// SCAN REPORT

Demo

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

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

Last updated: 3 Jul 2026

5 can modify or destroy data

5 read-only

10 tools total

Community server · catalogue entry verified 03/07/2026

How to control Demo ↓

TOOL MAP

What Demo exposes to your agents

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

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Demo tools

Execute · High analyze_image_with_openai This tool sends image data to an external OpenAI API endpoint, triggering an external operation with potential data exfiltration risks. Execute · Medium query_db Although described as read-only SELECT queries, this tool executes SQL against a local database. Write · Medium move_files_by_glob Moving files is a reversible write operation that modifies data locations without permanent deletion. Write · Medium make_directory This tool creates a new directory, which is a reversible write operation on the filesystem.

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

POLICY

How to control Demo

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

Rate limit write operations

{
  "make_directory": {
    "limits": [
      {
        "counter": "make_directory_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "inspect_file": {
    "limits": [
      {
        "counter": "inspect_file_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 Demo — 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 DEMO →

Instant setup, no code required.

FULL CATALOGUE

All 10 Demo tools

EXECUTE 2 tools

Execute analyze_image_with_openai Analyze an image file with an OpenAI vision-capable model. Execute query_db Run a read-only SELECT query against local SQLite demo.db.

WRITE 3 tools

Write make_directory Create a directory inside MCP_FILE_OPS_ROOT. Write move_file Move a file from source_path to destination_path inside MCP_FILE_OPS_ROOT. Write move_files_by_glob Move all files matching a glob pattern from source_dir into destination_dir.

READ 5 tools

Read inspect_file Return file metadata and content preview for text/csv/image workflows. Read list_directories List directories directly inside a folder within MCP_FILE_OPS_ROOT. Read list_files List files directly inside a folder within MCP_FILE_OPS_ROOT. Read read_file Read a UTF-8 text file inside MCP_FILE_OPS_ROOT. Read weather Return current weather for a city using wttr.in.

FAQ

Questions about Demo

How do I prevent bulk modifications through Demo? +

The Demo server has 3 write tools including make_directory, move_file, move_files_by_glob. 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 Demo.

How many tools does the Demo MCP server expose? +

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

How do I enforce a policy on Demo? +

Register the Demo 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 Demo tool call.

Deterministic rules across all 10 Demo tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON DEMO →

Instant setup, no code required.

10 Demo tools catalogued and risk-classified — across an index of 43,000+ MCP servers.