// SCAN REPORT

Claude Code

3 tools. 2 can modify or destroy data without limits.

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

Last updated: 12 Jun 2026

2 can modify or destroy data

1 read-only

3 tools total

Community server · catalogue entry verified 12/06/2026

How to control Claude Code ↓

TOOL MAP

What Claude Code exposes to your agents

Read (1) Write / Execute (2) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Claude Code tools

Execute · High claude_code_session The tool can list/inspect sessions (Read), but also cancel or interrupt them (Execute/Destructive). Execute · Critical claude_code_reply This tool continues an existing Claude Code session that enables autonomous coding tasks.

2 of Claude Code's 3 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 Code

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

Cap read operations

{
  "claude_code_check": {
    "limits": [
      {
        "counter": "claude_code_check_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 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 CLAUDE CODE →

Free to start. No card required.

FULL CATALOGUE

All 3 Claude Code tools

EXECUTE 2 tools

Execute claude_code_session List, inspect, cancel, or interrupt sessions. Execute claude_code_reply Send a follow-up to an existing session. Reuse the same sessionId instead of starting a new claude_code sessio

READ 1 tools

Read claude_code_check Poll session state or answer a pending permission request.\n\nPOLLING FREQUENCY: Do NOT poll every turn. Claud

EXPLORE

Related servers

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

FAQ

Questions about Claude Code

Is the Claude Code MCP server safe to use without restrictions? +

The Claude Code server is primarily read-only with 1 read tools. While it cannot modify data, an agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up costs. Rate limiting is still recommended.

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

3 tools across 3 categories: Destructive, Read, Write. 1 are read-only. 2 can modify, create, or delete data.

How do I enforce a policy on Claude Code? +

Register the 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 Claude Code tool call.

Deterministic rules across all 3 Claude Code tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON CLAUDE CODE →

Free to start. No card required.

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