OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
MCP & Tooling

Proxima

Proxima is a local developer platform that combines an MCP server exposing AI and coding tools to compatible development environments with a separate Python agent for software debugging and browser automation.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Proxima — OpenViST project profile in MCP & Tooling.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Proxima when you want to expose AI and developer tools to an MCP-compatible coding environment, or when you need its separate Python agent for local coding and browser-automation workflows.

Who it is for

  • Developers who want AI model and coding tools available in an MCP-compatible IDE.
  • Developers who want a separate local Python agent for code repair, test verification, or browser automation.

Documented uses

  • Connect AI model queries and developer tools to a compatible coding environment through MCP.
  • Search the web, generate or review code, and compare or route queries across models.
  • Run a local coding agent for debugging, test workflows, and Chrome DevTools-based browser automation.
Before you choose

Requirements & limits

The site describes Proxima as free and open-source. Its About page says centralized accounts are not needed. Node.js 18+ is required for the core hub, MCP server, and CLI; Python 3.10+ is required for the autonomous agent. Windows has a standalone installer, while macOS and Linux use a source build.

  • The MCP server and Python agent are separate components; the agent requires Python 3.10 or later in addition to the Node.js requirement for the core.
  • The MCP server must be configured in the coding host; the documentation describes a settings-based configuration option in the desktop app.
  • Model access can use browser-session routing, provider APIs with locally encrypted keys, or offline local-model software. These are distinct connection modes.
  • The agent's Auto, Smart, and Suggest modes provide different levels of execution autonomy and developer approval.
  • The documented Windows setup uses a standalone installer; macOS and Linux setup is described as a source build.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up Proxima from source and configure an IDE MCP server

Install Proxima from its repository and add its MCP server to an AI coding app.

Before you start

  • Node.js 18 or later.
  • Python 3.10 or later for the Autonomous Agent runtime.
  • The Proxima repository: https://github.com/Zen4-bit/Proxima.
  • An AI coding app with MCP configuration support.

Steps

  1. Clone the Proxima repository and change into its directory.

  2. Install Node dependencies with the command below, then start the Electron Hub with the command below.

    Documented command
    npm install
    Documented command
    npm start

  3. In proxima-agent, create and activate a Python virtual environment, install dependencies from requirements.txt, and start the agent with the command below.

    Documented command
    python main.py

  4. Add an MCP server entry to the IDE configuration using node as the command and the path to proxima/src/mcp/index.js as its argument. The desktop app’s Settings tab can provide pre-filled configuration JSON.

Expected outcome

Proxima’s desktop hub and Python agent are started, and the IDE is configured to launch Proxima’s MCP server.

Guide limitations

  • The source-build instructions require the stated Node.js and Python versions.
  • The documented MCP configuration uses a path placeholder; it must be replaced with the local path.
  • This recipe covers setup and configuration, not a verified IDE connection or tool execution.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for AI coding assistance

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
ProximaConnect AI model queries and developer tools to a compatible coding environment through MCP.Windows, macOS, Linux, CLI, Self-hosted, ServerThe site describes Proxima as free and open-source. Its About page says centralized accounts are not needed. Node.js 18+ is required for the core hub, MCP server, and CLI; Python 3.10+ is required for the autonomous agent. Windows has a standalone installer, while macOS and Linux use a source build.
OvertureInspect a coding agent’s planned steps and branches before code is written.Self-hosted, Server, WebOpen-source software under the MIT license. The documented setup runs the MCP server locally and opens its web interface at `http://localhost:3031` by default.
WigoloSearch the web and fetch pages for an agent’s research task.CLI, Self-hosted, ServerThe quickstart lists macOS, Linux and Windows, and requires Node.js 20 or later with about 1.5 GB of free disk space. The repository labels the project public beta.
Evidence and transparency

Sources & review

proximamcp.in ↗Guide documentation ↗
Source record details
Source availability
Active
Sources checked
23 October 2026
Original website title
Proxima - Unified Multi-AI MCP Server & Local Agent · Official homepage title · retained in its source language
How we review sourcesSuggest a correction