{"id":31581007,"url":"https://github.com/askbudi/roundtable","last_synced_at":"2025-10-29T20:32:37.575Z","repository":{"id":316657111,"uuid":"1059882384","full_name":"askbudi/roundtable","owner":"askbudi","description":"Zero-configuration MCP server that unifies multiple AI coding assistants (Codex, Claude Code, Cursor, Gemini) through intelligent auto-discovery and standardized interface","archived":false,"fork":false,"pushed_at":"2025-09-25T03:56:36.000Z","size":133,"stargazers_count":4,"open_issues_count":0,"forks_count":1,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-09-25T23:51:00.384Z","etag":null,"topics":["claude-code","cursor","gemini-cli","mcp-server","openai-codex","vibe-coding"],"latest_commit_sha":null,"homepage":"https://askbudi.ai/roundtable","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/askbudi.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-09-19T04:53:02.000Z","updated_at":"2025-09-25T21:30:46.000Z","dependencies_parsed_at":"2025-09-26T00:02:49.729Z","dependency_job_id":null,"html_url":"https://github.com/askbudi/roundtable","commit_stats":null,"previous_names":["askbudi/roundtable"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/askbudi/roundtable","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/askbudi%2Froundtable","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/askbudi%2Froundtable/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/askbudi%2Froundtable/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/askbudi%2Froundtable/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/askbudi","download_url":"https://codeload.github.com/askbudi/roundtable/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/askbudi%2Froundtable/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":278526242,"owners_count":26001325,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-10-05T02:00:06.059Z","response_time":54,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["claude-code","cursor","gemini-cli","mcp-server","openai-codex","vibe-coding"],"created_at":"2025-10-05T21:52:04.612Z","updated_at":"2025-10-05T21:52:10.296Z","avatar_url":"https://github.com/askbudi.png","language":"Python","funding_links":[],"categories":["CI/CD \u0026 DevOps Pipelines","Aggregators \u0026 Gateways","3. \u003ca name='Dev'\u003e\u003c/a\u003e💻 Dev","精选文章","Docker MCP Toolkit","Components \u0026 Libraries","AI-Powered Compilers and Code Assistants","Model Context Protocol (MCP)","MCP 更多玩法","LLMOps","カテゴリ","Agent Infrastructure","📂 카테고리","MCP Middleware \u0026 Orchestration","Tools","📦 Other","📂 Server Implementations"],"sub_categories":["🔗 Aggregators","Aggregators","编程开发","Development Tools","Dev Tools","Other Cloud Provider Credits","亲测优质Server","Observability","🛠️ \u003ca name=\"developer-tools\"\u003e\u003c/a\u003e開発ツール","Multi-Agent Orchestration","Community"],"readme":"# Roundtable AI MCP Server\n\n[![PyPI version](https://badge.fury.io/py/roundtable-ai.svg)](https://badge.fury.io/py/roundtable-ai)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)\n\n[![Install Roundtable AI MCP Server in Cursor](https://cursor.com/deeplink/mcp-install-dark.svg)](cursor://anysphere.cursor-deeplink/mcp/install?name=roundtable-ai\u0026config=eyJ0eXBlIjoic3RkaW8iLCJjb21tYW5kIjoidXZ4IiwiYXJncyI6WyJyb3VuZHRhYmxlLWFpQGxhdGVzdCJdLCJlbnYiOnsiQ0xJX01DUF9TVUJBR0VOVFMiOiJjb2RleCxjbGF1ZGUsY3Vyc29yLGdlbWluaSJ9fQo=)\n\nStop 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.\n\n**Key Features:**\n- **Context Continuity**: Shared project context across all sub-agents\n- **Parallel Execution**: All agents work simultaneously\n- **Model Specialization**: Right AI for each task (Gemini's 1M context, Claude's reasoning, Codex's implementation)\n- **Zero Markup**: Uses your existing CLI tools and API subscriptions\n- **26+ IDE Support**: Works with Claude Code, Cursor, VS Code, JetBrains, and more\n\n## Table of Contents\n\n- [Quick Start](#quick-start)\n- [What is Roundtable AI](#what-is-roundtable-ai)\n- [Technical Architecture](#technical-architecture)\n- [Why Multi-Agent vs Single AI](#why-multi-agent-vs-single-ai)\n- [Real-World Examples](#real-world-examples)\n- [Installation](#installation)\n- [IDE Integration](#ide-integration)\n- [Advanced Configuration](#advanced-configuration)\n- [Contributing](#contributing)\n- [License](#license)\n\n## Quick Start\n\n```bash\n# Install Roundtable AI\npip install roundtable-ai\n\n# Check available AI tools\nroundtable-ai --check\n\n# Start with all available tools\nroundtable-ai\n\n# Use specific assistants only\nroundtable-ai --agents codex,claude\n```\n\n**One-liner for Claude Code:**\n```bash\nclaude mcp add roundtable-ai -- roundtable-ai --agents gemini,claude,codex,cursor\n```\n\n**Try this multi-agent prompt in your IDE:**\n```markdown\nThe user dashboard is randomly slow for enterprise customers.\n\nUse Gemini SubAgent to analyze frontend performance issues in the React components, especially expensive re-renders and inefficient data fetching.\n\nUse Codex SubAgent to examine the backend API endpoint for N+1 queries and database bottlenecks.\n\nUse Claude SubAgent to review the infrastructure logs and identify memory/CPU pressure during peak hours.\n```\n\n## What is Roundtable AI\n\nRoundtable AI is a local Model Context Protocol (MCP) server that coordinates specialized AI sub-agents to solve complex engineering problems. Instead of manually switching between different AI tools, you delegate tasks from a single prompt in your IDE, and Roundtable manages the coordination, context sharing, and response synthesis.\n\n### Key Benefits\n\n- **Context Continuity**: The primary agent provides shared, rich context to all sub-agents\n- **Parallel Execution**: All agents work simultaneously, drastically reducing wait time\n- **Model Specialization**: Use the right AI for each task - Gemini's 1M context for analysis, Claude's reasoning for logic, Codex for implementation\n- **No Extra Cost**: Uses your existing CLI tools and API subscriptions with zero markup\n- **Single Interface**: One prompt, multiple specialized responses, automatically synthesized\n\n## Technical Architecture\n\n```text\n    +----------------------------------+\n    | Your IDE (VS Code, Cursor, etc.) |\n    | (Primary AI Assistant)           |\n    +----------------+-----------------+\n                     |\n    (1. User prompt with subagent delegation)\n                     |\n    +----------------v-----------------+\n    |      Roundtable MCP Server       |\n    |         (localhost)              |\n    +----------------+-----------------+\n                     |\n    (2. Dispatches tasks to sub-agent CLIs in parallel)\n                     |\n+--------------------v--------------------+\n|                                         |\n|  +-----------+   +-----------+   +-----------+  |\n|  |  Gemini   |   |  Claude   |   |   Codex   |  |\n|  | (Analysis)|   |  (Logic)  |   | (Implement)| |\n|  +-----------+   +-----------+   +-----------+  |\n|                                         |\n+--------------------^--------------------+\n                     |\n    (3. Sub-agents execute using local tools,\n        e.g., read_file, run_shell_command)\n                     |\n    +----------------+-----------------+\n    |      Roundtable MCP Server       |\n    | (Aggregates \u0026 Synthesizes)       |\n    +----------------+-----------------+\n                     |\n(4. Returns a single, synthesized response)\n                     |\n    +----------------v-----------------+\n    | Your IDE (Primary AI Assistant)  |\n    +----------------------------------+\n```\n\n### How It Works\n\n1. **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.\n\n2. **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.\n\n3. **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.\n\n## Why Multi-Agent vs Single AI\n\nBecause manual context-switching is slow, error-prone, and prevents deep analysis.\n\n### The Multi-Tab Workflow ❌\n\n- Manually copy-paste code and context between different AI chats\n- Each agent starts fresh, unaware of other conversations or files\n- You wait for one agent to finish before starting the next\n- You are responsible for merging disparate, often conflicting, advice\n- High risk of pasting outdated code or incorrect context\n\n### The Roundtable Workflow ✅\n\n- Delegate tasks from a single prompt in your IDE\n- The primary agent provides shared, rich context to all sub-agents\n- All agents work in parallel, drastically reducing wait time\n- The final output automatically synthesizes the best insights from each model\n- The entire workflow is a single, deterministic, and repeatable command\n\n## Real-World Examples\n\nEach example includes real code, logs, and explicit delegation to specialized sub-agents. Copy the whole block and paste it into your IDE assistant.\n\n1) Multi-Stack Debugging — Virtual War Room for Production Issues\n\n```markdown\nI'm debugging a critical production issue. The user sees a \"Failed to load data\" message.\n\nHere is the browser console output:\n```json\n{\n  \"timestamp\": \"2024-09-24T10:05:21.123Z\",\n  \"level\": \"error\",\n  \"message\": \"API request failed for /api/v1/user/profile\",\n  \"error\": {\n    \"status\": 500,\n    \"statusText\": \"Internal Server Error\"\n  }\n}\n```\n\nHere is the backend server log:\n```\nERROR: Exception in ASGI application\nFile \"/app/services/user_service.py\", line 42, in get_user_profile\n  user_data = await db.fetch_one(query)\nValueError: Database connection is not available\n```\n\nUse Gemini SubAgent to analyze the logs from both stacks, correlate the events, and form a hypothesis about the root cause.\nUse Codex SubAgent to analyze the Python backend traceback and suggest a specific code fix for the database connection error.\nUse Claude SubAgent to review the frontend error handling and recommend more resilient patterns.\nUse Cursor SubAgent to search the codebase for other files that might have similar database connection issues.\n\nAt the end, aggregate all findings into a single incident report with root cause analysis and prioritized fixes.\n```\n\n2) Performance Optimization — API Latency \u0026 Database Query Tuning\n\n```markdown\nOur checkout API p95 latency increased from 220ms to 780ms. Need optimization strategy.\n\nPostgreSQL slow query log:\n```sql\n-- Duration: 2455.112 ms\nSELECT c.name, COUNT(o.id) AS total_orders, SUM(p.amount) AS revenue\nFROM companies c, orders o, payments p\nWHERE c.id = o.company_id\n  AND o.id = p.order_id\n  AND c.region = 'North America'\nGROUP BY c.name\nORDER BY revenue DESC;\n```\n\nEXPLAIN ANALYZE shows:\n```\nSeq Scan on orders (cost=0.00..52000.00 rows=100000)\n  Filter: (status = 'completed')\n  Rows Removed by Filter: 134,201\n```\n\nNode.js hotspot from profiling:\n```javascript\n// 40% CPU time\norders.map(o =\u003e ({ ...o, json: JSON.stringify(o) }));\n\n// N+1 query problem\nfor (const id of orderIds) {\n  await fetchInventory(id);\n}\n```\n\nUse Claude SubAgent to analyze the EXPLAIN plan and identify why the query is slow.\nUse Codex SubAgent to rewrite the SQL with proper JOINs and suggest indexes.\nUse Gemini SubAgent to fix the N+1 query problem with batch fetching.\nUse Cursor SubAgent to find all instances of JSON.stringify in hot code paths.\n\nAggregate findings into a performance optimization plan with measurable improvements.\n```\n\n## Installation\n\n### Using pip (Standard)\n\n```bash\npip install roundtable-ai\n```\n\n### Using UV/UVX (Recommended for faster installs)\n\n```bash\nuvx roundtable-ai@latest\n```\n\n## IDE Integration\n\nRoundtable AI supports 26+ MCP-compatible clients. Here are the top 7:\n\n### 1. Claude Code\n\n**Using pip:**\n```bash\nclaude mcp add roundtable-ai -- roundtable-ai --agents gemini,claude,codex,cursor\n```\n\n**Using UVX:**\n```bash\nclaude mcp add roundtable-ai -- uvx roundtable-ai@latest --agents gemini,claude,codex,cursor\n```\n\n### 2. Cursor\n\n**One-Click Install:**\n\n[![Install Roundtable AI MCP Server in Cursor](https://cursor.com/deeplink/mcp-install-dark.svg)](cursor://anysphere.cursor-deeplink/mcp/install?name=roundtable-ai\u0026config=eyJ0eXBlIjoic3RkaW8iLCJjb21tYW5kIjoidXZ4IiwiYXJncyI6WyJyb3VuZHRhYmxlLWFpQGxhdGVzdCJdLCJlbnYiOnsiQ0xJX01DUF9TVUJBR0VOVFMiOiJjb2RleCxjbGF1ZGUsY3Vyc29yLGdlbWluaSJ9fQo=)\n\nOr use this direct link:\n```\ncursor://anysphere.cursor-deeplink/mcp/install?name=roundtable-ai\u0026config=eyJ0eXBlIjoic3RkaW8iLCJjb21tYW5kIjoidXZ4IiwiYXJncyI6WyJyb3VuZHRhYmxlLWFpQGxhdGVzdCJdLCJlbnYiOnsiQ0xJX01DUF9TVUJBR0VOVFMiOiJjb2RleCxjbGF1ZGUsY3Vyc29yLGdlbWluaSJ9fQo=\n```\n\n**Manual Installation:**\n\n**File:** `.cursor/mcp.json`\n\n**Using pip:**\n```json\n{\n  \"mcpServers\": {\n    \"roundtable-ai\": {\n      \"command\": \"roundtable-ai\",\n      \"env\": {\n        \"CLI_MCP_SUBAGENTS\": \"codex,claude,cursor,gemini\"\n      }\n    }\n  }\n}\n```\n\n**Using UVX:**\n```json\n{\n  \"mcpServers\": {\n    \"roundtable-ai\": {\n      \"type\": \"stdio\",\n      \"command\": \"uvx\",\n      \"args\": [\n        \"roundtable-ai@latest\"\n      ],\n      \"env\": {\n        \"CLI_MCP_SUBAGENTS\": \"codex,claude,cursor,gemini\"\n      }\n    }\n  }\n}\n```\n\n### 3. Claude Desktop\n\n**File:** `~/.config/claude_desktop_config.json`\n\n**Using pip:**\n```json\n{\n  \"mcpServers\": {\n    \"roundtable-ai\": {\n      \"command\": \"roundtable-ai\",\n      \"env\": {\n        \"CLI_MCP_SUBAGENTS\": \"codex,claude,cursor,gemini\"\n      }\n    }\n  }\n}\n```\n\n**Using UVX:**\n```json\n{\n  \"mcpServers\": {\n    \"roundtable-ai\": {\n      \"command\": \"uvx\",\n      \"args\": [\"roundtable-ai@latest\"],\n      \"env\": {\n        \"CLI_MCP_SUBAGENTS\": \"codex,claude,cursor,gemini\"\n      }\n    }\n  }\n}\n```\n\n### 4. VS Code\n\n**Add to `settings.json`:**\n\n**Using pip:**\n```json\n{\n  \"mcp.servers\": {\n    \"roundtable-ai\": {\n      \"command\": \"roundtable-ai\",\n      \"env\": {\n        \"CLI_MCP_SUBAGENTS\": \"codex,claude,cursor,gemini\"\n      }\n    }\n  }\n}\n```\n\n**Using UVX:**\n```json\n{\n  \"mcp.servers\": {\n    \"roundtable-ai\": {\n      \"command\": \"uvx\",\n      \"args\": [\"roundtable-ai@latest\"],\n      \"env\": {\n        \"CLI_MCP_SUBAGENTS\": \"codex,claude,cursor,gemini\"\n      }\n    }\n  }\n}\n```\n\n### 5. OpenAI Codex\n\n**File:** `~/.codex/config.toml`\n\n**Using pip:**\n```toml\n# IMPORTANT: the top-level key is 'mcp_servers' rather than 'mcpServers'.\n[mcp_servers.roundtable-ai]\ncommand = \"roundtable-ai\"\nargs = []\nenv = { \"CLI_MCP_SUBAGENTS\" = \"codex,claude,cursor,gemini\" }\n```\n\n**Using UVX:**\n```toml\n# IMPORTANT: the top-level key is 'mcp_servers' rather than 'mcpServers'.\n[mcp_servers.roundtable-ai]\ncommand = \"uvx\"\nargs = [\"roundtable-ai@latest\"]\nenv = { \"CLI_MCP_SUBAGENTS\" = \"codex,claude,cursor,gemini\" }\n```\n\n### 6. Windsurf\n\n**File:** `~/.codeium/windsurf/mcp_config.json`\n\n**Using pip:**\n```json\n{\n  \"mcpServers\": {\n    \"roundtable-ai\": {\n      \"command\": \"roundtable-ai\",\n      \"env\": {\n        \"CLI_MCP_SUBAGENTS\": \"codex,claude,cursor,gemini\"\n      }\n    }\n  }\n}\n```\n\n**Using UVX:**\n```json\n{\n  \"mcpServers\": {\n    \"roundtable-ai\": {\n      \"command\": \"uvx\",\n      \"args\": [\"roundtable-ai@latest\"],\n      \"env\": {\n        \"CLI_MCP_SUBAGENTS\": \"codex,claude,cursor,gemini\"\n      }\n    }\n  }\n}\n```\n\n### 7. Gemini CLI\n\n**File:** `~/.gemini/settings.json`\n\n**Using pip:**\n```json\n{\n  \"mcpServers\": {\n    \"roundtable-ai\": {\n      \"command\": \"roundtable-ai\",\n      \"env\": {\n        \"CLI_MCP_SUBAGENTS\": \"codex,claude,cursor,gemini\"\n      }\n    }\n  }\n}\n```\n\n**Using UVX:**\n```json\n{\n  \"mcpServers\": {\n    \"roundtable-ai\": {\n      \"command\": \"uvx\",\n      \"args\": [\"roundtable-ai@latest\"],\n      \"env\": {\n        \"CLI_MCP_SUBAGENTS\": \"codex,claude,cursor,gemini\"\n      }\n    }\n  }\n}\n```\n\n### Additional IDE Support\n\nRoundtable AI integrates with **26+ different IDEs and AI coding tools**:\n\n#### JetBrains IDEs (IntelliJ, PyCharm, WebStorm, etc.)\n\n**Settings Path**: `Settings \u003e Tools \u003e AI Assistant \u003e Model Context Protocol (MCP)`\n\n```json\n{\n  \"name\": \"roundtable-ai\",\n  \"command\": \"roundtable-ai\",\n  \"transport\": \"stdio\",\n  \"env\": {\n    \"CLI_MCP_SUBAGENTS\": \"codex,claude,cursor,gemini\"\n  }\n}\n```\n\n#### GitHub Copilot\n\n```json\n{\n  \"github.copilot.mcp.servers\": {\n    \"roundtable-ai\": {\n      \"command\": \"roundtable-ai\",\n      \"env\": {\n        \"CLI_MCP_SUBAGENTS\": \"codex,claude,cursor,gemini\"\n      }\n    }\n  }\n}\n```\n\n---\n\n### 🖥️ Desktop IDEs\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eJetBrains AI Assistant\u003c/b\u003e - IntelliJ, PyCharm, WebStorm, etc.\u003c/summary\u003e\n\n1. **Settings Path**: `Settings \u003e Tools \u003e AI Assistant \u003e Model Context Protocol (MCP)`\n2. **Add New Server**: Click \"+\" to add new MCP server\n3. **Configuration**:\n   ```json\n   {\n     \"name\": \"roundtable-ai\",\n     \"command\": \"roundtable-ai\",\n     \"transport\": \"stdio\",\n     \"env\": {\n       \"CLI_MCP_SUBAGENTS\": \"codex,claude,cursor,gemini\",\n     }\n   }\n   ```\n4. **Apply \u0026 Restart**: Apply settings and restart the IDE\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eVisual Studio 2022\u003c/b\u003e - Microsoft's Flagship IDE\u003c/summary\u003e\n\nCreate `mcp_config.json` in your project root:\n```json\n{\n  \"servers\": {\n    \"roundtable-ai\": {\n      \"command\": \"roundtable-ai\",\n      \"transport\": \"stdio\",\n      \"env\": {\n        \"CLI_MCP_SUBAGENTS\": \"codex,claude,cursor,gemini\"\n      }\n    }\n  }\n}\n```\n\n**Alternative**: Use Extensions \u003e Manage Extensions \u003e Search for \"Roundtable AI\"\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eZed\u003c/b\u003e - High-Performance Code Editor\u003c/summary\u003e\n\nAdd to `settings.json` (Cmd/Ctrl + ,):\n```json\n{\n  \"context_servers\": {\n    \"roundtable-ai\": {\n      \"command\": \"roundtable-ai\",\n      \"env\": {\n        \"CLI_MCP_SUBAGENTS\": \"codex,claude,cursor,gemini\"\n      }\n    }\n  }\n}\n```\n\n**Extension Alternative**: Search for \"Roundtable AI\" in Zed Extensions\n\n\u003c/details\u003e\n\n---\n\n### 💻 CLI Tools\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eGemini CLI\u003c/b\u003e - Google's Gemini Command-Line Interface\u003c/summary\u003e\n\nEdit `~/.gemini/settings.json`:\n```json\n{\n  \"mcpServers\": {\n    \"roundtable-ai\": {\n      \"command\": \"roundtable-ai\",\n      \"env\": {\n        \"CLI_MCP_SUBAGENTS\": \"codex,claude,cursor,gemini\"\n      }\n    }\n  }\n}\n```\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eRovo Dev CLI\u003c/b\u003e - Atlassian's Development CLI\u003c/summary\u003e\n\nConfigure via `rovo config` command:\n```bash\n# Add MCP server\nrovo mcp add roundtable-ai roundtable-ai\n\n# Verify\nrovo mcp list\n```\n\n**Manual configuration** in `~/.rovo/config.json`:\n```json\n{\n  \"mcpServers\": {\n    \"roundtable-ai\": {\n      \"command\": \"roundtable-ai\",\n      \"env\": {\n        \"CLI_MCP_SUBAGENTS\": \"codex,claude,cursor,gemini\"\n      }\n    }\n  }\n}\n```\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eAmazon Q Developer CLI\u003c/b\u003e - Amazon's AI Development Assistant\u003c/summary\u003e\n\nEdit configuration in `~/.aws/q-developer/config.json`:\n```json\n{\n  \"mcpServers\": {\n    \"roundtable-ai\": {\n      \"command\": \"roundtable-ai\",\n      \"env\": {\n        \"CLI_MCP_SUBAGENTS\": \"codex,claude,cursor,gemini\"\n      }\n    }\n  }\n}\n```\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eCrush\u003c/b\u003e - Terminal-Based AI Assistant\u003c/summary\u003e\n\nCreate or edit `crush.json` in your project:\n```json\n{\n  \"mcp\": {\n    \"roundtable-ai\": {\n      \"command\": \"roundtable-ai\",\n      \"transport\": \"stdio\",\n      \"env\": {\n        \"CLI_MCP_SUBAGENTS\": \"codex,claude,cursor,gemini\"\n      }\n    }\n  }\n}\n```\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eWarp\u003c/b\u003e - AI-Powered Terminal\u003c/summary\u003e\n\nConfigure via Warp settings:\n1. **Open Settings**: Cmd/Ctrl + ,\n2. **Navigate to**: Features \u003e AI \u003e MCP Servers\n3. **Add Server**:\n   ```json\n   {\n     \"name\": \"roundtable-ai\",\n     \"command\": \"roundtable-ai\",\n     \"env\": {\n       \"CLI_MCP_SUBAGENTS\": \"codex,claude,cursor,gemini\"\n     }\n   }\n   ```\n\n\u003c/details\u003e\n\n---\n\n### 🤖 AI Assistants\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eClaude Desktop\u003c/b\u003e - Anthropic's Desktop Application\u003c/summary\u003e\n\nEdit `~/.config/claude_desktop_config.json`:\n```json\n{\n  \"mcpServers\": {\n    \"roundtable-ai\": {\n      \"command\": \"roundtable-ai\",\n      \"env\": {\n        \"CLI_MCP_SUBAGENTS\": \"codex,claude,cursor,gemini\"\n      }\n    }\n  }\n}\n```\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eCline\u003c/b\u003e - AI Assistant Extension\u003c/summary\u003e\n\n**One-Click Install**:\n1. Open Cline MCP Server Marketplace\n2. Search for \"Roundtable AI\"\n3. Click \"Install\"\n\n**Manual Configuration** in `cline_mcp_settings.json`:\n```json\n{\n  \"mcpServers\": {\n    \"roundtable-ai\": {\n      \"command\": \"roundtable-ai\",\n      \"env\": {\n        \"CLI_MCP_SUBAGENTS\": \"codex,claude,cursor,gemini\"\n      }\n    }\n  }\n}\n```\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eBoltAI\u003c/b\u003e - AI Assistant Application\u003c/summary\u003e\n\n1. **Open BoltAI Settings**\n2. **Navigate to**: Plugins \u003e MCP Servers\n3. **Add New Server**:\n   - Name: `roundtable-ai`\n   - Command: `roundtable-ai`\n   - Environment Variables:\n     ```\n     CLI_MCP_SUBAGENTS=codex,claude,cursor,gemini\n     ```\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003ePerplexity Desktop\u003c/b\u003e - AI Search and Research Assistant\u003c/summary\u003e\n\nConfigure in Perplexity settings:\n```json\n{\n  \"mcpConfig\": {\n    \"servers\": {\n      \"roundtable-ai\": {\n        \"command\": \"roundtable-ai\",\n        \"env\": {\n          \"CLI_MCP_SUBAGENTS\": \"codex,claude,cursor,gemini\"\n        }\n      }\n    }\n  }\n}\n```\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eQodo Gen\u003c/b\u003e - AI Code Generation and Analysis Tool\u003c/summary\u003e\n\nAdd to Qodo Gen configuration:\n```json\n{\n  \"mcp_servers\": {\n    \"roundtable-ai\": {\n      \"command\": \"roundtable-ai\",\n      \"env\": {\n        \"CLI_MCP_SUBAGENTS\": \"codex,claude,cursor,gemini\"\n      }\n    }\n  }\n}\n```\n\n\u003c/details\u003e\n\n---\n\n### 🛠️ Specialized Tools\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eOpencode\u003c/b\u003e - Open-Source AI Code Editor\u003c/summary\u003e\n\nAdd to `opencode_config.json`:\n```json\n{\n  \"mcpServers\": {\n    \"roundtable-ai\": {\n      \"command\": \"roundtable-ai\",\n      \"env\": {\n        \"CLI_MCP_SUBAGENTS\": \"codex,claude,cursor,gemini\"\n      }\n    }\n  }\n}\n```\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eOpenAI Codex\u003c/b\u003e - OpenAI's Code Generation Model Interface\u003c/summary\u003e\n\nEdit `config.toml`:\n```toml\n[mcp_servers.roundtable-ai]\ncommand = \"roundtable-ai\"\nenv = { CLI_MCP_SUBAGENTS = \"codex,claude,cursor,gemini\" }\n```\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eKiro\u003c/b\u003e - AI Development Assistant\u003c/summary\u003e\n\nConfigure in `~/.kiro/config.json`:\n```json\n{\n  \"mcpServers\": {\n    \"roundtable-ai\": {\n      \"command\": \"roundtable-ai\",\n      \"env\": {\n        \"CLI_MCP_SUBAGENTS\": \"codex,claude,cursor,gemini\"\n      }\n    }\n  }\n}\n```\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eTrae\u003c/b\u003e - AI Development Environment\u003c/summary\u003e\n\nAdd to Trae workspace configuration:\n```json\n{\n  \"mcp\": {\n    \"servers\": {\n      \"roundtable-ai\": {\n        \"command\": \"roundtable-ai\",\n        \"env\": {\n          \"CLI_MCP_SUBAGENTS\": \"codex,claude,cursor,gemini\"\n        }\n      }\n    }\n  }\n}\n```\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eLM Studio\u003c/b\u003e - Local Language Model Interface\u003c/summary\u003e\n\n**One-Click Install**:\n1. Navigate to **Program \u003e Install \u003e Edit mcp.json**\n2. Search for \"Roundtable AI\" in marketplace\n3. Click \"Install\"\n\n**Manual Configuration**:\n```json\n{\n  \"mcpServers\": {\n    \"roundtable-ai\": {\n      \"command\": \"roundtable-ai\",\n      \"env\": {\n        \"CLI_MCP_SUBAGENTS\": \"codex,claude,cursor,gemini\"\n      }\n    }\n  }\n}\n```\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eZencoder\u003c/b\u003e - AI-Powered Coding Assistant\u003c/summary\u003e\n\nConfigure via Zencoder settings panel:\n```json\n{\n  \"mcp_configuration\": {\n    \"roundtable-ai\": {\n      \"command\": \"roundtable-ai\",\n      \"env\": {\n        \"CLI_MCP_SUBAGENTS\": \"codex,claude,cursor,gemini\"\n      }\n    }\n  }\n}\n```\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eAugment Code\u003c/b\u003e - AI-Powered Code Completion\u003c/summary\u003e\n\nAdd to Augment Code workspace settings:\n```json\n{\n  \"mcpServers\": {\n    \"roundtable-ai\": {\n      \"command\": \"roundtable-ai\",\n      \"transport\": \"stdio\",\n      \"env\": {\n        \"CLI_MCP_SUBAGENTS\": \"codex,claude,cursor,gemini\"\n      }\n    }\n  }\n}\n```\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eRoo Code\u003c/b\u003e - AI Development Environment\u003c/summary\u003e\n\nConfigure in Roo Code project settings:\n```json\n{\n  \"ai_assistants\": {\n    \"mcp_servers\": {\n      \"roundtable-ai\": {\n        \"command\": \"roundtable-ai\",\n        \"env\": {\n          \"CLI_MCP_SUBAGENTS\": \"codex,claude,cursor,gemini\"\n        }\n      }\n    }\n  }\n}\n```\n\n\u003c/details\u003e\n\n---\n\n### 🔧 Configuration Tips\n\n#### Environment Variables Reference\n```bash\n# Specify which AI assistants to enable\nCLI_MCP_SUBAGENTS=\"codex,claude,cursor,gemini\"\n\n\n# Enable debug logging\nCLI_MCP_DEBUG=true\n\n# Override availability checking\nCLI_MCP_IGNORE_AVAILABILITY=true\n```\n\n#### Command Alternatives\nAll IDEs support these equivalent commands:\n- `roundtable-ai` (primary command)\n- `roundtable-mcp-server` (descriptive alias)\n- `python -m roundtable_mcp_server` (Python module)\n- `npx @roundtable/mcp-server` (NPM package - coming soon)\n\n#### Verification\nAfter installation, verify the integration works:\n\n```bash\n# Check server availability\nroundtable-ai --check\n\n# Test connection (varies by IDE)\n# Most IDEs will show \"Roundtable AI\" in their AI assistant panel\n```\n\n#### Troubleshooting\n1. **Server not found**: Ensure `roundtable-ai` is in your PATH\n2. **Permission denied**: Run `chmod +x $(which roundtable-ai)`\n3. **Config not loaded**: Check file paths and JSON syntax\n4. **No AI tools detected**: Run `roundtable-ai --check` first\n\n## Available MCP Tools\n\nOnce integrated, you get access to:\n\n### Availability Checks\n- `check_codex_availability` - Verify Codex CLI status\n- `check_claude_availability` - Verify Claude Code CLI status\n- `check_cursor_availability` - Verify Cursor CLI status\n- `check_gemini_availability` - Verify Gemini CLI status\n\n### Unified Task Execution\n- `execute_codex_task` - Run coding tasks through Codex\n- `execute_claude_task` - Run coding tasks through Claude Code\n- `execute_cursor_task` - Run coding tasks through Cursor\n- `execute_gemini_task` - Run coding tasks through Gemini\n\n## Advanced Configuration\n\n### Environment Variables\n```bash\n# Specify which assistants to enable\nexport CLI_MCP_SUBAGENTS=\"codex,gemini\"\n\n\n# Enable all tools regardless of availability\nexport CLI_MCP_IGNORE_AVAILABILITY=true\n\n# Enable debug logging\nexport CLI_MCP_DEBUG=true\n```\n\n### Command Line Options\n\n```bash\nroundtable-ai --help\n\nOptions:\n  --agents TEXT     Comma-separated list of agents (gemini,claude,codex,cursor)\n  --check          Check availability of all AI tools\n  --debug          Enable debug logging\n  --version        Show version information\n  --help           Show this message and exit\n```\n\n## Contributing\n\n1. Fork the repository\n2. Create a feature branch (`git checkout -b feature/amazing-feature`)\n3. Commit your changes (`git commit -m 'Add some amazing feature'`)\n4. Push to the branch (`git push origin feature/amazing-feature`)\n5. Open a Pull Request\n\n## License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n\n---\n\n**Built for developers who value their time.** Stop context-switching between AI tools and start solving problems faster with coordinated multi-agent workflows.\n\nFor more examples, advanced usage patterns, and troubleshooting guides, visit our [GitHub repository](https://github.com/askbudi/roundtable).","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faskbudi%2Froundtable","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faskbudi%2Froundtable","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faskbudi%2Froundtable/lists"}