Roundtable AI MCP Server

Stop copy-pasting between AI models. Roundtable AI is a local MCP server that lets your primary AI assistant delegate tasks to specialized models like Gemini, Claude, Codex, and Cursor. Solve complex engineering problems in parallel, directly from your IDE.

$ pip install roundtable-ai

Install in IDEs →

Claude Code

~/my-project

Multi-Agent Debugging Prompt

The user dashboard is randomly slow for enterprise customers.

Use Gemini SubAgent to analyze frontend performance issues in the React components, especially expensive re-renders and inefficient data fetching.

Use Codex SubAgent to examine the backend API endpoint for N+1 queries and database bottlenecks.

Use Claude SubAgent to review the infrastructure logs and identify memory/CPU pressure during peak hours.

✨ Claude Code with Roundtable AI will delegate this to specialized subagents and synthesize their findings

Why Not Just Use Multiple Tabs?

Because manual context-switching is slow, error-prone, and prevents deep analysis.

The Multi-Tab Workflow

Manually copy-paste code and context between different AI chats.
Each agent starts fresh, unaware of other conversations or files.
You wait for one agent to finish before starting the next.
You are responsible for merging disparate, often conflicting, advice.
High risk of pasting outdated code or incorrect context.

The Roundtable Workflow

Delegate tasks from a single prompt in your IDE.
The primary agent provides shared, rich context to all sub-agents.
All agents work in parallel, drastically reducing wait time.
The final output automatically synthesizes the best insights from each model.
The entire workflow is a single, deterministic, and repeatable command.

Technical Architecture

Roundtable is a local Model Context Protocol (MCP) server that coordinates sub-agents.


    +----------------------------------+
    | Your IDE (VS Code, Cursor, etc.) |
    | (Primary AI Assistant)           |
    +----------------+-----------------+
                     |
    (1. User prompt with subagent delegation)
                     |
    +----------------v-----------------+
    |      Roundtable MCP Server       |
    |         (localhost)              |
    +----------------+-----------------+
                     |
    (2. Dispatches tasks to sub-agent CLIs in parallel)
                     |
+--------------------v--------------------+
|                                         |
|  +-----------+   +-----------+   +-----------+  |
|  |  Gemini   |   |  Claude   |   |   Codex   |  |
|  | (Analysis)|   |  (Logic)  |   | (Implement)| |
|  +-----------+   +-----------+   +-----------+  |
|                                         |
+--------------------^--------------------+
                     |
    (3. Sub-agents execute using local tools,
        e.g., read_file, run_shell_command)
                     |
    +----------------+-----------------+
    |      Roundtable MCP Server       |
    | (Aggregates & Synthesizes)       |
    +----------------+-----------------+
                     |
(4. Returns a single, synthesized response)
                     |
    +----------------v-----------------+
    | Your IDE (Primary AI Assistant)  |
    +----------------------------------+

1. Context Continuity

The initial prompt and relevant file/project context are packaged by the primary agent. The MCP server passes this “context bundle” to each sub-agent, ensuring all participants have the same ground truth without manual copy-pasting.

2. Model Specialization

Use the right model for the job. Leverage Gemini's 1M context for codebase analysis, Claude's reasoning for logic and implementation, and Codex's proficiency for code generation and reviews, all in one workflow.

3. No Extra Cost

Roundtable invokes the CLI tools you already have installed and configured. It uses your existing API keys and subscriptions. We add no markup. The cost is exactly what you would pay running the tools manually.

Real-World Examples

Copyable prompts for common developer scenarios. Click to expand and copy.

Each example includes real code, logs, and explicit delegation to specialized subagents.

View More Examples on GitHub

Installation & IDE Setup

Install Roundtable AI and configure it with 26+ supported MCP clients

Quick Start

# Install Roundtable AI

# Install Roundtable AI
pip install roundtable-ai

# Check available AI tools
roundtable-ai --check

# Start with all available tools
roundtable-ai

# Use specific assistants only
roundtable-ai --agents codex,claude

IDE Configuration (Top 7)

1. Claude Code

claude mcp add roundtable-ai -- roundtable-ai --agents gemini,claude,codex,cursor

2. Cursor

Or manually add to .cursor/mcp.json:

{
  "mcpServers": {
    "roundtable-ai": {
      "command": "roundtable-ai",
      "env": {
        "CLI_MCP_SUBAGENTS": "codex,claude,cursor,gemini"
      }
    }
  }
}

3. Claude Desktop

File: ~/.config/claude_desktop_config.json

{
  "mcpServers": {
    "roundtable-ai": {
      "command": "roundtable-ai",
      "env": {
        "CLI_MCP_SUBAGENTS": "codex,claude,cursor,gemini"
      }
    }
  }
}

4. VS Code

Add to settings.json:

{
  "mcp.servers": {
    "roundtable-ai": {
      "command": "roundtable-ai",
      "env": {
        "CLI_MCP_SUBAGENTS": "codex,claude,cursor,gemini"
      }
    }
  }
}

5. OpenAI Codex

File: ~/.codex/config.toml

# IMPORTANT: the top-level key is 'mcp_servers' rather than 'mcpServers'.
[mcp_servers.roundtable-ai]
command = "roundtable-ai"
args = []
env = { "CLI_MCP_SUBAGENTS" = "codex,claude,cursor,gemini" }

6. Windsurf

File: ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "roundtable-ai": {
      "command": "roundtable-ai",
      "env": {
        "CLI_MCP_SUBAGENTS": "codex,claude,cursor,gemini"
      }
    }
  }
}

7. Gemini CLI

File: ~/.gemini/settings.json

{
  "mcpServers": {
    "roundtable-ai": {
      "command": "roundtable-ai",
      "env": {
        "CLI_MCP_SUBAGENTS": "codex,claude,cursor,gemini"
      }
    }
  }
}

Roundtable AI supports 26+ MCP-compatible clients including JetBrains IDEs, GitHub Copilot, Zed, and more.

View Full Documentation on GitHub

Advanced Configuration

# Use environment variables for project-specific setup
export CLI_MCP_SUBAGENTS="codex,claude"
export CLI_MCP_DEBUG=true

# Override with command flags (highest priority)
roundtable-ai --agents gemini,claude

# Ignore availability checks
CLI_MCP_IGNORE_AVAILABILITY=true roundtable-ai