// SCAN REPORT

Tools

29 tools. 16 can modify or destroy data without limits.

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

Last updated: 6 Jul 2026

16 can modify or destroy data

13 read-only

29 tools total

Verified server · catalogue entry verified 06/07/2026 · full schemas captured for 28 of 29 tools

How to control Tools ↓

TOOL MAP

What Tools exposes to your agents

Read (13) Write / Execute (16) Destructive / Financial (0)

Running more than one server? Check your whole stack →

CONTEXT-WINDOW COST

What Tools costs in tokens

3,399 tokens of tool definitions, loaded on every request

1.7% of a 200k context window

278 heaviest tool: cron_task_create

Full per-tool breakdown → Model it in the token calculator →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Tools tools

Write · Medium cron_task_create This tool creates a new scheduled/cron task, which is a Write operation (creating new data/configuration). Write · Low url_shorten This tool creates or modifies data (new short URL mappings) in a reversible manner. Write · Medium cron_task_done This tool modifies the state of an existing scheduled task (marking it complete/failed) but does not delete or irreversibly destroy data. Write · Medium file_generate This tool creates new files programmatically, which is a Write operation.

16 of Tools's 29 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Tools

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

Rate limit write operations

{
  "ai_text_generate": {
    "limits": [
      {
        "counter": "ai_text_generate_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "base_convert": {
    "limits": [
      {
        "counter": "base_convert_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 Tools — 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 TOOLS →

Instant setup, no code required.

FULL CATALOGUE

All 29 Tools tools

WRITE 16 tools

Write ai_text_generate AI-powered text generation: copywriting, naming, slogans, catchy titles, praise/replies, couplets. Powered by Write cron_task_create Create a scheduled task with cron expression. For AI agents to manage daily check-ins, monitoring, reminders e Write cron_task_done Mark a scheduled task as completed or failed. Supports failure tracking and auto-retry. Write file_generate Generate CSV/TSV/JSON file from structured data array. Returns base64-encoded file and raw text. Write html_entity Encode or decode HTML entities. Write idea_submit Submit a new idea or feature request to the JieBang ideas board. Supports categorization, priority, and source Write image_convert Convert image format to WebP/AVIF/PNG/JPEG with optional resize and quality control. Write json_yaml_convert Convert between JSON and YAML formats. Auto-detects direction. Write meta_desc_generate Generate SEO-friendly meta description (120-160 chars) from title, keyword, and content. Includes call-to-acti Write qrcode_generate Generate QR code for text or URL. Returns SVG data URI. Write sql_format Beautify, minify, or uppercase SQL keywords. Write text_humanize Rewrite AI-generated text to sound naturally human-written. Supports Chinese and English. Reduces AI detection Write text_rewrite Rewrite text with different styles while preserving meaning. Modes: standard (natural), creative (expressive), Write text_summarize Summarize text into concise version. Lengths: short (1-2 sentences), medium (3-5 sentences), long (full paragr Write url_shorten Create a short link for any URL. Returns short URL and click tracking. Free: 100 links/day. Write xml_format Beautify or minify XML code.

READ 13 tools

Read base_convert Convert numbers between decimal, binary, octal, hexadecimal. Read cron_parse Parse cron expression to human-readable description with next 5 run times. Read cron_task_list List scheduled tasks. Use due=true to see only tasks that need action now. Read cron_task_logs Get execution history/logs for a scheduled task. Shows past completion times, success/failure status, and coun Read cron_task_templates Get preset task templates with common cron schedules (daily, weekday, hourly, stock market, etc.). Use these t Read file_analyze Analyze tabular data: detect column types, compute stats (min/max/mean/median for numbers, top values for text Read file_parse Parse CSV/TSV/JSON/XML file content to structured JSON. Auto-detects format and column types. Returns columns, Read idea_list List ideas from the JieBang ideas board. Filter by status, sort by votes. View community feature requests and Read keyword_extract Extract keywords and key phrases from text with search intent classification. Returns 10-20 keywords sorted by Read meta_extract Extract SEO meta tags from any URL. Returns title, description, OG tags, Twitter cards, structured data, and S Read seo_check Quick SEO health check for any URL. Returns score and issues list. Read seo_title_generate Generate multiple SEO-optimized article titles from a keyword. Diverse styles: question, number, list, compari Read timezone_convert Convert datetime between time zones.

EXPLORE

Related servers

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

FAQ

Questions about Tools

How do I prevent bulk modifications through Tools? +

The Tools server has 16 write tools including ai_text_generate, cron_task_create, cron_task_done. 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 Tools.

How many tools does the Tools MCP server expose? +

29 tools across 3 categories: Execute, Read, Write. 13 are read-only. 16 can modify, create, or delete data.

How do I enforce a policy on Tools? +

Register the Tools 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 Tools tool call.

Deterministic rules across all 29 Tools tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON TOOLS →

Instant setup, no code required.

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