Skip to main content
Glama
nishimoto265

Agent Collaboration MCP Server

by nishimoto265
OverviewSchemaRelated ServersScoreDiscussions
Local

Agent Collaboration MCP Server

English version is here

複数のAIエージェントが協調して作業できるようにする完全自己完結型MCPサーバーです。このツールをClaude Codeなどのエージェントに使わせることで、エージェントが他のエージェントを起動・制御し、チームとして複雑なタスクを実行できます。

✨ 特徴

  • シンプルなアーキテクチャ: ペイン番号を直接指定する直感的な操作

  • 複数エージェント対応: Claude CodeとGeminiの同時制御

  • 柔軟なセッション管理: 複数プロジェクトの並行作業に対応

  • 高度な状態管理: エージェントの実行状態をリアルタイムで監視

Related MCP server: Terminal MCP Server

🎯 エージェント同士の協調作業

⚠️ 自動認証機能について
新しいエージェントの認証を自動化したい場合は、Playwright MCPが必要です。Playwright MCPがインストールされていない場合、認証は手動で行う必要があります。詳細は自動認証代行機能をご覧ください。

このMCPサーバーの主な用途は、エージェントが他のエージェントを管理することです。例えば：

  • ボスエージェントがタスクを分割し、複数のワーカーエージェントに割り振る

  • 各エージェントが得意分野で作業（Claude Codeはコーディング、Geminiは画像生成）

  • エージェント間でメッセージを送り合い、進捗を共有

  • 一つのエージェントが他のエージェントの作業結果を確認・統合

  • 自動認証代行: 新しいエージェントが認証を要求された場合、既存の認証済みエージェントが自動で認証を代行

🛠️ 提供ツール

エージェントが使用できる6つのツール：

1. start_agent - エージェントの起動

start_agent(target="multiagent:0.2", agentType="claude")
start_agent(target="multiagent:0.3", agentType="gemini")

指定したtmuxターゲットでAIエージェントを起動します。

  • target: tmuxターゲット形式（"session:window.pane"、例："multiagent:0.5"）

  • agentType: claude（一般的なコード開発）または gemini（画像生成タスク）

  • additionalArgs: 追加の引数（オプション）

2. get_agent_status - ステータス確認

get_agent_status()                          // 全エージェントの状態を確認
get_agent_status(target="multiagent:0.2")  // 特定ペインの詳細状態を確認
get_agent_status(target="multiagent:*")    // セッション内全ペインの状態確認

取得可能なステータス

ステータス

アイコン

説明

running_claude

✅

Claude Codeが実行中で入力待機状態

running_gemini

💎

Geminiが実行中で入力待機状態

auth_claude

🔐

Claude Codeが認証プロセス中

auth_gemini

🔑

Geminiが認証プロセス中

executing_claude

⚡

Claude実行中（ESC to interrupt表示）

stopped

⚫

エージェントが停止中またはシェル状態

3. send_message - メッセージ送信

send_message(target="multiagent:0.2", message="こんにちは")
send_message(target="multiagent:0.3", message="C-c", sendEnter=false) // Ctrl+C送信

指定したペインにメッセージや制御文字を送信します。高度なメッセージ送信機能付き。

4. capture_screen - 画面キャプチャ

capture_screen(target="multiagent:0.2")        // 全履歴キャプチャ
capture_screen(target="multiagent:0.3", lines=50) // 最後の50行

ペインの画面内容を取得します。

5. parallel_implement - 並列実装

parallel_implement(prompt="ユーザー認証機能を実装してください")
parallel_implement(prompt="リファクタリングを実行", workerCount=5, complexity="complex")

複数のワーカーエージェントが同じタスクを並列で実装し、ボスエージェントが最良の成果物を選択・統合します。

重要: この機能はGitリポジトリ内で実行する必要があります。各ワーカーは独自のGit worktreeで作業を行います。

  • prompt: 実装指示（必須）

  • workerCount: ワーカー数（デフォルト: 3）

  • complexity: タスクの複雑度（simple, medium, complex）

  • agentType: 使用するエージェント（claude, gemini）

  • autoMerge: 完了後の自動マージ（デフォルト: false）

6. get_parallel_status - 並列実装状態確認

get_parallel_status()                    // 全セッションの一覧を取得
get_parallel_status(sessionId="parallel_20240105_123456")  // 特定セッションの詳細

並列実装セッションの進捗状況を確認します。各ワーカーの作業状況、完了率、エラー情報などを取得できます。

📦 セットアップ

1. インストール

npm経由（推奨）:

npm install -g agent-collaboration-mcp@latest

GitHubから直接:

git clone https://github.com/nishimoto265/Agent_Collaboration_MCP.git
cd Agent_Collaboration_MCP
npm install

2. Claude Codeへの追加（推奨）

簡単な方法（CLIを使用）:

claude mcp add agent-collaboration npx agent-collaboration-mcp@latest

自動認証機能を使用する場合は、Playwright MCPも追加:

claude mcp add playwright npx @playwright/mcp@latest

または、JSON設定を使用:

  1. プロジェクトルートに.mcp.jsonを作成：

{
  "mcpServers": {
    "agent-collaboration": {
      "command": "npx",
      "args": ["agent-collaboration-mcp"]
    }
  }
}

  1. ローカルインストールの場合：

{
  "mcpServers": {
    "agent-collaboration": {
      "command": "node",
      "args": ["/absolute/path/to/Agent_Collaboration_MCP/index.js"]
    }
  }
}

3. tmuxセッションの準備

# デフォルトセッション（multiagent）を作成
tmux new-session -d -s multiagent

# 複数プロジェクトの場合
tmux new-session -d -s project1
tmux new-session -d -s project2

💡 使用例

基本的な使い方

// 1. エージェントを起動
start_agent(target="multiagent:0.2", agentType="claude")
start_agent(target="multiagent:0.3", agentType="claude")

// 2. ステータス確認
get_agent_status()

// 3. タスクを指示
send_message(target="multiagent:0.2", message="READMEを確認してください")
send_message(target="multiagent:0.3", message="テストを実行してください")

// 4. 結果を確認
capture_screen(target="multiagent:0.3")

複数セッションでの作業例

// プロジェクト1での作業
start_agent(target="project1:0.0", agentType="claude")
send_message(target="project1:0.0", message="バックエンドAPIを実装してください")

// プロジェクト2での並行作業
start_agent(target="project2:0.0", agentType="gemini")
send_message(target="project2:0.0", message="UIデザインを作成してください")

自動認証代行機能（オプション）

新しいエージェントの認証を自動化したい場合は、Playwright MCPを併用することで、既存の認証済みエージェントが新しいエージェントの認証を自動で代行できます。

// Playwright MCPがインストールされている場合の動作
start_agent(target="multiagent:0.5", agentType="claude")
// 認証が必要な場合、以下が自動実行されます：
// 1. 既存の認証済みエージェントを検出
// 2. 新エージェントの認証URLを抽出
// 3. Playwright MCPを使用してブラウザで自動認証
// 4. 認証コードを自動的に新エージェントに送信

マルチエージェント協調の例

// Boss エージェント（タスク管理）
start_agent(target="multiagent:0.0", agentType="claude")

// Worker エージェント群
start_agent(target="multiagent:0.1", agentType="claude")  // コード開発担当
start_agent(target="multiagent:0.2", agentType="gemini") // 画像生成担当
start_agent(target="multiagent:0.3", agentType="claude") // テスト担当

// Bossからタスク分割指示
send_message(target="multiagent:0.0", message="プロジェクトの進捗確認と各チームへのタスク分割をお願いします")

// 各Workerの状態監視
get_agent_status()

緊急停止・制御

// プロセスを停止
send_message(target="multiagent:0.2", message="C-c", sendEnter=false)

// 画面をクリア
send_message(target="multiagent:0.2", message="C-l", sendEnter=false)

🔧 前提条件

必須

  • Node.js 18以上

  • tmux

  • tmuxセッション: tmux new-session -d -s multiagent

オプション（認証自動化用）

  • Playwright MCP: エージェントの認証を自動化する場合に必要

🚀 高度な機能

柔軟なターゲット指定

  • セッション指定: 異なるプロジェクトで並行作業

  • ワイルドカード: multiagent:*で全ペインを対象に

  • 直感的な番号指定: 0, 1, 2...のシンプルな指定

精密な状態検出

  • リアルタイム監視: エージェントの実行状態を即座に判定

  • 複数状態の識別: 実行中、認証中、停止中などを正確に判別

  • アイコン付き表示: 視覚的に分かりやすい状態表示

🚨 トラブルシューティング

tmuxセッションが存在しない

# multiagentセッションを作成
tmux new-session -d -s multiagent

エージェントが起動しない

  • get_agent_status()で状態を確認

  • capture_screen()でエラーメッセージを確認

  • 認証代行システムが自動で問題を解決する場合が多い

メッセージが送信されない

  • エージェントが起動中かget_agent_status()で確認

  • tmuxセッションが存在するか確認

  • ターゲット形式が正しいか確認（"session:window.pane"）

📄 スクリプトのカスタマイズ

Agent Collaboration MCPはscripts/agent_tools/内のスクリプトを使用します。独自のエージェント起動方法やメッセージ送信方法がある場合は、これらのスクリプトをカスタマイズしてください：

  • agent_manager.sh: エージェント起動コマンドの定義

  • pane_controller.sh: メッセージ送信方法の定義

🤝 貢献

このプロジェクトへの貢献を歓迎します。バグ報告や機能提案をお願いします。

📄 ライセンス

MIT License

Available Tools

6 tools
capture_screenCapture ScreenC

Capture screen content from a tmux target

ParametersJSON Schema
NameRequiredDescriptionDefault
targetYestmux target in format "session:window.pane" (e.g., "multiagent:0.5")
linesNoNumber of lines to capture (default: all history)

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states what the tool does but lacks details on permissions needed, whether it's read-only or has side effects, error handling, or output format (e.g., text, image). This is inadequate for a tool that interacts with system resources.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that directly states the tool's function without unnecessary words. It's front-loaded and every part earns its place, making it highly concise and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of capturing screen content from a tmux target, with no annotations and no output schema, the description is incomplete. It doesn't explain what the capture returns (e.g., text output, file path), error conditions, or dependencies, leaving significant gaps for an AI agent to use it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema description coverage is 100%, so the schema already documents both parameters ('target' and 'lines') with clear descriptions. The description doesn't add any additional meaning beyond what's in the schema, such as examples of valid targets beyond the schema's format, making the baseline score appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('capture') and resource ('screen content from a tmux target'), making the purpose immediately understandable. However, it doesn't distinguish this tool from potential siblings like 'get_agent_status' or 'send_message', which might also involve tmux interactions, so it doesn't reach the highest score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. The description doesn't mention prerequisites (e.g., tmux must be running), exclusions, or how it relates to sibling tools like 'get_agent_status' that might provide status without capturing content.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_agent_statusGet Agent StatusC

Get status of agents

ParametersJSON Schema
NameRequiredDescriptionDefault
targetNotmux target in format "session:window.pane" (e.g., "multiagent:0.5") or "session:*" for all panes in session

TDQS

C2.7/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden but only states the action without behavioral details. It doesn't disclose whether this is a read-only operation, what permissions are needed, error conditions, or response format, which is insufficient for a tool with no annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise with a single, clear sentence. It's front-loaded and wastes no words, making it efficient for quick understanding, though this brevity contributes to gaps in other dimensions.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no annotations, no output schema, and a single parameter with full schema coverage, the description is incomplete. It lacks details on behavior, output, and usage context, making it inadequate for the tool's complexity and the absence of structured support.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema description coverage is 100%, so the input schema fully documents the 'target' parameter. The description adds no additional parameter semantics beyond what's in the schema, resulting in the baseline score of 3 for adequate but no extra value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Get status of agents' clearly states the verb ('Get') and resource ('status of agents'), but it's vague about what 'status' entails and doesn't distinguish from sibling tools like 'get_parallel_status'. It provides basic purpose but lacks specificity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. The description doesn't mention sibling tools, prerequisites, or specific contexts for usage, leaving the agent without direction on tool selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_parallel_statusGet Parallel Implementation StatusC

Get status of parallel implementation sessions

ParametersJSON Schema
NameRequiredDescriptionDefault
sessionIdNoSession ID (omit to list all sessions)

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden for behavioral disclosure. It states this is a 'Get status' operation, implying read-only behavior, but doesn't clarify whether this requires authentication, has rate limits, returns paginated results, or what happens when sessionId is omitted versus provided. The description is too minimal for a tool with potential behavioral complexity.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise - a single sentence that directly states the tool's purpose without any unnecessary words. It's perfectly front-loaded and every word earns its place, making it highly efficient for an agent to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no annotations and no output schema, the description is insufficiently complete. It doesn't explain what 'status' includes, what format results are returned in, whether it lists all sessions or just one, or how to interpret the output. For a status-checking tool with potential complexity, more context is needed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with the parameter 'sessionId' clearly documented in the schema. The description adds no additional parameter information beyond what the schema provides, so it meets the baseline expectation but doesn't enhance understanding of parameter usage or semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Get status') and target resource ('parallel implementation sessions'), which is specific and unambiguous. However, it doesn't differentiate from sibling tools like 'get_agent_status' or explain what distinguishes 'parallel implementation' from other types of sessions, preventing a perfect score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like 'get_agent_status' or 'parallel_implement'. It doesn't mention prerequisites, timing considerations, or any context that would help an agent decide between this and sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

parallel_implementStart Parallel ImplementationC

Start parallel implementation with multiple workers

ParametersJSON Schema
NameRequiredDescriptionDefault
promptYesImplementation instructions
workerCountNoNumber of workers (default: 3)
complexityNoTask complexitymedium
autoMergeNoAuto-merge after completion
agentTypeNoAgent type to useclaude

TDQS

C2.6/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description mentions 'multiple workers' which hints at concurrency, but doesn't explain what happens during implementation, whether this is a long-running process, what resources it consumes, how failures are handled, or what the expected output format might be. For a tool with 5 parameters and no annotations, this leaves significant behavioral questions unanswered.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise - just 7 words. While this is efficient, it borders on under-specification rather than optimal conciseness. Every word earns its place, but more context would be helpful. The structure is front-loaded with the core action, though it lacks supporting details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 5 parameters, no annotations, and no output schema, the description is insufficiently complete. It doesn't explain what 'parallel implementation' means, what gets implemented, what the workers do, or what the expected outcome is. For a tool with this level of complexity and no structured behavioral hints, the description should provide more context about the tool's operation and results.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all parameters are documented in the schema itself. The description adds no additional parameter information beyond what's already in the schema descriptions. The baseline score of 3 reflects adequate parameter documentation through the schema alone, with no value added by the description text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states the tool 'Start parallel implementation with multiple workers' which provides a basic verb+resource combination ('start' + 'parallel implementation'), but it's vague about what 'parallel implementation' actually means in this context. It doesn't distinguish this tool from sibling tools like 'start_agent' or 'get_parallel_status', leaving the specific purpose unclear beyond the general concept of initiating some parallel process.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. There's no mention of prerequisites, when this tool is appropriate versus other tools like 'start_agent' or 'send_message', or what scenarios warrant parallel implementation. The agent must infer usage context solely from the tool name and parameters.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

send_messageSend MessageB

Send a message to a tmux target. Control characters supported: C-c (stop), C-l (clear), etc.

ParametersJSON Schema
NameRequiredDescriptionDefault
targetYestmux target in format "session:window.pane" (e.g., "multiagent:0.5")
messageYesMessage to send (use C-c for Ctrl+C, C-l for Ctrl+L, etc.)
sendEnterNoWhether to send Enter after the message

TDQS

B3.1/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions control character support but lacks critical details such as whether this is a read/write operation, what happens if the target doesn't exist, error conditions, or any side effects. For a tool that sends messages to tmux sessions, this represents significant gaps in behavioral transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is appropriately sized with two sentences that efficiently convey core functionality. It's front-loaded with the main purpose and follows with specific details about control characters. There's no wasted text, though it could potentially integrate usage context more effectively.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of interacting with tmux sessions and the absence of both annotations and output schema, the description is insufficient. It doesn't explain what happens after sending the message, what success/failure looks like, or any system dependencies. For a tool with 3 parameters and no structured safety/behavior annotations, more comprehensive context is needed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all three parameters thoroughly. The description adds minimal value beyond the schema by mentioning control character examples (C-c, C-l) which are already covered in the schema's message parameter description. This meets the baseline expectation when schema coverage is complete.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action ('Send a message') and resource ('to a tmux target'), distinguishing it from sibling tools like capture_screen or get_agent_status. It provides precise functionality details including control character support, making the purpose unambiguous and distinct.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance is provided on when to use this tool versus alternatives. The description mentions control characters but doesn't specify scenarios where this tool is preferred over other tmux-related operations or when it should be avoided, leaving usage context implied rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

start_agentStart AgentB

Start an agent in a specific tmux target

ParametersJSON Schema
NameRequiredDescriptionDefault
targetYestmux target in format "session:window.pane" (e.g., "multiagent:0.5", "dev:1.3")
agentTypeNoType of agent to startclaude
additionalArgsNoAdditional arguments for the agent

TDQS

B3.2/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states what the tool does but lacks critical behavioral details: it doesn't specify what happens if the target is invalid, whether starting an agent is destructive to existing processes, authentication requirements, or error handling. For a tool that initiates processes, this gap is significant.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, direct sentence with zero wasted words. It front-loads the core purpose ('Start an agent') and efficiently specifies the context ('in a specific tmux target'). Every word earns its place, making it easy to parse quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of starting an agent (a mutation operation with no annotations and no output schema), the description is incomplete. It doesn't cover behavioral aspects like side effects, success/failure indicators, or interaction with sibling tools. For a tool with 3 parameters and potential system impacts, more context is needed to guide safe and effective use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema description coverage is 100%, so all parameters are documented in the schema itself. The description adds no additional parameter semantics beyond what's in the schema (e.g., it doesn't explain the tmux target format or agent types further). This meets the baseline for high schema coverage, but doesn't enhance understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Start an agent') and the resource ('in a specific tmux target'), making the purpose immediately understandable. It uses specific terminology that distinguishes it from sibling tools like 'get_agent_status' (which checks status) or 'send_message' (which communicates). The verb 'Start' is precise and unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., whether the tmux target must exist), when not to use it (e.g., if an agent is already running), or how it relates to siblings like 'get_agent_status' for monitoring. Without such context, the agent must infer usage from the tool name alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3.2/5.0
Disambiguation4/5

Most tools have distinct purposes: screen capture, agent status, parallel status, parallel implementation, messaging, and agent starting. However, 'get_agent_status' and 'get_parallel_status' could be slightly confused as both retrieve status information, though they target different entities (agents vs. parallel sessions). The descriptions clarify this distinction, making misselection unlikely.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern using snake_case: capture_screen, get_agent_status, get_parallel_status, parallel_implement, send_message, and start_agent. The verbs are clear and appropriate (e.g., 'capture', 'get', 'parallel_implement', 'send', 'start'), with no deviations or mixed conventions.

Tool Count5/5

With 6 tools, the count is well-scoped for an agent collaboration server. Each tool serves a specific role in managing agents, parallel sessions, and tmux interactions, and none appear redundant or unnecessary. This is a typical range (3-15 tools) that supports the server's purpose without being overwhelming.

Completeness3/5

The tool set covers core operations like starting agents, checking status, sending messages, and screen capture, but has notable gaps. For example, there are no tools to stop or manage agents beyond starting them (e.g., stop_agent, restart_agent), and parallel sessions lack update or termination capabilities. This may cause agents to work around limitations, but basic workflows are supported.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • tmux-bridge-mcp

    howardpen9
    A
    license
    A
    quality
    C
    maintenance
    Enables AI agents to communicate and coordinate across tmux panes, allowing them to read, type, and send messages to each other without manual copy-pasting.
    9
    60
    99
    MIT

  • wezterm-agent-mcp

    multiagentcognition
    F
    license
    Not graded
    quality
    D
    maintenance
    Enables orchestration of multiple AI coding agents (Claude Code, Gemini CLI, etc.) in isolated Wezterm panes, allowing one agent to spawn, monitor, and communicate with others across projects.
    10
    1

  • ddx-term-mcp

    Dudoxx
    A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI agents to execute commands in a shared tmux session that is simultaneously visible to a human via a web-based terminal UI.
    1
    MIT

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/nishimoto265/Agent_Collaboration_MCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server