Roundtable AICAUTION
Zero-configuration MCP server that unifies multiple AI coding assistants (Codex, Claude Code, Cursor, Gemini) through intelligent auto-discovery and standardized interface
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://badge.fury.io/py/roundtable-ai) [](https://opensource.org/licenses/MIT) [](https://www.python.org/downloads/)
[](cursor://anysphere.cursor-deeplink/mcp/install?name=roundtable-ai&config=eyJ0eXBlIjoic3RkaW8iLCJjb21tYW5kIjoidXZ4IiwiYXJncyI6WyJyb3VuZHRhYmxlLWFpQGxhdGVzdCJdLCJlbnYiOnsiQ0xJX01DUF9TVUJBR0VOVFMiOiJjb2RleCxjbGF1ZGUsY3Vyc29yLGdlbWluaSJ9fQo=)
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.
Key Features:
- Context Continuity: Shared project context across all sub-agents
- Parallel Execution: All agents work simultaneously
- Model Specialization: Right AI for each task (Gemini's 1M context, Claude's reasoning, Codex's implementation)
- Zero Markup: Uses your existing CLI tools and API subscriptions
- 26+ IDE Support: Works with Claude Code, Cursor, VS Code, JetBrains, and more
Table of Contents
- Quick Start
- What is Roundtable AI
- Technical Architecture
- Why Multi-Agent vs Single AI
- Real-World Examples
- Installation
- IDE Integration
- Advanced Configuration
- Contributing
- License
Quick Start
# Install Roundtable AI pip install roundtable-ai # Check available AI tools roundtable-ai --check # Start with all available tools roundtable-ai # Use specific assistants o
e405294c09d4OBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add roundtable-ai --env ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY} --env CURSOR_API_KEY=${CURSOR_API_KEY} --env GEMINI_AUTH_METHOD=${GEMINI_AUTH_METHOD} --env QWEN_AUTH_METHOD=${QWEN_AUTH_METHOD} -- uvx roundtable-ai{
"mcpServers": {
"roundtable-ai": {
"command": "uvx",
"args": [
"roundtable-ai"
],
"env": {
"ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}",
"CURSOR_API_KEY": "${CURSOR_API_KEY}",
"GEMINI_AUTH_METHOD": "${GEMINI_AUTH_METHOD}",
"QWEN_AUTH_METHOD": "${QWEN_AUTH_METHOD}"
}
}
}
}Exposed tools (9)
9 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
check_claude_availability | read | |
check_codex_availability | read | |
check_cursor_availability | read | |
check_gemini_availability | read | |
claude_subagent | read | |
codex_subagent | read | |
cursor_subagent | read | |
gemini_subagent | read | |
test_tool | read |
Trust audit
CAUTIONgrade C · trust 79/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (5 observation(s))
- Network
- declared (9 observation(s))
- Shell
- declared (2 observation(s))
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (10)
module = importlib.import_module(f".{module_name}", package=package)module = importlib.import_module(module_name)
return hashlib.md5(core_error.encode()).hexdigest()[:8]
current_hash += hashlib.md5(f.read()).hexdigest()
current_hash += hashlib.md5(f.read()).hexdigest()
final_hash = hashlib.md5(current_hash.encode()).hexdigest()
current_hash += hashlib.md5(f.read()).hexdigest()
img_bytes = _b64.b64decode(b64_str, validate=False)
decoded = base64.b64decode(ciphertext)
Gates applied: no_behavioural_pass, no_license.
e405294c09d4full audit observations/trust-audit/mcp-server/askbudi__roundtable-ai.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | e405294c09d4 | CAUTION | C | 79 | first audit |
Questions
What is the Roundtable AI MCP server?
Zero-configuration MCP server that unifies multiple AI coding assistants (Codex, Claude Code, Cursor, Gemini) through intelligent auto-discovery and standardized interface
What tools does Roundtable AI expose?
9 in total: 9 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Roundtable AI safe to connect to an agent?
With care. The audit graded it C (79/100) and found 10 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does Roundtable AI need?
It reads ANTHROPIC_API_KEY, CURSOR_API_KEY, GEMINI_AUTH_METHOD and QWEN_AUTH_METHOD from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How current is this page?
The grade is for one exact copy of the source (e405294c09d4), read on 2026-10-07. The repository is watched and re-audited when it changes.