Add it to Claude Code
claude mcp add ccg-mcp-tool -- npx -y @diazstg/ccg-mcp-tool --provider gemini --agent-mode read-onlyMake your agent remember this setup
ccg-mcp-tool's config, env vars, and the gotchas you hit — recalled in every future Claude Code, Cursor, and Codex session.
npx conare@latestFree · one command · indexes the sessions already on disk. Set up in the browser instead →
What it does
- Unified interface for Claude Code, OpenAI Codex, and Google Gemini
- Multi-agent orchestration with parallel and sequential execution
- Research-grounded mistake mitigation gates
- Structured ideation tools including SCAMPER and lateral thinking
- Large context window analysis via Gemini integration
Tools 10
ask-aiUniversal AI analysis across providersbrainstormStructured ideation (SCAMPER, lateral, etc.)mitigate-mistakesResearch-grounded gates for common AI failurescoordinate-reviewCoordinated multi-gate review by task typedeploy-agentsMulti-agent orchestration (parallel/sequential/fan-out)agent-statusMonitor orchestration sessionsfetch-chunkRetrieve chunks from large responsespingTest connectivityHelpList available toolstimeout-testDeveloper timeout testingTry it
Original README from diaz3618/ccg-mcp-tool
CCG MCP Tool (Claude Code/Codex/Gemini)
<a href="https://glama.ai/mcp/servers/@diaz3618/ccg-mcp-tool"> </a>MCP server that integrates Claude Code, OpenAI Codex, and Google Gemini into a single workflow. Analyze codebases with Gemini's massive context window, get precision edits with Codex, or use Claude's reasoning — all from one MCP interface.
Quick Start
claude mcp add ccg-tool -- npx -y @diazstg/ccg-mcp-tool
Or configure manually:
{
"mcpServers": {
"ccg-tool": {
"command": "npx",
"args": ["-y", "@diazstg/ccg-mcp-tool", "--provider", "gemini", "--agent-mode", "read-only"]
}
}
}
Prerequisites
- Node.js v16+
- At least one AI CLI: Gemini CLI, Codex CLI, or Claude Code
Tools
| Tool | Description |
|---|---|
ask-ai |
Universal AI analysis across providers |
brainstorm |
Structured ideation (SCAMPER, lateral, etc.) |
mitigate-mistakes |
Research-grounded gates for common AI failures |
coordinate-review |
Coordinated multi-gate review by task type |
deploy-agents |
Multi-agent orchestration (parallel/sequential/fan-out) |
agent-status |
Monitor orchestration sessions |
fetch-chunk |
Retrieve chunks from large responses |
ping |
Test connectivity |
Help |
List available tools |
timeout-test |
Developer timeout testing |
Documentation
- Getting Started
- Tools Reference
- Providers & Models
- Multi-Agent Orchestration
- Mitigation Skills
- Architecture
License
MIT — see LICENSE.
Disclaimer: This is an unofficial tool and is not affiliated with Google, OpenAI, or Anthropic.