buremba/1mcp
Let your agent write code and execute code directly in the browser with WASM
Compiles and executes TypeScript/JavaScript in a sandboxed QuickJS WASM runtime, allowing agents to chain multiple MCP tool calls into single code blocks that reduce token usage by up to 96%. Exposes only 4 core tools (`run_js`, `read`, `write`, `search`) to the LLM instead of individual MCP endpoints, with session-scoped network, filesystem, and memory policies. Supports browser execution via Worker threads with SSE relay, or backend execution, and integrates directly with Anthropic's AI SDK through `@onemcp/ai-sdk`.
Available on npm.
Stars
34
Forks
5
Language
TypeScript
License
Apache-2.0
Category
Last pushed
Dec 08, 2025
Commits (30d)
0
Dependencies
19
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/mcp/buremba/1mcp"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Kiln-AI/Kilntainers
MCP server to give every agent an ephemeral Linux sandboxes for executing shell commands.
universal-tool-calling-protocol/code-mode
🔌 Plug-and-play library to enable agents to call MCP and UTCP tools via code execution.
gradion-ai/ipybox
Python code execution sandbox with programmatic MCP tool calling (PTC)
BlackSnufkin/LitterBox
A secure sandbox environment for malware developers and red teamers to test payloads against...
ashishgituser/bunkervm
BunkerVM is a tiny operating system that boots in 2 seconds and gives AI agents a safe, isolated...