// SCAN REPORT

MCP Claude Code

15 tools. 10 can modify or destroy data without limits.

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

Last updated: 26 Jun 2026

10 can modify or destroy data

5 read-only

15 tools total

Community server · catalogue entry verified 26/06/2026

How to control MCP Claude Code ↓

TOOL MAP

What MCP Claude Code exposes to your agents

Read (5) Write / Execute (9) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous MCP Claude Code tools

Execute · High batch The server description explicitly states it can 'execute commands' and 'modify files'. Execute · High dispatch_agent The server-level description explicitly mentions executing commands and modifying files. Write · High content_replace The tool performs file content replacement, which is a Write operation (creates or modifies data reversibly). Write · High edit The tool's name 'edit' combined with server description stating it 'modifies files' and 'manage projects through direct file system interactions' indicates this creates or modifies files reversibly—a Write operation.

10 of MCP Claude Code's 15 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control MCP Claude Code

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

Rate limit write operations

{
  "content_replace": {
    "limits": [
      {
        "counter": "content_replace_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "directory_tree": {
    "limits": [
      {
        "counter": "directory_tree_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 MCP Claude Code — 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 MCP CLAUDE CODE →

Instant setup, no code required.

FULL CATALOGUE

All 15 MCP Claude Code tools

EXECUTE 2 tools

Execute batch batch Execute dispatch_agent dispatch_agent

WRITE 7 tools

Write content_replace content_replace Write edit edit Write grep_ast grep_ast Write multi_edit multi_edit Write notebook_edit notebook_edit Write todo_write todo_write Write write write

READ 5 tools

Read directory_tree directory_tree Read grep grep Read notebook_read notebook_read Read read read Read todo_read todo_read

OTHER 1 tools

Other think think

FAQ

Questions about MCP Claude Code

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

The MCP Claude Code server has 7 write tools including content_replace, edit, grep_ast. 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 MCP Claude Code.

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

15 tools across 2 categories: Read, Write. 5 are read-only. 10 can modify, create, or delete data.

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

Register the MCP Claude Code 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 MCP Claude Code tool call.

Deterministic rules across all 15 MCP Claude Code tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MCP CLAUDE CODE →

Instant setup, no code required.

15 MCP Claude Code tools catalogued and risk-classified — across an index of 43,000+ MCP servers.