// SCAN REPORT

Tools

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

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

Last updated: 26 Aug 2026

5 can modify or destroy data

12 read-only

17 tools total

Community server · catalogue entry checked 26/08/2026 · full schemas captured for 17 of 17 tools

How to control Tools ↓

TOOL MAP

What Tools exposes to your agents

Read (12) Write / Execute (5) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Tools tools

Execute · High cron_next Parses a standard 5-field cron expression (or 6-field with leading seconds, or a macro like @daily), validates it, describes it in plain Eng Execute · High edi_build Compiles structured JSON into standards-valid X12. The parts that get documents rejected are exactly the parts a language model cannot hold Execute · High edi_parse Reads a raw ASC X12 interchange and returns it as JSON: delimiters taken from the ISA header, the ISA/GS/ST envelope decoded, every segment Write · Medium tool_call Dispatches to any tool in the catalogue. Most clients cap how many tools they will hold at once — Cursor drops everything past roughly forty

5 of Tools's 17 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

{
  "time_convert": {
    "limits": [
      {
        "counter": "time_convert_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "edi_validate": {
    "limits": [
      {
        "counter": "edi_validate_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 17 Tools tools

EXECUTE 3 tools

Execute cron_next Parses a standard 5-field cron expression (or 6-field with leading seconds, or a macro like @daily), validates Execute edi_build Compiles structured JSON into standards-valid X12. The parts that get documents rejected are exactly the parts Execute edi_parse Reads a raw ASC X12 interchange and returns it as JSON: delimiters taken from the ISA header, the ISA/GS/ST en

WRITE 2 tools

Write time_convert Converts one instant into any number of timezones, handling daylight saving transitions correctly. Naive input Write tool_call Dispatches to any tool in the catalogue. Most clients cap how many tools they will hold at once — Cursor drops

READ 12 tools

Read edi_validate Runs the structural checks a trading partner runs before rejecting a file: control numbers matching between th Read hash Computes cryptographic digests and HMAC signatures. Returns hex and base64 at once, so a webhook signature can Read http_assert The difference between an agent believing it succeeded and knowing it did. http.check tells you a URL is alive Read http_check Resolves a URL and reports what actually happens to it — final status, the full redirect chain, content type a Read json_query Runs a JSONPath query and returns the matching values with their concrete paths. Supports property access, arr Read json_repair Takes JSON that almost parses and makes it parse: markdown code fences, prose wrapped around the object, trail Read math_eval Evaluates arithmetic with correct operator precedence, parentheses, exponentiation, factorials, named variable Read time_diff Computes the elapsed time between two instants: exact totals in each unit, a calendar breakdown (years/months/ Read time_now Returns the authoritative current time in one or more timezones, with UTC offset, ISO week number, day of year Read time_window Answers the questions a deadline actually poses: is this instant inside the window, how long until it opens or Read tool_describe Returns everything needed to call a tool correctly: its complete JSON Schema, every parameter with type and de Read tool_search Searches every tool by name, summary, description and keywords, and returns the closest matches with their end

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 2 write tools including time_convert, tool_call. 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? +

17 tools across 3 categories: Execute, Read, Write. 12 are read-only. 5 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 17 Tools tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON TOOLS →

Instant setup, no code required.

17 Tools tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Tools's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →