load ALL tool descriptions before starting analysis. Each tool's description explains how to read its output — without that context, results are uninterpretable. The 13 tools are: analyze, detail, categorize, distance, diff, trace, between, extract, impact, evolve, compose, conserve, render. Speak in the user's domain, not in graph theory. Only call render when the user explicitly asks to visualize.",
+  "instructions": "EN Diagram is a deterministic structural analysis engine. No AI inside.\n\nTo describe a system, write one statement per line:\n  actor do: action needs: input1, input2 yields: output1, output2\n\nShared names between yields and needs create connections automatically. Multi-word names work fine. Use commas to separate multiple inputs or outputs.\n\nThe engine computes structural truth from the description — the tool outputs are raw mathematical findings. Translate them into the language of the system being analyzed. If analyzing a payment flow, say 'the payment gateway is structurally isolated' not 'node X has high centrality'. Speak in the user's domain, not in graph theory.\n\nEvery tool output contains node names, values, and structural properties that can be fed directly into other tools. Read the output. Find the surprising node, the unexpected value, the structural anomaly. Then pick the tool that investigates THAT specific finding. One tool surfaces a fact. The next tool explains it. The next stress-tests it. Keep narrowing until you reach the root cause. One thread followed to completion beats ten shallow observations.\n\nDo not stop at one tool call. Do not summarize after one result. The first call reveals the structure — the real insight comes from the second, third, fourth call that digs into what the first one found.\n\nSpeak in the user's domain, not in graph theory. Only call render when the user explicitly asks to visualize.",
   "tools": [
     {
       "name": "analyze",