Add @agentkit-js/mcp-server to Code Execution

README.md

@@ -495,6 +495,7 @@ Code execution servers. Allow LLMs to execute code in a secure environment, e.g.
 - [r33drichards/mcp-js](https://github.com/r33drichards/mcp-js) 🦀 🏠 🐧 🍎 - A Javascript code execution sandbox that uses v8 to isolate code to run AI generated javascript locally without fear. Supports heap snapshotting for persistent sessions.
 - [rikarazome/prolog-reasoner](https://github.com/rikarazome/prolog-reasoner) [![rikarazome/prolog-reasoner MCP server](https://glama.ai/mcp/servers/rikarazome/prolog-reasoner/badges/score.svg)](https://glama.ai/mcp/servers/rikarazome/prolog-reasoner) 🐍 🏠 🍎 🪟 🐧 - SWI-Prolog execution for LLMs with CLP(FD), negation-as-failure, and recursion. Benchmarked 90% vs 73% LLM-only accuracy on 30 logic problems.
 - [Sowiedu/Edict](https://github.com/Sowiedu/Edict) [![Sowiedu/Edict MCP server](https://glama.ai/mcp/servers/sowiedu/edict/badges/score.svg)](https://glama.ai/mcp/servers/sowiedu/edict) 📇 🏠 – Agent-first programming language: agents produce JSON AST, the compiler validates, type-checks, effect-checks, verifies contracts via Z3/SMT, and compiles to WASM. 19 MCP tools for the full compile-and-execute loop.
+- [telleroutlook/agentkit-js/mcp-server](https://github.com/telleroutlook/agentkit-js/tree/main/packages/mcp-server) 📇 ☁️ 🏠 🐧 🍎 🪟 – 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.
 - [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