diff --git a/README.md b/README.md
index 3b79332b..6ca02a36 100644
--- a/README.md
+++ b/README.md
@@ -1464,6 +1464,7 @@ Persistent memory storage using knowledge graph structures. Enables AI models to
 - [AlekseiMarchenko/central-intelligence](https://github.com/AlekseiMarchenko/central-intelligence) [![central-intelligence MCP server](https://glama.ai/mcp/servers/AlekseiMarchenko/central-intelligence/badges/score.svg)](https://glama.ai/mcp/servers/AlekseiMarchenko/central-intelligence) 📇 ☁️ - Persistent memory for AI agents. Five tools (remember, recall, context, forget, share) with semantic search via vector embeddings and agent/user/org scoping. Works with Claude Code, Cursor, Windsurf, and any MCP client.
 - [epicsagas/alcove](https://github.com/epicsagas/alcove)[![alcove MCP server](https://glama.ai/mcp/servers/epicsagas/alcove/badges/score.svg)](https://glama.ai/mcp/servers/epicsagas/alcove) 🦀 🏠 🍎 🪟 🐧 - MCP server that gives AI coding agents on-demand access to private project docs via BM25 ranked search. One setup for Claude Code, Cursor, Codex, Gemini CLI, and more. Docs stay private, never in public repos.
 - [alibaizhanov/mengram](https://github.com/alibaizhanov/mengram) [![mengram MCP server](https://glama.ai/mcp/servers/@alibaizhanov/mengram/badges/score.svg)](https://glama.ai/mcp/servers/@alibaizhanov/mengram) 🐍 ☁️ 🏠 🍎 🪟 🐧 - Human-like memory layer for AI agents with semantic, episodic, and procedural memory. Claude Code hooks (auto-save, auto-recall, cognitive profile). 29 MCP tools, knowledge graph, smart triggers, multi-user isolation. Python & JS SDKs.
+- [AntonioTF5/soul-mcp-server](https://github.com/AntonioTF5/soul-mcp-server) 📇 🏠 🍎 🪟 🐧 - Validate and generate SOUL.md agent identity files from Claude Desktop. SOUL.md is the open format for persistent AI agent identity — personality, voice, values, and behavioral constraints in a machine-readable YAML file.
 - [apecloud/ApeRAG](https://github.com/apecloud/ApeRAG) 🐍 ☁️ 🏠 - Production-ready RAG platform combining Graph RAG, vector search, and full-text search. Best choice for building your own Knowledge Graph and for Context Engineering
 - [bitatlas-group/bitatlas](https://github.com/bitatlas-group/bitatlas) [![bitatlas MCP server](https://glama.ai/mcp/servers/bitatlas-group/bitatlas/badges/score.svg)](https://glama.ai/mcp/servers/bitatlas-group/bitatlas) 📇 ☁️ - Zero-Knowledge Cloud Drive for Humans and Agents. Client-side AES-256-GCM encryption with 7 MCP tools for encrypted file vault management — upload, download, search, and organize files that the server never sees in plaintext.
 - [besslframework-stack/project-tessera](https://github.com/besslframework-stack/project-tessera) [![project-tessera MCP server](https://glama.ai/mcp/servers/@besslframework-stack/project-tessera/badges/score.svg)](https://glama.ai/mcp/servers/@besslframework-stack/project-tessera) 🐍 🏠 🍎 🪟 🐧 - Local workspace memory for Claude Desktop. Indexes your documents (Markdown, CSV, session logs) into a vector store with hybrid search, cross-session memory, auto-learn, and knowledge graph visualization. Zero external dependencies — fastembed + LanceDB, no Ollama or Docker required. 15 MCP tools.