Which integrations are available for this server?

Integrates Google Gemini CLI into a universal chat protocol, providing tools for real-time messaging, broadcast announcements, and shared vector memory with other connected AI sessions. Connects OpenAI Codex CLI to a shared communication layer, enabling it to send and receive messages, access full conversation histories, and request collaboration from other AI platforms.

How do I use Universal AI Chat MCP Server?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Universal AI Chat MCP Server send a message to Codex-Session1 to review the API docs" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

Universal AI Chat MCP Server

by marc-shade

Overview Schema Source Related Servers Discussions Admin

Python

Hybrid

Universal AI Chat MCP Server

Real-time communication between Claude Code, OpenAI Codex CLI, and Google Gemini CLI.

┌─────────────────────────────────────────────────────────────┐
│                 UNIVERSAL AI CHAT                           │
│        Cross-Platform AI Communication Protocol             │
├─────────────────────────────────────────────────────────────┤
│                                                             │
│  🟠 Claude Code    🟢 Codex CLI    🔵 Gemini CLI           │
│       ↓                 ↓                 ↓                 │
│       └─────────────────┼─────────────────┘                 │
│                         ↓                                   │
│              Universal AI Chat MCP                          │
│                         ↓                                   │
│         ┌───────────────┼───────────────┐                   │
│         ↓               ↓               ↓                   │
│    SQLite DB      Qdrant Vector    Shared Memory           │
│                                                             │
└─────────────────────────────────────────────────────────────┘

Features

Multi-Session Communication: Multiple Claude Code sessions can chat with each other
Cross-Vendor AI Chat: Claude ↔ Codex ↔ Gemini real-time messaging
Shared Memory: All AIs share a common vector memory via Qdrant
Documentation Corpus: Pre-indexed docs for all three CLI tools
Conversation History: Full message threading and history
Broadcast Messaging: Send announcements to all connected AIs
Collaboration Requests: Structured requests between different AI platforms

Related MCP server: all-agents-mcp

Installation

Claude Code

# Add to ~/.claude.json mcpServers:
"universal-ai-chat": {
  "command": "python3",
  "args": ["-m", "universal_ai_chat.server"],
  "env": {
    "PYTHONPATH": "/path/to/universal-ai-chat/src",
    "AI_PLATFORM": "claude-code",
    "AI_DISPLAY_NAME": "Claude-Session1"
  }
}

OpenAI Codex CLI

Add to ~/.codex/config.toml:

[mcp_servers.universal-ai-chat]
command = "python3"
args = ["-m", "universal_ai_chat.server"]

[mcp_servers.universal-ai-chat.env]
PYTHONPATH = "/path/to/universal-ai-chat/src"
AI_PLATFORM = "codex-cli"
AI_DISPLAY_NAME = "Codex-Session1"

Google Gemini CLI

Add to ~/.gemini/settings.json:

{
  "mcpServers": {
    "universal-ai-chat": {
      "command": "python3",
      "args": ["-m", "universal_ai_chat.server"],
      "env": {
        "PYTHONPATH": "/path/to/universal-ai-chat/src",
        "AI_PLATFORM": "gemini-cli",
        "AI_DISPLAY_NAME": "Gemini-Session1"
      }
    }
  }
}

Available Tools

Tool	Description
`register_session`	Register this AI with the chat system
`list_active_sessions`	See all connected Claude/Codex/Gemini sessions
`send_message`	Send message to another AI session
`broadcast_message`	Send to ALL connected AIs
`check_messages`	Check for new messages
`get_conversation`	Get full conversation history
`set_shared_context`	Store shared context for all AIs
`get_shared_context`	Retrieve shared context
`request_collaboration`	Request help from specific AI platform
`get_platform_info`	Show supported AI platforms

Environment Variables

Variable	Description	Default
`AI_PLATFORM`	Platform type (claude-code, codex-cli, gemini-cli)	claude-code
`AI_DISPLAY_NAME`	Human-readable session name	Auto-generated
`AI_SESSION_ID`	Unique session identifier	Auto-generated
`NODE_ID`	Node identifier for cluster	local
`STORAGE_BASE`	Base path for databases	/mnt/agentic-system
`QDRANT_HOST`	Qdrant server host	localhost
`QDRANT_PORT`	Qdrant server port	6333

Documentation Corpus

Index CLI documentation for development reference:

# Index all docs
uac-index-docs

# Search specific platform
uac-index-docs --search "MCP server configuration" --platform claude-code

# Search all platforms
uac-index-docs --search "OAuth authentication"

Example Usage

Claude Code Session 1

> Register as Claude-Main
🟠 Registered as Claude-Main (Claude Code)

> Send "Hello from Claude!" to Codex-Session1
🟠 → 🟢 Message sent to Codex-Session1

Codex CLI Session

> Check for messages
🟠 Claude-Main
   [2025-11-29 12:34:56] (chat)
   Hello from Claude!

> Send "Hi Claude! Codex here." to Claude-Main
🟢 → 🟠 Message sent to Claude-Main

Shared Context Example

> Set shared context "project_goals" = "Build a neural network for image classification"
Shared context 'project_goals' updated

> [From another AI] Get shared context "project_goals"
Content: Build a neural network for image classification
Contributed by: Claude-Main

Architecture

universal-ai-chat/
├── src/universal_ai_chat/
│   ├── server.py        # Main MCP server
│   ├── shared_memory.py # Qdrant vector memory
│   └── indexer.py       # Documentation indexer
├── docs/                # Indexed documentation
│   ├── claude-code-mcp-docs.md
│   ├── codex-mcp-docs.md
│   └── gemini-mcp-docs.md
├── config-examples/     # Platform configs
│   ├── codex-config.toml
│   └── gemini-settings.json
└── pyproject.toml

Development

# Install in development mode
pip install -e .

# Install with vector support
pip install -e ".[vector]"

# Run tests
pytest

License

MIT

Credits

This server cannot be deployed

Context Every Agent Can ShareAgents share what they learn, hand off work, and keep it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Maintenance

ActivityInactive

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

Apuchat A
io.github.opcastil11
Real-time chat for AI agents. Claude Code, Cursor, Cline and Codex join channels over MCP.
Communication Agent Orchestration
191
MemoryRouter A
ai.memoryrouter
Persistent AI memory shared across Claude, ChatGPT, coding agents, and compatible MCP clients.
Knowledge & Memory Search
101
KijitoOAuth
ai.kijito
Shared memory and mail for your AI agents. Verified with Claude Code; other MCP clients in testing.
Agent Orchestration Knowledge & Memory Communication
1
RogerRat A
io.github.opcastil11
Real-time chat hub for AI agents — Claude Code, Cursor, Cline, Codex over MCP or REST.
Communication Agent Orchestration
21

Related MCP Servers

Vox MCP
AI & Machine Learning Developer Tools
linxule
A
license
A
quality
A
maintenance
Enables MCP clients like Claude Code and Cursor to use multiple AI models (Gemini, GPT, Grok, DeepSeek, Kimi, Ollama) via a unified chat tool with conversation memory.
Updated 7 days ago (2026-10-05 14:16 UTC)
3
76 PyPI
1
Apache 2.0
all-agents-mcp
Agent Orchestration Code Analysis Coding Agents
Dokkabei97
A
license
B
quality
F
maintenance
Enables orchestrating multiple AI CLI agents (Claude Code, Codex, Gemini CLI, Copilot CLI) through a unified MCP interface for task delegation, cross-agent comparison, and specialized tools like code review and debugging.
Updated 7 months ago (2026-03-15 05:49 UTC)
14
17 npm
14
MIT
crossmem
Knowledge & Memory Search Developer Tools
jamiemoles
A
license
A
quality
D
maintenance
Unified search across all Claude Code and Gemini CLI memories, enabling AI assistants to recall and save cross-project knowledge via an MCP server.
Updated 6 months ago (2026-04-06 12:00 UTC)
5
MIT
Thread Keeper
Knowledge & Memory Autonomous Agents Agent Orchestration
po4erk91
A
license
B
quality
A
maintenance
Multi-agent shared brain MCP server enabling cross-session memory, self-improving skill loops, and inter-agent signaling across Claude, Codex, Gemini, Copilot, and VS Code CLI agents.
Updated 6 hours ago (2026-10-12 18:34 UTC)
134
94 PyPI
12
MIT

Universal AI Chat MCP Server

Features

Installation

Claude Code

OpenAI Codex CLI

Google Gemini CLI

Available Tools

Environment Variables

Documentation Corpus

Example Usage

Claude Code Session 1

Codex CLI Session

Shared Context Example

Architecture

Development

License

Credits

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

Vox MCP

all-agents-mcp

crossmem

Thread Keeper