// SCAN REPORT

Claude Viewer

5 tools. 1 can modify or destroy data without limits.

1 write tool that can modify data. Rate limits recommended.

Last updated: 4 Jul 2026

1 can modify or destroy data

4 read-only

5 tools total

Community server · catalogue entry verified 04/07/2026

How to control Claude Viewer ↓

TOOL MAP

What Claude Viewer exposes to your agents

Read (4) Write / Execute (1) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Claude Viewer tools

Execute · Medium open_dashboard This tool starts a web server process and triggers a browser action (opening a URL), both of which are external operations with side effects.

1 of Claude Viewer's 5 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 Viewer

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

Cap read operations

{
  "get_claude_users": {
    "limits": [
      {
        "counter": "get_claude_users_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 Viewer — 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 VIEWER →

Instant setup, no code required.

FULL CATALOGUE

All 5 Claude Viewer tools

EXECUTE 1 tools

Execute open_dashboard Start the Claude Viewer web server and open the dashboard in your default browser

READ 4 tools

Read get_claude_users Get list of users with Claude Code conversation history on this machine Read get_conversation_details Get full transcript and details of a specific conversation session Read get_conversations Get Claude Code conversations with optional filters (username, search text, project, date range) Read get_stats Get aggregated statistics for Claude Code usage (tokens, models, tools, daily stats)

FAQ

Questions about Claude Viewer

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

The Claude Viewer server is primarily read-only with 4 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 Viewer MCP server expose? +

5 tools across 2 categories: Read, Write. 4 are read-only. 1 can modify, create, or delete data.

How do I enforce a policy on Claude Viewer? +

Register the Claude Viewer 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 Viewer tool call.

Deterministic rules across all 5 Claude Viewer tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON CLAUDE VIEWER →

Instant setup, no code required.

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