What is ai_collaboration_mcp_server CLAUDE.md?

Repository instructions for an MCP server that lets Claude Code work with several AI providers. MCP, or Model Context Protocol, is a standard way for an AI assistant to use external tools and services.

They help develop and verify the server, run unit or integration tests, configure Claude Code, check provider connections, and use its Docker development setup.

They collect the project overview and essential development commands in one place. This helps agents install, build, test, lint, format, and run the server consistently.

How atsuki-sakai/ai_collaboration_mcp_server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to atsuki-sakai/ai_collaboration_mcp_server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/atsuki-sakai/ai_collaboration_mcp_server/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/atsuki-sakai/ai_collaboration_mcp_server

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/atsuki-sakai/ai_collaboration_mcp_server/claude-md/github.svg)](https://agentmods.dev/instructions/atsuki-sakai/ai_collaboration_mcp_server/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/atsuki-sakai/ai_collaboration_mcp_server/claude-md"><img src="https://agentmods.dev/badge/instructions/atsuki-sakai/ai_collaboration_mcp_server/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/atsuki-sakai/ai_collaboration_mcp_server/claude-md"><img src="https://agentmods.dev/badge/instructions/atsuki-sakai/ai_collaboration_mcp_server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 823 This file is loaded in full into every session.

When invoked 823 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00823	$0.00823
Opus 5	$0.00411	$0.00411
Sonnet 5	$0.00165	$0.00165
Haiku 4.5	$0.00082	$0.00082

Measured 10d ago against content hash b3780dfc040b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ai_collaboration_mcp_server CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

This is an MCP (Model Context Protocol) server that enables multi-provider AI collaboration. It integrates with Claude Code to provide access to multiple AI providers (DeepSeek, OpenAI, Anthropic, O3) through various collaboration strategies.

Essential Commands

Development

pnpm install              # Install dependencies
pnpm run build           # Build TypeScript to dist/
pnpm run dev             # Run server in development mode
pnpm test                # Run all tests
pnpm run lint            # Run ESLint
pnpm run format          # Format code with Prettier

# Run specific test suites
pnpm run test:unit       # Unit tests only
pnpm run test:integration # Integration tests
pnpm run test:coverage   # Generate coverage report

# Setup and verification
pnpm run setup:claude-code  # Configure Claude Code integration
pnpm run verify-deepseek    # Test DeepSeek API connection

Docker Operations

pnpm run docker:build    # Build Docker image
pnpm run docker:dev      # Run with docker-compose (development)
pnpm run docker:prod     # Run with docker-compose (production)

Architecture

The codebase follows dependency injection patterns using InversifyJS:

Core Framework (src/core/): DI container, logging, configuration
Providers (src/providers/): AI provider implementations (DeepSeek, OpenAI, etc.)
Strategies (src/strategies/): Collaboration patterns (parallel, sequential, consensus, iterative)
MCP Server (src/server/): Protocol implementation and tool registration
Services (src/services/): Caching, metrics, search, synthesis

Key Integration Points

Entry Point: src/index.ts - Main server initialization
DI Container: src/core/container.ts - All service bindings
MCP Tools: src/tools/ - Collaborate, review, compare, refine tools
Configuration: config/default.yaml + environment-specific overrides

Read the full file on GitHub · 95 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

10d ago First seen · 95 lines · 823 tokens per session scan A b3780dfc040b

Subscribe to this mod's changes

ai_collaboration_mcp_server CLAUDE.md is an instructions file published in the GitHub repository atsuki-sakai/ai_collaboration_mcp_server (1 stars, last pushed 1y ago), licensed MIT. It adds 823 tokens to every session, about $0.0041 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

ai_collaboration_mcp_server: Instructions file for Claude Code