Proxima

MCP server · GitHub · ★ 1.2k · graded 2026-10-22Source linked

Multi-AI MCP Server - Connect ChatGPT, Claude, Gemini & Perplexity to your coding tools without any API

No outside reports on file

Proxima's actual security depends heavily on implementation details not clear from the description—verify credential handling, test permissions carefully, and monitor what data flows through each connected service before trusting it with real projects.

Based on public adoption and transparency signals as of Oct 22, 2026. Our opinion, not a code audit or security guarantee.

Was this verdict for Proxima helpful?

What it can access

Local filesNo local folder access notedLOW
Command executionNo shell command runner notedLOW
Network reachConnects to outside service APINOTED
CredentialsNo API token requiredLOW
Package sourceGitHub (Zen4-bit/Proxima)PUBLIC

Inferred from this listing’s public package details and description. Check the project’s source before installing.

Install

No npm or PyPI package is listed. Install from source: github.com/Zen4-bit/Proxima ↗

All setup options ↓

Check this skill Watch it in my stack Compare Add to allowlist README badge View project

About Proxima

Proxima is an MCP (Model Context Protocol) server that lets you connect multiple AI assistants—like ChatGPT, Claude, Gemini, and Perplexity—to your coding tools and local development environment. It aims to do this without requiring individual API keys for each service.

Who it’s for

Developers who want to use multiple AI assistants together with their coding setup. People who prefer not to manage separate API credentials for different AI platforms.

Alternatives

Continue.dev: Open-source IDE plugin for multiple AI models with local control
LangChain: Framework for building AI applications with tool integration
OpenRouter: Unified API for accessing many AI models with a single key
Ollama: Run open-source AI models locally without external APIs

Setup

Check these steps against the project’s own instructions before running anything.

Follow the project's README for installation and configuration instructions. The project is on GitHub at the linked repository, and you should consult its documentation for how to set up the MCP server with your specific AI tools.

Why this grade

CC — Moderate risk signals

Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.

Popularity and upkeep

34/100

GitHub stars: 1.2k
Listing last refreshed: 2026-10-29

These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.

Security reports

No reports found for this package in our research (last checked 2026-10-29).

Check a specific version →

Risks to watch for

Local tool access: Proxima connects AI assistants to your coding environment; if misconfigured, an AI could run unintended commands or access files it shouldn't
Credential handling: The tool claims to work without APIs, but verify how it actually authenticates—unclear methods could leak authentication data
Multi-AI coordination: Routing requests through multiple AI services creates more points where data could be logged, cached, or intercepted
Untrusted input amplification: If one AI's output feeds into another AI, prompt injection attacks could chain and become harder to spot
No clear security audit: With 1,199 GitHub stars but very low adoption metrics (0 npm downloads), the security track record is unknown

How to lower the risk

Least-privilege permissions

Run Proxima with only the file and tool access it actually needs
Don't let it access your entire codebase or secrets folder

Network isolation

Keep Proxima on your local machine or isolated network when possible
Log all outbound requests to see where data goes

Monitoring

Check logs regularly for unexpected AI commands or data access
Watch for requests to services you didn't authorize

Red flags to watch for

Unclear documentation about how credentials are stored or passed
Requests to external URLs you didn't configure
AI assistants suddenly accessing files outside your project

Questions

How do I install Proxima?

Proxima does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/Zen4-bit/Proxima.

Are there security reports about Proxima?

No reports found for this package in our research (last checked 2026-10-29). Proxima currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include local tool access, credential handling, multi-ai coordination.

Is Proxima actively maintained?

Proxima has 1.2k GitHub stars. Our directory data was last refreshed on 2026-10-29. Check recent commit activity, release tags, and open issues at github.com/Zen4-bit/Proxima before pinning it in production.

What are alternatives to Proxima?

Notable alternatives to Proxima include Continue.dev (Open-source IDE plugin for multiple AI models with local control), LangChain (Framework for building AI applications with tool integration), OpenRouter (Unified API for accessing many AI models with a single key), Ollama (Run open-source AI models locally without external APIs). You can also compare Proxima side by side with other MCP servers in the Related tools section on this page.

Maintain or use Proxima? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.

GitHub README Markdown:

markdown

[![AgentArmorHQ Risk Grade for Proxima](https://agentarmorhq.com/api/badge/zen4-bit-proxima)](https://agentarmorhq.com/skills/zen4-bit-proxima)

HTML embed:

html

<a href="https://agentarmorhq.com/skills/zen4-bit-proxima"><img src="https://agentarmorhq.com/api/badge/zen4-bit-proxima" alt="AgentArmorHQ Risk Grade for Proxima" height="20" /></a>

Terminal check:

terminal

curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "zen4-bit-proxima"

Share with your security lead

Need sign-off to use Proxima? Copy this note for Slack, a ticket or a pull request.

### AgentArmorHQ Security Review Memo: Proxima
- **Listing URL:** https://agentarmorhq.com/skills/zen4-bit-proxima
- **Type:** App connector
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 1.2k GitHub stars

#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Connects to outside service API
- **Credentials:** No API token required
- **Package source:** GitHub (Zen4-bit/Proxima)

#### Recommended Hardened Setup
- **Source Repo:** https://github.com/Zen4-bit/Proxima
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.

_Based on public adoption and transparency signals as of Oct 22, 2026. Our opinion, not a code audit or security guarantee._

Key facts

Type: App connector
Publisher: Zen4-bit
Source code: github.com/Zen4-bit/Proxima
Est. context load: ~700 tokens / turn (~4 tool schemas, 0.35% of 200k context)
Popularity: 1.2k GitHub stars
Last updated: 2026-10-29
Last graded: 2026-10-22

Community

Discussions for Proxima

Ask questions or share configuration tips. Governed by our Community Rules & Terms.

No posts match this filter yet.

Be the first to ask a question or share a working tip.

Was this listing for Proxima helpful?

Check before you install, in Claude

Your assistant answers Block, Review or No known issues for any package before it installs it.

Get this check inside Claude