// SCAN REPORT

Claude Team MCP

18 tools. 4 can modify or destroy data without limits.

4 write tools that can modify data. Rate limits recommended.

Last updated: 28 Sept 2026

4 can modify or destroy data

14 read-only

18 tools total

Community server · catalogue entry checked 28/09/2026

How to control Claude Team MCP ↓

TOOL MAP

What Claude Team MCP exposes to your agents

Read (14) Write / Execute (4) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Claude Team MCP tools

Execute · High run_workflow run_workflow is an Execute category tool because it executes workflows whose effects depend on the workflow definition and arguments passed to it. Execute · High fix_bug A bug-fix tool that invokes an AI QA expert to fix bugs will likely write or modify code, and may execute code to verify the fix. Execute · High team_work This tool orchestrates multiple AI agents to autonomously execute complex development tasks with intelligent task distribution. Write · Low generate_commit_message This tool creates or modifies git commit metadata (a write operation), but with minimal risk.

4 of Claude Team MCP's 18 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Claude Team MCP

PolicyLayer is an MCP gateway — it sits between your AI agents and Claude Team MCP, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "generate_commit_message": {
    "limits": [
      {
        "counter": "generate_commit_message_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "analyze_project_structure": {
    "limits": [
      {
        "counter": "analyze_project_structure_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Claude Team MCP — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON CLAUDE TEAM →

Instant setup, no code required.

FULL CATALOGUE

All 18 Claude Team MCP tools

EXECUTE 3 tools

Execute fix_bug 让 QA 专家修复 Bug Execute run_workflow 使用指定工作流执行任务 Execute team_work 让 AI 开发团队协作完成任务。团队包含前端专家、后端专家、QA专家，会智能分配任务并互相协作。

WRITE 1 tools

Write generate_commit_message 根据代码变更生成 Git commit message

READ 14 tools

Read analyze_project_structure 分析项目结构，识别技术栈和架构 Read ask_expert 向特定专家咨询问题 Read code_review 让专家审查代码 Read cost_estimate 预估任务执行成本（Token 用量、预计耗时） Read explain_plan 解释 Tech Lead 会如何分配任务（不实际执行） Read history_context 获取最近的协作上下文，可用于继续之前的工作 Read history_get 获取某次协作的详细记录 Read history_list 查看团队协作历史记录列表 Read history_search 搜索协作历史记录 Read list_workflows 列出所有可用的工作流模板 Read read_project_files 读取项目文件内容，让专家了解代码上下文 Read suggest_workflow 根据任务自动推荐合适的工作流 Read team_dashboard 查看团队当前状态：可用专家、模型配置、最近活动 Read usage_stats 查看各模型的使用统计（调用次数、成功率、平均耗时）

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Claude Team MCP

How do I prevent bulk modifications through Claude Team MCP? +

The Claude Team MCP server has 1 write tools including generate_commit_message. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Claude Team MCP.

How many tools does the Claude Team MCP server expose? +

18 tools across 3 categories: Execute, Read, Write. 14 are read-only. 4 can modify, create, or delete data.

How do I enforce a policy on Claude Team MCP? +

Register the Claude Team MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Claude Team MCP tool call.

Deterministic rules across all 18 Claude Team MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON CLAUDE TEAM →

Instant setup, no code required.

18 Claude Team MCP tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Claude Team's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →