refactor(marketplace): align institutional copy and harden MCP contract v2.3.0

- server.json: description updated to official copy (no technical jargon)
- smithery.yaml: displayName + description aligned to institutional messaging
- Both files: 0 forbidden claims, valid JSON/YAML, auth headers confirmed
- Integrity tests: 7/7 PASS (claims, auth, schema, JSON, YAML, endpoint, version)

Author: Ismael Marchi

server.json

@@ -2,7 +2,7 @@
   "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
   "name": "io.github.SynapseLayer/synapse-layer",
   "title": "Synapse Layer — Persistent Memory Infrastructure",
-  "description": "Persistent encrypted memory for AI agents. AES-256-GCM at rest, PII redaction, HMAC-SHA-256 integrity. Server never sees plaintext.",
+  "description": "Persistent memory infrastructure for AI agents — encrypted, governed, and cross-agent. Server never sees plaintext.",
   "version": "2.3.0",
   "websiteUrl": "https://synapselayer.org",
   "repository": {

smithery.yaml

@@ -1,10 +1,8 @@
 qualifiedName: "@synapselayer/synapse-protocol"
-displayName: "Synapse Layer — Persistent Memory for AI Agents"
+displayName: "Synapse Layer — Persistent Memory Infrastructure"
 description: >
-  Persistent, encrypted memory infrastructure for AI agents.
-  Store, recall and transfer context across models via MCP.
-  AES-256-GCM encryption, PII redaction, TRUTH QUOTIENT™ scoring.
-  Server never sees plaintext. Works in 30 seconds.
+  Persistent memory infrastructure for AI agents — encrypted,
+  governed, and cross-agent. Server never sees plaintext.
 version: "2.3.0"
 icon: "🧠"
 sourceUrl: "https://github.com/SynapseLayer/synapse-layer"