diff --git a/README.md b/README.md
index 71083478..80d425a7 100644
--- a/README.md
+++ b/README.md
@@ -361,6 +361,7 @@ Code execution servers. Allow LLMs to execute code in a secure environment, e.g.
 - [dagger/container-use](https://github.com/dagger/container-use) 🏎️ 🏠 🐧 🍎 🪟 - Containerized environments for coding agents. Multiple agents can work independently, isolated in fresh containers and git branches. No conflicts, many experiments. Full execution history, terminal access to agent environments, git workflow. Any agent/model/infra stack.
 - [gwbischof/outsource-mcp](https://github.com/gwbischof/outsource-mcp) 🐍 ☁️ - Give your AI assistant its own AI assistants. For example: "Could you ask openai to generate an image of a dog?"
 - [hileamlakB/PRIMS](https://github.com/hileamlakB/PRIMS) 🐍 🏠 – A Python Runtime Interpreter MCP Server that executes user-submitted code in an isolated environment.
+- [mavdol/capsule/mcp-server](https://github.com/mavdol/capsule/tree/main/integrations/mcp-server) ([glama](https://glama.ai/mcp/servers/mavdol/capsule-mcp-server)) 🦀 🏠 🍎 🪟 🐧 - Run untrusted Python/JavaScript code in WebAssembly sandboxes.
 - [ouvreboite/openapi-to-mcp](https://github.com/ouvreboite/openapi-to-mcp) #️⃣ ☁️ - Lightweight MCP server to access any API using their OpenAPI specification. Supports OAuth2 and full JSON schema parameters and request body.
 - [pydantic/pydantic-ai/mcp-run-python](https://github.com/pydantic/pydantic-ai/tree/main/mcp-run-python) 🐍 🏠 - Run Python code in a secure sandbox via MCP tool calls
 - [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.