// SCAN REPORT

Code Analysis MCP Server

24 tools. 17 can modify or destroy data without limits.

4 destructive tools with no built-in limits. Policy required.

Last updated: 3 Jul 2026

17 can modify or destroy data

7 read-only

24 tools total

Community server · catalogue entry verified 03/07/2026

How to control Code Analysis MCP Server ↓

TOOL MAP

What Code Analysis MCP Server exposes to your agents

Read (7) Write / Execute (13) Destructive / Financial (4)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Code Analysis MCP Server tools

Destructive · High delete_list_variable Any delete operation that removes data from files or code structures is classified as Destructive, as it cannot be undone. Destructive · Medium delete_plan The tool performs an irreversible operation (deletion) on stored plan data. Destructive · Low delete_todo The tool deletes a todo item, which is an irreversible removal of data. Destructive · Medium remove_from_list_variable Removing an item from a list variable is a destructive operation in that the item is deleted/removed, likely irreversibly unless there is an undo mechanism (none described).

17 of Code Analysis MCP Server's 24 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Code Analysis MCP Server

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

Deny destructive operations

{
  "delete_list_variable": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "append_to_list_variable": {
    "limits": [
      {
        "counter": "append_to_list_variable_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_file_status": {
    "limits": [
      {
        "counter": "get_file_status_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 Code Analysis MCP Server — 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 CODE ANALYSIS →

Instant setup, no code required.

FULL CATALOGUE

All 24 Code Analysis MCP Server tools

DESTRUCTIVE 4 tools

Destructive delete_list_variable 删除列表变量 Destructive delete_plan 删除计划 Destructive delete_todo 删除待办事项 Destructive remove_from_list_variable 从列表变量删除项

WRITE 13 tools

Write append_to_list_variable 向列表变量添加项 Write audit_architecture_consistency 以资深软件架构师的视角对新架构代码进行严格的一致性审计，通过添加注释和异常标记所有与原架构不一致的地方。在审计完成后会修改新架构代码，提供参考注释，并将将不一致内容使用raise NotImplementedError替 Write create_doc 创建目录的文档（已实现功能的说明） Write create_list_variable 创建列表变量（如审计豁免规则等） Write create_plan 创建计划 Write create_todo 创建待办事项（必须关联到某个计划） Write finish_todo 完成待办事项（标记为completed并记录git日志） Write move_todo 移动待办事项到列表开头或结尾 Write update_doc 更新目录的文档 Write update_file_status 更新文件审计状态 Write update_list_variable 更新列表变量 Write update_plan 更新计划 Write update_recent_changes 更新最近的更改记录（由AI调用，合并现有记录和新的更改）

READ 7 tools

Read get_file_status 获取文件审计状态 Read get_recent_changes 获取最近的更改记录 Read list_file_status 列出文件审计状态（返回Markdown表格） Read read_doc 读取目录的文档 Read read_list_variable 读取列表变量 Read read_plan 读取计划 Read read_todos 读取待办事项

EXPLORE

Related servers

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

FAQ

Questions about Code Analysis MCP Server

Can an AI agent delete data through the Code Analysis MCP Server MCP server? +

Yes. The Code Analysis MCP Server server exposes 4 destructive tools including delete_list_variable, delete_plan, delete_todo. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Code Analysis MCP Server? +

The Code Analysis MCP Server server has 13 write tools including append_to_list_variable, audit_architecture_consistency, create_doc. 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 Code Analysis MCP Server.

How many tools does the Code Analysis MCP Server MCP server expose? +

24 tools across 3 categories: Destructive, Read, Write. 7 are read-only. 17 can modify, create, or delete data.

How do I enforce a policy on Code Analysis MCP Server? +

Register the Code Analysis MCP Server 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 Code Analysis MCP Server tool call.

Deterministic rules across all 24 Code Analysis MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON CODE ANALYSIS →

Instant setup, no code required.

24 Code Analysis MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.