// SCAN REPORT

MCP Developer Server

58 tools. 31 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 4 Jul 2026

31 can modify or destroy data

27 read-only

58 tools total

Community server · catalogue entry verified 04/07/2026

How to control MCP Developer Server ↓

TOOL MAP

What MCP Developer Server exposes to your agents

Read (27) Write / Execute (30) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous MCP Developer Server tools

Destructive · High delete_container This tool performs an irreversible destructive action: it removes a Docker container entirely. Execute · High execute_command This tool runs commands inside Docker containers with effects dependent on the command arguments provided. Execute · High playwright_launch_browser This is an Execute category tool because it triggers external operations (browser automation) whose effects depend on arguments (which URL to visit, what actions to perform). Execute · High playwright_navigate This tool executes browser automation commands that can interact with arbitrary websites, trigger network requests, and load remote content.

31 of MCP Developer Server's 58 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 Developer Server

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

Deny destructive operations

{
  "delete_container": {
    "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

{
  "create_container_backup": {
    "limits": [
      {
        "counter": "create_container_backup_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "find_module": {
    "limits": [
      {
        "counter": "find_module_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 Developer 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 MCP DEVELOPER →

Instant setup, no code required.

FULL CATALOGUE

All 58 MCP Developer Server tools

DESTRUCTIVE 1 tools

Destructive delete_container Delete a container (stops and removes it)

EXECUTE 19 tools

Execute ai_code_analysis Perform AI-powered code analysis and suggestions Execute create_container Create and start a new Docker container that runs indefinitely Execute create_dev_environment Create a development environment with pre-configured tools Execute execute_command Execute a command in a running container Execute firecrawl_crawl firecrawl_crawl Execute inspect_container Inspects the container, and runs the command docker command Execute playwright_click Click an element on a Playwright page Execute playwright_create_page Create a new page in a Playwright browser Execute playwright_launch_browser Launch a new Playwright browser instance (chromium, firefox, or webkit). Supports headless, so try to use Head Execute playwright_navigate Navigate to a URL in a Playwright page Execute playwright_screenshot Take a screenshot of a Playwright page Execute playwright_type Type text into an element on a Playwright page Execute restart_container Restart a container Execute selenium_click Click an element using Selenium Execute selenium_launch_driver Launch a Selenium WebDriver (chrome or firefox) Execute selenium_navigate Navigate to a URL using Selenium Execute selenium_type Type text into an element using Selenium Execute start_container Start a stopped container Execute stop_container Stop a running container (without removing it)

WRITE 11 tools

Write create_container_backup Create a backup of a container and its data Write create_docker_compose Generate a docker-compose.yml file for multi-service applications Write create_dockerfile Generate a Dockerfile template for the specified language Write create_github_workflow Generate GitHub Actions workflow file Write create_makefile Generate a Makefile for common project tasks Write create_workspace_backup Create a backup of the shared workspace Write generate_project_template Generate a project template with common structure and files Write save_artifact Saves any code based languages, e.g. Python or Go. Write save_markdown Save notes, or any markdown or HTML based languages for future use. Write setup_ci_cd_pipeline Setup a complete CI/CD pipeline with all necessary files Write upload_file Upload a file to the shared workspace

READ 27 tools

Read find_module find_module Read firecrawl_scrape firecrawl_scrape Read firecrawl_status Check if Firecrawl services are available Read get_container_logs Get logs from a container Read get_cve_data Fetch CVE data from the NVD API. Read get_devdocs_content Get the full content of a specific documentation page from DevDocs Read get_gpu_status Get GPU status and availability (NVIDIA and AMD) Read get_quick_reference Get a quick reference for a programming language or specific topic Read get_server_status Get comprehensive server status and health information Read learn_more_llms_format learn_more_llms_format Read list Shows the entire content of the Markdown and Artifacts directory from the save_markdown and save_artifact feat Read list_allowed_images List allowed Docker images that can be used to create containers Read list_browser_instances List all active browser instances Read list_containers List all active containers Read list_devdocs_available List all available documentation sets in DevDocs Read list_workspace_files List files in the shared workspace Read monitor_container_performance Monitor performance metrics for a specific container Read monitor_system_resources Monitor system CPU, memory, disk, and network usage Read playwright_get_text Get text content from an element on a Playwright page Read read Reads a file from the directories. Please specify if it is a Artifact or if its a note. Read request_llms_txtfile request_llms_txtfile Read search_devdocs Search through DevDocs documentation Read searxng_get_categories Get list of available search categories from SearXNG instance. Read searxng_get_engines Get list of available search engines from SearXNG instance. Read searxng_search searxng_search Read searxng_status Check SearXNG instance status and capabilities. Read searxng_suggestions Get search suggestions from SearXNG.

EXPLORE

Related servers

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

FAQ

Questions about MCP Developer Server

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

Yes. The MCP Developer Server server exposes 1 destructive tools including delete_container. 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 MCP Developer Server? +

The MCP Developer Server server has 11 write tools including create_container_backup, create_docker_compose, create_dockerfile. 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 Developer Server.

How many tools does the MCP Developer Server MCP server expose? +

58 tools across 4 categories: Destructive, Execute, Read, Write. 27 are read-only. 31 can modify, create, or delete data.

How do I enforce a policy on MCP Developer Server? +

Register the MCP Developer 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 MCP Developer Server tool call.

Deterministic rules across all 58 MCP Developer Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MCP DEVELOPER →

Instant setup, no code required.

58 MCP Developer Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.