CCG MCP Tool is a unified MCP server that integrates Claude Code, OpenAI Codex, and Google Gemini into a single workflow for AI-powered code analysis, ideation, review, and multi-agent orchestration.
ask-ai: Send prompts to Gemini, Codex, or Claude for code analysis, file inspection (via @ syntax), and structured edit suggestions; supports sandbox mode (Gemini) and chunked responses for large outputs.
brainstorm: Generate ideas using creative frameworks (SCAMPER, Design Thinking, lateral thinking, etc.) with feasibility analysis, domain context integration, and configurable idea counts.
mitigate-mistakes: Apply targeted, research-grounded skill gates (e.g., requirements-grounding, secure-coding, dependency-verification) to detect common AI coding mistakes at specific development stages.
coordinate-review: Run an automated multi-gate code review tailored to a task type (feature, bugfix, refactor, dependency-update), producing gate-by-gate findings and a merge recommendation.
deploy-agents: Orchestrate up to 10 AI agents in parallel, sequential, or fan-out strategies for collaborative or independent task execution, with support for Claude Code Agent Teams.
agent-status: Monitor and inspect active or recent multi-agent orchestration sessions.
fetch-chunk: Retrieve paginated chunks from large cached responses (e.g., structured change mode outputs).
ping: Test connectivity to the MCP server.
Help: Display help information for the configured AI provider CLI.
timeout-test: Developer utility to test timeout prevention behavior.
Allows analyzing codebases using Google Gemini's massive context window within a unified workflow.
Provides precision code edits and analysis through integration with OpenAI Codex.
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.
Related MCP server: Agent Orchestration
claude mcp add ccg-tool -- npx -y @diazstg/ccg-mcp-toolOr configure manually:
{
"mcpServers": {
"ccg-tool": {
"command": "npx",
"args": ["-y", "@diazstg/ccg-mcp-tool", "--provider", "gemini", "--agent-mode", "read-only"]
}
}
}Node.js v16+
At least one AI CLI: Gemini CLI, Codex CLI, or Claude Code
Tool | Description |
| Universal AI analysis across providers |
| Structured ideation (SCAMPER, lateral, etc.) |
| Research-grounded gates for common AI failures |
| Coordinated multi-gate review by task type |
| Multi-agent orchestration (parallel/sequential/fan-out) |
| Monitor orchestration sessions |
| Retrieve chunks from large responses |
| Test connectivity |
| List available tools |
| Developer timeout testing |
MIT — see LICENSE.
Disclaimer: This is an unofficial tool and is not affiliated with Google, OpenAI, or Anthropic.
Check status of multi-agent orchestration sessions. Provide a sessionId to get details, or omit to list recent sessions. Current agent mode: read-only.
Inputs: sessionId.
Provider selection [--provider], model selection [-m], sandbox [-s], and changeMode:boolean for providing edits. Supports Gemini, Codex, and Claude Code.
Inputs: prompt (required), provider, model, sandbox, +3 more.
Generate novel ideas with dynamic context gathering. --> Creative frameworks (SCAMPER, Design Thinking, etc.), domain context integration, idea clustering, feasibility analysis, and iterative refinement. Supports Gemini, Codex, and Claude.
Inputs: prompt (required), provider, model, methodology, +5 more.
Coordinated multi-gate review. Auto-selects the minimum set of research-grounded skill gates for a given task type (feature/bugfix/refactor/dependency-update) and runs them in a single structured pass. Produces gate-by-gate findings, blocking issues, and a final merge recommendation. Uses the AI Coding Agent Mitigator coordinator pattern.
Inputs: prompt (required), task_type (required), provider, model.
Deploy multiple AI agents to work on tasks collaboratively or independently. Strategies: 'parallel' (N agents on 1 task), 'sequential' (chained, each sees prior output), 'fan-out' (1 agent per task). Agents communicate via shared context to avoid conflicts and redundancy. Current agent mode: read-only.
Inputs: tasks (required), agentCount, strategy, provider, +4 more.
Retrieves cached chunks from a changeMode response. Use this to get subsequent chunks after receiving a partial changeMode response.
Inputs: cacheKey (required), chunkIndex (required).
Display help information for the configured AI provider CLI
Inputs: no named parameters.
Apply a single research-grounded skill gate to detect common AI coding mistakes. Choose the gate relevant to your current task stage: requirements-grounding, context-scope-discipline, dependency-verification, design-doc-and-architecture-gate, test-and-error-path-gate, secure-coding-and-validation-gate, code-review-and-change-gate, code-quality-enforcer, or deterministic-validation-gate. Based on academic research and professional engineering standards.
Inputs: prompt (required), skill (required), provider, model.
Echo
Inputs: prompt.
Test timeout prevention by running for a specified duration
Inputs: duration (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 10 tools
Most tools have distinct purposes, but ask-ai and brainstorm overlap in using AI models, and coordinate-review and mitigate-mistakes both involve code review gates. Descriptions help differentiate, but some confusion remains.
Names mix styles: some single-word (brainstorm, ping, Help), some hyphenated verb-noun (ask-ai, coordinate-review, deploy-agents, fetch-chunk, mitigate-mistakes), and 'Help' is capitalized. No consistent pattern.
With 10 tools covering agent status, deployment, AI queries, brainstorming, code review, and utilities, the count is well-scoped for a development assistant server. No unnecessary tools.
The tool set covers core workflows: AI interaction, agent orchestration, code review, and mistake detection. Missing tools for session management or configuration, but the surface is largely complete for its domain.
Shared memory MCP server for Claude Code, Codex, Gemini CLI and Cursor. Cited, editable.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
Real-time chat hub for AI agents — Claude Code, Cursor, Cline, Codex over MCP or REST.
