Atlas / MCP servers / askbudi / Roundtable AI

Roundtable AICAUTION

mcp/askbudi/roundtable-ai

Zero-configuration MCP server that unifies multiple AI coding assistants (Codex, Claude Code, Cursor, Gemini) through intelligent auto-discovery and standardized interface

Verdict
CAUTION
Grade
C
Trust score
79 /100
Exposed tools
9 9r · 0w · 0d
Transport
—
License
—
Stars
125
01

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
Read from source at commit e405294c09d4OBSERVED · 2026-10-07
02

Connect

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-code
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
claude-desktop
{
  "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}"
      }
    }
  }
}
03

Exposed tools (9)

9 read · 0 write · 0 destructive.

ToolRiskDescription
check_claude_availabilityread
check_codex_availabilityread
check_cursor_availabilityread
check_gemini_availabilityread
claude_subagentread
codex_subagentread
cursor_subagentread
gemini_subagentread
test_toolread
04

Trust audit

CAUTIONgrade C · trust 79/100 Install with care. The audit found things worth knowing before you trust its output.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codeWARN
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (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)

MEDIUMCode injection · code.dynamic_import · CWE-78, CWE-94, CWE-95
roundtable_mcp_server/server.py:31
module = importlib.import_module(f".{module_name}", package=package)
MEDIUMCode injection · code.dynamic_import · CWE-78, CWE-94, CWE-95
roundtable_mcp_server/server.py:39
module = importlib.import_module(module_name)
LOWInventory / provenance · inv.no_license · CWE-1104
Why it matters. no LICENSE file and no repo licence
Fix. add a licence
LOWInsecure crypto · crypto.weak_hash · CWE-327, CWE-338
claudable_helper/services/local_runtime.py:69
return hashlib.md5(core_error.encode()).hexdigest()[:8]
LOWInsecure crypto · crypto.weak_hash · CWE-327, CWE-338
claudable_helper/services/local_runtime.py:239
current_hash += hashlib.md5(f.read()).hexdigest()
LOWInsecure crypto · crypto.weak_hash · CWE-327, CWE-338
claudable_helper/services/local_runtime.py:244
current_hash += hashlib.md5(f.read()).hexdigest()
LOWInsecure crypto · crypto.weak_hash · CWE-327, CWE-338
claudable_helper/services/local_runtime.py:247
final_hash = hashlib.md5(current_hash.encode()).hexdigest()
LOWInsecure crypto · crypto.weak_hash · CWE-327, CWE-338
claudable_helper/services/local_runtime.py:273
current_hash += hashlib.md5(f.read()).hexdigest()
LOWObfuscation / stealth · obf.decode_call · CWE-506, CWE-94
claudable_helper/cli/adapters/codex_cli.py:287
img_bytes = _b64.b64decode(b64_str, validate=False)
LOWObfuscation / stealth · obf.decode_call · CWE-506, CWE-94
claudable_helper/core/crypto.py:31
decoded = base64.b64decode(ciphertext)

Gates applied: no_behavioural_pass, no_license.

Audited 2026-10-07 · audit v0.4.1 · source sha e405294c09d4full audit observations/trust-audit/mcp-server/askbudi__roundtable-ai.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-07e405294c09d4CAUTIONC79first audit
06

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.

Advertisement