MCP Directory

Roundtable AI MCP Server

Local MCP server that delegates coding tasks to specialized AI sub-agents (Codex, Claude, Cursor, Gemini) in parallel.

Unverified
stdio (local)
No auth
Stale
Python

Add to your client

Copy the config for your MCP client and paste it into its config file.

Install / run
pip install roundtable-ai

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "roundtable-ai-mcp-server": {
      "command": "uvx",
      "args": [
        "roundtable-ai@latest"
      ],
      "env": {
        "CLI_MCP_SUBAGENTS": "codex,claude,cursor,gemini"
      }
    }
  }
}

Requires `uv` (the Python package runner). Install it from https://docs.astral.sh/uv/ if `uvx` is not found.

Step-by-step guides: Add to Claude Desktop · Add to Cursor · Add to Windsurf

Before you start

  • Python 3.10+
  • pip or uv/uvx to install the roundtable-ai package
  • The CLI tools for the sub-agents you enable (e.g. Codex, Claude Code, Cursor, Gemini), installed and authenticated with your own API keys/subscriptions

About Roundtable AI MCP Server

Roundtable AI is a zero-configuration local MCP server that unifies multiple AI coding assistants (Codex, Claude Code, Cursor, Gemini) behind a standardized interface. Your primary IDE assistant delegates subtasks to specialized sub-agents that run in parallel; Roundtable shares context across them and synthesizes their outputs into a single response. It uses the CLI tools and API subscriptions you already have, adding no markup. Enable specific agents via the CLI_MCP_SUBAGENTS env var or the --agents flag, and verify tool availability with roundtable-ai --check.

Tools & capabilities (8)

check_codex_availability

Verify Codex CLI status / availability.

check_claude_availability

Verify Claude Code CLI status / availability.

check_cursor_availability

Verify Cursor CLI status / availability.

check_gemini_availability

Verify Gemini CLI status / availability.

execute_codex_task

Run coding tasks through Codex.

execute_claude_task

Run coding tasks through Claude Code.

execute_cursor_task

Run coding tasks through Cursor.

execute_gemini_task

Run coding tasks through Gemini.

When to use it

  • Multi-stack debugging — delegate frontend, backend, infra, and codebase-search analysis to different sub-agents in parallel and aggregate into one incident report.
  • Performance optimization — have one agent analyze a slow SQL EXPLAIN plan, another rewrite queries and suggest indexes, another fix N+1 problems, all from a single prompt.
  • Cross-model code review by routing logic, implementation, and analysis to the model best suited for each.
  • Avoiding manual copy-paste/context-switching between separate AI chat tools while keeping shared project context.

Security notes

Runs locally and invokes your installed CLI coding agents (Codex, Claude Code, Cursor, Gemini), executing tasks against your codebase with your existing API keys/subscriptions. Sub-agents run local tools such as read_file and run_shell_command, so only enable agents you trust with shell and file access in your project.

Roundtable AI MCP Server FAQ

Does Roundtable charge extra to use multiple models?

No. It invokes the CLI tools you already have installed and uses your existing API keys and subscriptions with zero markup; cost is the same as running the tools manually.

How do I choose which AI assistants are enabled?

Set the CLI_MCP_SUBAGENTS environment variable (e.g. "codex,claude,cursor,gemini") or pass --agents on the command line (e.g. `roundtable-ai --agents codex,claude`).

How do I add it to Claude Code?

Run `claude mcp add roundtable-ai -- roundtable-ai --agents gemini,claude,codex,cursor`, or with uvx: `claude mcp add roundtable-ai -- uvx roundtable-ai@latest --agents gemini,claude,codex,cursor`.

How do I check that my AI tools are detected?

Run `roundtable-ai --check` to verify availability of all configured AI tools before connecting it to your IDE.

Alternatives to Roundtable AI MCP Server

Compare all alternatives →

Microsoft's official browser-automation MCP using Playwright's accessibility tree (no vision model).

Featured
Verified
stdio (local)
No auth
TypeScript
12 tools
Updated 13 days agoRepo

Up-to-date, version-specific library documentation injected into your coding agent.

Verified
stdio (local)
API key
TypeScript
2 tools
Updated 17 days agoRepo

LSP-powered coding agent toolkit: semantic symbol search, references and structural edits.

Verified
stdio (local)
No auth
Python
11 tools
Updated 15 days agoRepo