Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Agent Data Tools: Utilities

Owner verified

REMOTE · AGENT-DATA-TOOLS.REVMESH2074.WORKERS.DEV

74 tools: JSON repair, CSV, hashes, cron, dates, units, validators. 25 free calls.

68 Trust /100

Last scanned (6 hours ago)

Scores higher than 57% of remote servers

Reachable. Last reached 24 Oct 2026.

Category Developer Tools

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security69
Transport & Reachability100
Schema Quality & AI Usability72
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 9447 tokens (~149/item across 63 items; 63 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management10
  • Stability check failed: schema churn in the 5 days we've observed: 0 tool removals, 7 breaking changes, 0 auth/transport breaks, 11 additions. See how to fix → Fail
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "json_minify" implies "remove" and declares readOnlyHint instead, contradicting what its own name says it does. See how to fix → Fail
  • An AI judge read all 64 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 23 Oct 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “validate_luhn” rewrote its description, which is the text the model reads security
    • Schema quality: 7453 → 9447 ▼ functional
    • Schema quality: 7453 → 9443 ▼ functional
    • Server version: 1.51.3 → 1.52.0 functional
    • Server version: 1.50.5 → 1.51.3 functional
    • New tool “calc_age” functional
    • New tool “calc_bmi” functional
    • New tool “calc_compound_interest” functional
    • New tool “calc_loan” functional
    • New tool “calc_tip” functional
    • New tool “json_schema” functional
    • New tool “qr” functional
    • New tool “text_caesar” functional
    • New tool “text_lorem” functional
    • New tool “text_morse” functional
    • New tool “xml_to_json” functional
    • “calc_loan” reworded the description of “years” cosmetic
    • Tool “color” changed its title: Convert a colour → Color converter, hex to RGB cosmetic
    • Tool “validate_luhn” changed its title: Luhn check digit → Credit card validation (Luhn) cosmetic
  • 22 Oct 26 +1
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “base64_decode” rewrote its description, which is the text the model reads security
    • Tool “base64_encode” rewrote its description, which is the text the model reads security
    • Tool “case” rewrote its description, which is the text the model reads security
    • Tool “coin” rewrote its description, which is the text the model reads security
    • Tool “color” rewrote its description, which is the text the model reads security
    • Tool “color_contrast” rewrote its description, which is the text the model reads security
    • Tool “cron_next” rewrote its description, which is the text the model reads security
    • Tool “csv_to_json” rewrote its description, which is the text the model reads security
    • Tool “date_add” rewrote its description, which is the text the model reads security
    • Tool “date_diff” rewrote its description, which is the text the model reads security
    • Tool “date_info” rewrote its description, which is the text the model reads security
    • Tool “dice” rewrote its description, which is the text the model reads security
    • Tool “echo” rewrote its description, which is the text the model reads security
    • Tool “hash” rewrote its description, which is the text the model reads security
    • Tool “hmac” rewrote its description, which is the text the model reads security
    • Tool “html_to_text” rewrote its description, which is the text the model reads security
    • Tool “http_status” rewrote its description, which is the text the model reads security
    • Tool “ip_cidr” rewrote its description, which is the text the model reads security
    • Tool “ip_info” rewrote its description, which is the text the model reads security
    • Tool “json_format” rewrote its description, which is the text the model reads security
    • Tool “json_minify” rewrote its description, which is the text the model reads security
    • Tool “json_repair” rewrote its description, which is the text the model reads security
    • Tool “json_to_csv” rewrote its description, which is the text the model reads security
    • Tool “json_validate” rewrote its description, which is the text the model reads security
    • Tool “jwt_decode” rewrote its description, which is the text the model reads security
    • Tool “magic_8_ball” rewrote its description, which is the text the model reads security
    • Tool “markdown_to_html” rewrote its description, which is the text the model reads security
    • Tool “mime” rewrote its description, which is the text the model reads security
    • Tool “number_roman” rewrote its description, which is the text the model reads security
    • Tool “number_words” rewrote its description, which is the text the model reads security
    • Tool “ping” rewrote its description, which is the text the model reads security
    • Tool “random_color” rewrote its description, which is the text the model reads security
    • Tool “random_number” rewrote its description, which is the text the model reads security
    • Tool “random_password” rewrote its description, which is the text the model reads security
    • Tool “random_pick” rewrote its description, which is the text the model reads security
    • Tool “random_shuffle” rewrote its description, which is the text the model reads security
    • Tool “random_teams” rewrote its description, which is the text the model reads security
    • Tool “semver” rewrote its description, which is the text the model reads security
    • Tool “slug” rewrote its description, which is the text the model reads security
    • Tool “text_diff” rewrote its description, which is the text the model reads security
    • Tool “text_extract” rewrote its description, which is the text the model reads security
    • Tool “text_stats” rewrote its description, which is the text the model reads security
    • Tool “units_convert” rewrote its description, which is the text the model reads security
    • Tool “unix” rewrote its description, which is the text the model reads security
    • Tool “url_decode” rewrote its description, which is the text the model reads security
    • Tool “url_encode” rewrote its description, which is the text the model reads security
    • Tool “url_parse” rewrote its description, which is the text the model reads security
    • Tool “uuid” rewrote its description, which is the text the model reads security
    • Tool “validate_iban” rewrote its description, which is the text the model reads security
    • Tool “validate_isbn” rewrote its description, which is the text the model reads security
    • Tool “validate_luhn” rewrote its description, which is the text the model reads security
    • Tool “yes_no” rewrote its description, which is the text the model reads security
    • Server version: 1.50.3 → 1.50.5 functional
    • Server version: 1.50.2 → 1.50.3 functional
    • Server version: 1.50.1 → 1.50.2 functional
    • Server version: 1.49.1 → 1.50.1 functional
    • Server version: 1.48.6 → 1.49.1 functional
    • Server version: 1.48.4 → 1.48.6 functional
    • Server version: 1.48.2 → 1.48.4 functional
    • Server version: 1.48.0 → 1.48.2 functional
    • Server version: 1.47.15 → 1.48.0 functional
    • Server version: 1.47.7 → 1.47.15 functional
    • Server version: 1.47.5 → 1.47.7 functional
    • Server version: 1.45.3 → 1.47.5 functional
    • Tool “color_contrast” changed its title: Colour contrast check (WCAG) → Color contrast check (WCAG) cosmetic
    • Tool “date_diff” changed its title: Difference between two dates → Date difference between dates cosmetic
    • Tool “hash” changed its title: Hash text → Hash text, SHA-256 hash cosmetic
    • Tool “jwt_decode” changed its title: Decode a JWT → JWT decode cosmetic
    • Tool “random_password” changed its title: Generate a password → Password generator cosmetic
    • Tool “slug” changed its title: Make a URL slug → Slugify, make a URL slug cosmetic
    • Tool “text_diff” changed its title: Compare two texts → Text diff, compare two texts cosmetic
    • Tool “text_stats” changed its title: Text statistics and readability → Word count and readability cosmetic
    • Tool “units_convert” changed its title: Convert units → Unit conversion cosmetic
    • Tool “uuid” changed its title: Generate UUIDs → UUID generator cosmetic
    • Tool “validate_isbn” changed its title: Validate an ISBN → ISBN check, validate an ISBN cosmetic
    • Tool “json_repair” changed its title: Repair broken JSON → JSON repair: fix broken JSON cosmetic
    • Tool “validate_iban” changed its title: Validate an IBAN → IBAN validation: validate an IBAN cosmetic
  • 21 Oct 26 0
    • Server version: 1.45.1 → 1.45.3 functional
    • Server version: 1.45.0 → 1.45.1 functional
    • Server version: 1.44.0 → 1.45.0 functional
  • 20 Oct 26 0
    • Stability: unverified → fail ▼ security
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “cron_next” rewrote its description, which is the text the model reads security
    • Tool “csv_to_json” rewrote its description, which is the text the model reads security
    • Tool “date_add” rewrote its description, which is the text the model reads security
    • Tool “hash” rewrote its description, which is the text the model reads security
    • Tool “hmac” rewrote its description, which is the text the model reads security
    • Tool “ip_cidr” rewrote its description, which is the text the model reads security
    • Tool “json_format” rewrote its description, which is the text the model reads security
    • Tool “number_roman” rewrote its description, which is the text the model reads security
    • Tool “random_color” rewrote its description, which is the text the model reads security
    • Tool “random_number” rewrote its description, which is the text the model reads security
    • Tool “random_password” rewrote its description, which is the text the model reads security
    • Tool “random_pick” rewrote its description, which is the text the model reads security
    • Tool “random_teams” rewrote its description, which is the text the model reads security
    • Tool “slug” rewrote its description, which is the text the model reads security
    • Tool “url_decode” rewrote its description, which is the text the model reads security
    • Tool “ping” rewrote its description, which is the text the model reads security
    • Tool “yes_no” rewrote its description, which is the text the model reads security
    • “csv_to_json” changed the type of “numbers”: string → string|number|boolean ▼ functional
    • “json_format” changed the type of “indent”: string → string|number|boolean ▼ functional
    • “json_format” changed the type of “sortKeys”: string → string|number|boolean ▼ functional
    • “random_number” changed the type of “unique”: string → string|number|boolean ▼ functional
    • “random_password” changed the type of “symbols”: string → string|number|boolean ▼ functional
    • “unix” changed the type of “value”: string → string|number|boolean ▼ functional
    • “url_decode” changed the type of “plus”: string → string|number|boolean ▼ functional
    • “validate_luhn” changed the type of “number”: string → string|number|boolean ▼ functional
    • Stability: unverified → 0.03 ▲ functional
    • Server version: 1.41.0 → 1.44.0 functional
    • Server version: 1.40.0 → 1.41.0 functional
    • Server version: 1.39.3 → 1.40.0 functional
    • Server version: 1.37.1 → 1.39.3 functional
    • Server version: 1.36.1 → 1.37.1 functional
    • Server version: 1.35.3 → 1.36.1 functional
    • “date_add” added an optional parameter “hours” cosmetic
    • “date_add” added an optional parameter “minutes” cosmetic
    • “date_add” added an optional parameter “weeks” cosmetic
    • “date_add” added an optional parameter “years” cosmetic
    • “ping” added an optional parameter “only” cosmetic
    • “yes_no” added an optional parameter “only” cosmetic
    • “ping” reworded the description of “only” cosmetic
    • “yes_no” reworded the description of “only” cosmetic
    • “date_info” made “date” optional cosmetic
  • 19 Oct 26 67

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 24 Oct 2026 · Probed https://agent-data-tools.revmesh2074.workers.dev/mcp/utilities

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=revmesh2074.workers.dev CN=YE1,O=Let's Encrypt,C=US 9 Oct 2026 7 Jan 2027 ECDSA 256 ECDSA-SHA384 538c1f22b424c14420d956229d7db3228c3
SANs: *.revmesh2074.workers.dev, revmesh2074.workers.dev
CN=YE1,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 5ddd70dd31f801c85c186a7a04b80afe
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of agent-data-tools.revmesh2074.workers.dev. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
dev. present 60074 8 Verified
workers.dev. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=31536000

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://agent-data-tools.revmesh2074.workers.dev/mcp/utilities Verified 200
http (plaintext) http://agent-data-tools.revmesh2074.workers.dev/mcp/utilities Inconclusive 405
MCP tools · 63 exposed · ~8,930 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
text_morse ~155

Translate text to international Morse code (letters separated by spaces, words by /) or Morse code back to text; the direction is detected automatically or set with mode. Letters, digits and common punctuation are supported; anything else is reported, not guessed. Use for puzzles, radio practice and fun messages. Example: text=SOS help. Price $0.01/call via x402 USDC or a card key (/credits), first 25 free; failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

NameTypeReqDescription
modestring–auto (default), encode or decode
textstringyesText, or Morse code made of . - spaces and /

No output schema declared.

No examples provided.

text_stats ~126

Count characters, words, sentences and paragraphs, estimate reading and speaking time, and compute the Flesch reading-ease score and grade level for English text. Use to check the length and readability of a draft. Example: text=The quick brown fox jumps over the lazy dog. It was not amused.. Price $0.01/call via x402 USDC or a card key (/credits), first 25 free; failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

NameTypeReqDescription
textstringyesThe text

No output schema declared.

No examples provided.

units_convert ~179

Convert between units of length, mass, volume (incl. US cups and gallons), temperature (c, f, k), speed, area, data size (kB vs KiB), time, energy and pressure. Example units: km, mi, lb, kg, floz, ml, mph, kn, acre, gib, kwh, psi. Use when exact conversions matter. Example: value=10, from=km, to=mi. Price $0.01/call via x402 USDC or a card key (/credits), first 25 free; failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

NameTypeReqDescription
fromstringyesUnit to convert from
tostringyesUnit to convert to
valuenumberyesThe amount

No output schema declared.

No examples provided.

unix ~132

Convert a Unix timestamp (seconds or milliseconds, detected automatically) to ISO date and time, or an ISO date to a Unix timestamp. Without input, returns the current time in both forms. Use to read timestamps in logs and APIs. Example: value=1792281600. Price $0.01/call via x402 USDC or a card key (/credits), first 25 free; failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

NameTypeReqDescription
valuestring|number|boolean–Unix seconds/milliseconds or an ISO date (default now)

No output schema declared.

No examples provided.

url_decode ~120

Decode percent-encoded text, treating + as a space when plus=true (form encoding). Use to read encoded links and form data. Example: text=a%20b%26c. Price $0.01/call via x402 USDC or a card key (/credits), first 25 free; failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

NameTypeReqDescription
plusstring|number|boolean–true to read + as space
textstringyesThe encoded text

No output schema declared.

No examples provided.

url_encode ~107

Percent-encode text for use in a URL query value (encodeURIComponent) and as a full URL (encodeURI). Use when building query strings. Example: text=a b&c=d/é. Price $0.01/call via x402 USDC or a card key (/credits), first 25 free; failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

NameTypeReqDescription
textstringyesThe text to encode

No output schema declared.

No examples provided.

url_parse ~134

Split a URL into protocol, host, port, path, query parameters (as an object), hash and origin, and report whether the host is an IP address. Use to read query parameters or check a link's host. Example: url=https://example.com:8080/a/b?x=1&y=2#top. Price $0.01/call via x402 USDC or a card key (/credits), first 25 free; failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

NameTypeReqDescription
urlstringyesThe URL to parse

No output schema declared.

No examples provided.

uuid ~108

Generate 1 to 100 random version-4 UUIDs from a cryptographic random source. Use for IDs, idempotency keys and test data. Example: count=3. Price $0.01/call via x402 USDC or a card key (/credits), first 25 free; failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

NameTypeReqDescription
countinteger–How many (1-100, default 1)

No output schema declared.

No examples provided.

validate_iban ~128

Check an IBAN's format, its country-specific length and its mod-97 check digits, and return it formatted in groups of four. Use before saving bank details or paying out. Example: iban=SE45 5000 0000 0583 9825 7466. Price $0.01/call via x402 USDC or a card key (/credits), first 25 free; failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

NameTypeReqDescription
ibanstringyesThe IBAN, spaces allowed

No output schema declared.

No examples provided.

validate_isbn ~117

Check an ISBN-10 or ISBN-13 check digit and convert valid ISBN-10s to ISBN-13. Hyphens and spaces are ignored. Use before cataloguing or ordering books. Example: isbn=0-306-40615-2. Price $0.01/call via x402 USDC or a card key (/credits), first 25 free; failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

NameTypeReqDescription
isbnstringyesThe ISBN

No output schema declared.

No examples provided.

validate_luhn ~145

Check whether a card number or other ID passes the Luhn (mod 10) algorithm used by card numbers, IMEI numbers and many IDs, and compute the check digit to append. Only the format is checked; nothing is looked up. Use to catch typos in card or ID numbers. Example: number=79927398713. Price $0.01/call via x402 USDC or a card key (/credits), first 25 free; failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

NameTypeReqDescription
numberstring|number|booleanyesDigits, spaces and hyphens allowed

No output schema declared.

No examples provided.

xml_to_json ~176

Convert an XML document to JSON: attributes become "@name" keys, text becomes "#text" (or the value itself when an element only holds text), and repeated child elements become arrays. DOCTYPEs and external entities are refused, so nothing outside the document is ever loaded. Up to 100,000 characters. Use to read XML feeds, SOAP responses and config files in an agent. Example: xml=<order id="7"><item sku="a1">Pen</item><item sku="b2">Ink</item></order>. Price $0.01/call via x402 USDC or a card key (/credits), first 25 free; failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

NameTypeReqDescription
xmlstringyesThe XML document

No output schema declared.

No examples provided.

yes_no ~127

A fair random yes or no, with a cryptographic random source. For quick decisions when the options are equally good. Use to break ties. Price $0.01/call via x402 USDC or a card key (/credits), first 25 free; failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

NameTypeReqDescription
onlystring–Optional: comma-separated top-level result keys to keep, for a smaller answer (for example only=price,symbol); unknown keys are ignored and an empty match returns the full result

No output schema declared.

No examples provided.

Install

How do I install the Agent Data Tools: Utilities MCP server?

Agent Data Tools: Utilities is a hosted endpoint at https://agent-data-tools.revmesh2074.workers.dev/mcp/utilities, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · agent-data-tools.revmesh2074.workers.dev

# add to Claude Code
claude mcp add --transport http nutshell2000-agent-data-tools-utilities 'https://agent-data-tools.revmesh2074.workers.dev/mcp/utilities'
Common questions

What is the Agent Data Tools: Utilities MCP server?

Agent Data Tools: Utilities is an MCP server listed in the public MCP registry as io.github.Nutshell2000/agent-data-tools-utilities. 74 tools: JSON repair, CSV, hashes, cron, dates, units, validators. 25 free calls. This page covers its hosted endpoint (https://agent-data-tools.revmesh2074.workers.dev/mcp/utilities). Its publisher has verified ownership with us.

Is the Agent Data Tools: Utilities MCP server safe to use?

Agent Data Tools: Utilities scores 68 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Agent Data Tools: Utilities MCP server expose?

Agent Data Tools: Utilities exposes 63 tools: json_validate, json_format, json_minify, json_repair, json_to_csv, and 58 more. Their descriptions and schemas cost roughly 8,930 tokens of context every time the server is loaded.

Does the Agent Data Tools: Utilities MCP server require authentication?

No. We connected to Agent Data Tools: Utilities without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Agent Data Tools: Utilities MCP server still maintained?

Agent Data Tools: Utilities is still listed as active in the MCP registry. We last reached this channel on 24 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.