Enables AI agents to directly manipulate Jupyter Notebook cells and structure through a secure, well-defined API, overcoming Cursor's AI agent mode limitations.
An MCP server that lets AI models run code in 31 languages, evaluate symbolic math and logic problems, and measure complexity—exposed as 48 tools for execution, session management, translation, optimization, and more.
A secure MCP (Model Context Protocol) server hosted on Google Cloud Run that enables team collaboration by providing authenticated access via Google Cloud IAM, allowing teams to share custom MCP servers over the internet before official MCP authentication is implemented.
An auto-generated MCP server for Google's Serverless VPC Access API, enabling communication with Google Cloud VPC networks through natural language interactions.
An MCP Server that enables natural language interaction with the Open Policy Agent REST API, allowing users to manage policies, decisions, and data through conversational interfaces.
An MCP Server that enables users to interact with Google's On-Demand Scanning API (v1beta1) through natural language, likely providing capabilities for vulnerability scanning and security analysis of containers and artifacts.
An MCP server for the VTEX Subscriptions API (v3) that enables managing subscription services through natural language interactions, auto-generated using AG2's MCP builder.
An auto-generated MCP server that enables interaction with the OpenAI API, allowing users to access OpenAI's models and capabilities through the Multi-Agent Conversation Protocol.
An MCP (Multi-Agent Conversation Protocol) Server that enables interaction with Google Workflows API, allowing management of workflow executions and definitions through natural language commands.
Enables agents to interact with the Logflare API by writing JavaScript functions that run in a Vercel Sandbox, using three tools: search, execute_read, and execute_write.
Code-mode MCP server (docs_search + execute_code two-tool surface) backed by a unified capability manifest across three sandbox kernels (in-process node:vm, WASM via QuickJS / Pyodide / Wasmtime, and remote microVM via E2B / Cloudflare Sandbox). At N=30 tools the bootstrap-context cost drops to 13.6% of direct tool-use. Apache-2.0.