diff --git a/README.md b/README.md
index b65fd0ec6..b02a423b8 100644
--- a/README.md
+++ b/README.md
@@ -705,11 +705,11 @@ Code execution servers. Allow LLMs to execute code in a secure environment, e.g.
 - [telleroutlook/agentkit-js/mcp-server](https://github.com/telleroutlook/agentkit-js/tree/main/packages/mcp-server) [![telleroutlook/agentkit-js MCP server](https://glama.ai/mcp/servers/telleroutlook/agentkit-js/badges/score.svg)](https://glama.ai/mcp/servers/telleroutlook/agentkit-js) 📇 ☁️ 🏠 🐧 🍎 🪟 – Code-mode MCP server: collapses N user-defined tools into a two-tool surface (`execute_code` + `docs_search`). Backed by a unified capability manifest (`allowedHosts` / `cpuMs` / `memoryLimitBytes`) honoured across three sandbox kernels — in-process node:vm, WASM (QuickJS / Pyodide / Wasmtime), and remote microVM (E2B / Cloudflare Sandbox). Token-saving benchmark in repo CI.
 - [The-40-Thieves/codecalc](https://github.com/The-40-Thieves/codecalc) [![The-40-Thieves/codecalc MCP server](https://glama.ai/mcp/servers/The-40-Thieves/codecalc/badges/score.svg)](https://glama.ai/mcp/servers/The-40-Thieves/codecalc) 🐍 🏠 🍎 🪟 🐧 - Offline-core code & logic calculator for AI agents — run code in 31 languages, exact symbolic math, SMT/logic, complexity analysis, and cross-language/optimization verification, with an opt-in strict gVisor/AppContainer sandbox for untrusted code.
 - [yepcode/mcp-server-js](https://github.com/yepcode/mcp-server-js) 🎖️ 📇 ☁️ - Execute any LLM-generated code in a secure and scalable sandbox environment and create your own MCP tools using JavaScript or Python, with full support for NPM and PyPI packages
-
 ### 🤖 <a name="coding-agents"></a>Coding Agents
 
 Full coding agents that enable LLMs to read, edit, and execute code and solve general programming tasks completely autonomously.
 
+- [abnegate/magents](https://github.com/abnegate/magents) [![abnegate/magents MCP server](https://glama.ai/mcp/servers/abnegate/magents/badges/score.svg)](https://glama.ai/mcp/servers/abnegate/magents) 🦀 🏠 🍎 🐧 - Shared session bus for Claude Code, Codex, Cursor, Grok, and friends: MCP + CLI to list/read/handoff/send/spawn across live agent sessions. Install: `brew install abnegate/tap/magents`.
 - [5dive-ai/5dive-mcp](https://github.com/5dive-ai/5dive-mcp) [![5dive-mcp MCP server](https://glama.ai/mcp/servers/5dive-ai/5dive-mcp/badges/score.svg)](https://glama.ai/mcp/servers/5dive-ai/5dive-mcp) 📇 🏠 🍎 🪟 🐧 - Manage a 5dive agent fleet from any MCP client: file tasks, message and inspect agents, and read the fleet digest. Thin adapter over the 5dive CLI.
 - [agent-blueprint/mcp-server](https://github.com/agent-blueprint/mcp-server) [![agent-blueprint/mcp-server MCP server](https://glama.ai/mcp/servers/agent-blueprint/mcp-server/badges/score.svg)](https://glama.ai/mcp/servers/agent-blueprint/mcp-server) 📇 ☁️ - 8 MCP tools for exploring and downloading AI agent blueprints. List blueprints, get summaries, download full Agent Skills directories for implementation by coding agents. Vendor-agnostic output works with any enterprise platform. Install: `npx agentblueprint`.
 - [dugubuyan/agent-nexus](https://github.com/dugubuyan/agent-nexus) [![AgentNexus MCP server](https://glama.ai/mcp/servers/dugubuyan/agent-nexus/badges/score.svg)](https://glama.ai/mcp/servers/dugubuyan/agent-nexus) 🐍 🏠 ☁️ — Service-boundary-aware document exchange center for coordinating heterogeneous LLM code agents. Versioned Markdown store, pub-sub notifications, diff-aware updates, and lifecycle stage tracking. Each service registers as a sub-project; agents subscribe to cross-service document changes and receive structured diffs via MCP.