Skip to content
ProtocolProbe
Explore

MCP servers › io.github.Nutshell2000 › agent-data-tools-utilities

MCP server · registry snapshot 2026-10-23 · last tested 2026-10-23

io.github.Nutshell2000/agent-data-tools-utilities

52 tools: JSON repair, CSV, hashes, cron, dates, units, validators. 25 free calls. — the publisher's description

4 of 5 record checks metRead-only · tools listed 2026-10-23Topic: developer-tools · AI-classifiedversion 1.50.5JavaScriptstreamable HTTP52 tools

Summary

io.github.Nutshell2000/agent-data-tools-utilities is a remote MCP server listed in the official MCP registry at version 1.50.5. On 2026-10-23 ProtocolProbe connected to it in read-only mode and read its inventory: 52 tools, 0 resources and 0 prompts.

Record checks

4 of 5 record checks met · 4 do not apply

  • met: Registry entry is active and says how to run it
  • met: Source repository link opens
  • met: Repository is not archived
  • met: Code pushed to the repository in the 90 days before our check
  • not met: Repository publishes a security policy (SECURITY.md)
  • not applicable: Package names its licence with a standard (SPDX) identifier
  • not applicable: The version the registry lists can be installed and is not withdrawn
  • not applicable: npm package carries build provenance (attestation)
  • not applicable: No known critical or high advisory in the package or its dependencies
  • Not ranked by downloads: a remote server publishes no download figure
  • Not ranked by stars: 0 stars (ranked from 10)

From public records, not a safety rating. Each check with its reason · Is it safe to install?

Key facts

Runs
remote (hosted by the publisher)
Transport
streamable HTTP
Sign-in
none needed to open a session
Repository
public
Tools
52
Described as changing data
0 of 52 toolsAI-classified
Mainly works on
nothing outside itself: it only answers questionsAI-classified
Topic
developer-toolsAI-classified
Last tested
2026-10-23

Add to your client

How fresh this is

Live-tested
yes, a real session (not a text-only review)
Last tested
2026-10-23
Mode
read-only (no tool calls)
Latest version
1.50.5, published 2026-10-22 (registry, as of the 2026-10-23 snapshot)
First listed version
2026-10-19 (earliest version still in the registry; older removed versions would be earlier)
Version history
54 versions listed, 2026-10-19 to 2026-10-22; 54 in the 90 days before the 2026-10-23 snapshot.
Most recent 12 versions
  • 1.50.5 · 2026-10-22
  • 1.50.4 · 2026-10-22
  • 1.50.3 · 2026-10-22
  • 1.50.2 · 2026-10-22
  • 1.50.1 · 2026-10-22
  • 1.50.0 · 2026-10-22
  • 1.49.1 · 2026-10-22
  • 1.49.0 · 2026-10-22
  • 1.48.6 · 2026-10-22
  • 1.48.5 · 2026-10-22
  • 1.48.4 · 2026-10-22
  • 1.48.3 · 2026-10-22
(versions still listed in the registry only)
Registry data
snapshot 2026-10-23
Package and repository
checked 2026-10-23
Engine
mcp-runtime-engine@0.1.0 · sdk@1.32.0

Changes since the last refresh

New in the registry: not in the list of 2026-10-04, listed on 2026-10-23 with version 1.50.5 (published 2026-10-22).

Source: the official MCP Registry list on 2026-10-04 and on 2026-10-23.

What it is

What does this server offer?

Observed inventory
52tools
0resources
0prompts

What it mainly works on, as our AI model read its tool descriptions: nothing outside itself: it only answers questions.

None of its 52 tools are described as changing anything.

  • json_validateon 15 other serverscalculates or converts

    “Check whether text is valid JSON.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    1 input, 1 required
    • textstringrequired“The JSON text to check (up to 20,000 characters)”
  • json_formaton 15 other serverscalculates or converts

    “Format JSON with indentation (2 or 4 spaces, or tabs) and optionally sorted keys.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    3 inputs, 1 required
    • textstringrequired“The JSON text”
    • indentstring or number or boolean“2 (default), 4 or tab”
    • sortKeysstring or number or boolean“true to sort object keys”
  • json_minifyon 4 other serverscalculates or converts

    “Remove all unnecessary whitespace from JSON and report the size before and after.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    1 input, 1 required
    • textstringrequired“The JSON text”
  • json_repairon 9 other serverscalculates or converts

    “Fix JSON as LLMs often write it: removes ```json fences and surrounding prose, comments and trailing commas, converts single quotes, quotes bare keys, maps True/False/None, and closes unclosed bracke…”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    1 input, 1 required
    • textstringrequired“The broken JSON text”
  • json_to_csvon 14 other serverscalculates or converts

    “Convert a JSON array of objects to CSV with a header row built from all keys.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    1 input, 1 required
    • textstringrequired“A JSON array of objects”
  • csv_to_jsonon 17 other serverscalculates or converts

    “Convert CSV (comma, semicolon, tab or pipe; delimiter detected automatically; quoted fields supported) to a JSON array of objects using the first row as keys.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    2 inputs, 1 required
    • textstringrequired“The CSV text, first row is the header”
    • numbersstring or number or boolean“true to turn numeric cells into numbers”
  • base64_encodeon 17 other serverscalculates or converts

    “Encode UTF-8 text as standard base64, and also return the URL-safe variant.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    1 input, 1 required
    • textstringrequired“The text to encode”
  • base64_decodeon 16 other serverscalculates or converts

    “Decode standard or URL-safe base64 to UTF-8 text.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    1 input, 1 required
    • textstringrequired“The base64 text”
  • url_encodeon 13 other serverscalculates or converts

    “Percent-encode text for use in a URL query value (encodeURIComponent) and as a full URL (encodeURI).”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    1 input, 1 required
    • textstringrequired“The text to encode”
  • url_decodeon 12 other serverscalculates or converts

    “Decode percent-encoded text, treating + as a space when plus=true (form encoding).”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    2 inputs, 1 required
    • textstringrequired“The encoded text”
    • plusstring or number or boolean“true to read + as space”
  • url_parseon 10 other serverscalculates or converts

    “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.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    1 input, 1 required
    • urlstringrequired“The URL to parse”
  • hashon 27 other serverscalculates or converts

    “Hash UTF-8 text with SHA-256 (default), SHA-1, SHA-384 or SHA-512 and return the digest in hex and base64.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    2 inputs, 1 required
    • textstringrequired“The text to hash”
    • algorithmstring“sha256 (default), sha1, sha384 or sha512”
Show 40 more tools
  • hmacon 8 other serverscalculates or converts

    “Compute an HMAC of a message with a key using SHA-256 (default), SHA-1, SHA-384 or SHA-512, in hex and base64.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    3 inputs, 2 required
    • messagestringrequired“The message”
    • keystringrequired“The key”
    • algorithmstring“sha256 (default), sha1, sha384 or sha512”
  • uuidon 18 other serverscalculates or converts

    “Generate 1 to 100 random version-4 UUIDs from a cryptographic random source.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    1 input
    • countinteger“How many (1-100, default 1)”
  • slugon 2 other serverscalculates or converts

    “Turn any text into a URL-friendly slug: accents removed (é→e, ß→ss), lower case, non-alphanumerics replaced by a separator (- by default).”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    2 inputs, 1 required
    • textstringrequired“The text”
    • separatorstring“- (default) or _”
  • caseon 2 other serverscalculates or converts

    “Convert text or identifiers between camelCase, PascalCase, snake_case, kebab-case, CONSTANT_CASE, Title Case, Sentence case, UPPER and lower.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    2 inputs, 2 required
    • textstringrequired“The text”
    • tostringrequired“camel, pascal, snake, kebab, constant, title, sentence, upper or lower”
  • text_statson 20 other serverscalculates or converts

    “Count characters, words, sentences and paragraphs, estimate reading and speaking time, and compute the Flesch reading-ease score and grade level for English text.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    1 input, 1 required
    • textstringrequired“The text”
  • text_extracton 6 other servers

    “Find all email addresses, URLs, phone-number-like strings, hashtags, @mentions and numbers in a text, each list de-duplicated.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    1 input, 1 required
    • textstringrequired“The text”
  • text_diffon 23 other serverscalculates or converts

    “Line-by-line difference between two texts: each line marked as unchanged, removed or added, with counts.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    2 inputs, 2 required
    • astringrequired“The original text”
    • bstringrequired“The new text”
  • cron_nexton 8 other servers

    “Next run times (in UTC) of a standard 5-field cron expression (minute hour day month weekday; ranges, lists, steps and names like MON or JAN supported).”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    3 inputs, 1 required
    • exprstringrequired“The cron expression”
    • countinteger“How many runs (1-50, default 5)”
    • fromstring“Start time, ISO (default now)”
  • date_diffon 6 other serverscalculates or converts

    “Time between two dates or timestamps: total days, weeks, hours, minutes and seconds, a years-months-days breakdown, and the number of weekdays (Monday-Friday) in between.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    2 inputs, 2 required
    • fromstringrequired“Start date or ISO timestamp”
    • tostringrequired“End date or ISO timestamp”
  • date_addon 4 other serverscalculates or converts

    “Add (or subtract, with negative numbers) years, months, weeks, days, hours and minutes to a date, or add business days (skipping Saturdays and Sundays).”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    8 inputs, 1 required
    • datestringrequired“Start date or ISO timestamp”
    • yearsinteger“Years to add (negative subtracts)”
    • monthsinteger“Months to add”
    • weeksinteger“Weeks to add”
    • daysinteger“Days to add”
    • hoursinteger“Hours to add”
    • minutesinteger“Minutes to add”
    • businessDaysinteger“Weekdays to add (skips weekends)”
  • date_infoon 1 other server

    “Weekday, ISO week number and week-year, day of the year, quarter, days in the month, leap year, Unix timestamp and whether it is a weekend, for any date.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    1 input
    • datestring“Date or ISO timestamp (default today)”
  • unixon 1 other servercalculates or converts

    “Convert a Unix timestamp (seconds or milliseconds, detected automatically) to ISO date and time, or an ISO date to a Unix timestamp.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    1 input
    • valuestring or number or boolean“Unix seconds/milliseconds or an ISO date (default now)”
  • units_converton 1 other servercalculates or converts

    “Convert between units of length, mass, volume (incl.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    3 inputs, 3 required
    • valuenumberrequired“The amount”
    • fromstringrequired“Unit to convert from”
    • tostringrequired“Unit to convert to”
  • number_wordson 2 other serverscalculates or converts

    “Write a whole number (up to trillions, negatives allowed) out in English words, e.g.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    1 input, 1 required
    • numbernumberrequired“The number, decimals allowed”
  • number_romanon 2 other serverscalculates or converts

    “Convert a number (1-3999) to Roman numerals, or Roman numerals back to a number.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    2 inputs
    • numberinteger“1 to 3999”
    • romanstring“Roman numerals to read”
  • validate_ibanon 30 other serverscalculates or converts

    “Check an IBAN's format, its country-specific length and its mod-97 check digits, and return it formatted in groups of four.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    1 input, 1 required
    • ibanstringrequired“The IBAN, spaces allowed”
  • validate_isbnon 4 other serverscalculates or converts

    “Check an ISBN-10 or ISBN-13 check digit and convert valid ISBN-10s to ISBN-13.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    1 input, 1 required
    • isbnstringrequired“The ISBN”
  • validate_luhnon 2 other serverscalculates or converts

    “Check whether a number passes the Luhn (mod 10) algorithm used by card numbers, IMEI numbers and many IDs, and compute the check digit to append.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    1 input, 1 required
    • numberstring or number or booleanrequired“Digits, spaces and hyphens allowed”
  • coloron 8 other serverscalculates or converts

    “Convert a colour between hex, RGB and HSL, and give its relative luminance and whether black or white text reads better on it.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    1 input, 1 required
    • colorstringrequired“The colour”
  • color_contraston 3 other serverscalculates or converts

    “WCAG 2 contrast ratio between a text colour and a background colour, with pass/fail for AA and AAA at normal and large text sizes.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    2 inputs, 2 required
    • fgstringrequired“Text colour”
    • bgstringrequired“Background colour”
  • ip_cidron 2 other serverscalculates or converts

    “Details of an IPv4 network in CIDR notation: network and broadcast address, first and last usable host, netmask, number of addresses, and whether a given IP falls inside.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    2 inputs, 1 required
    • cidrstringrequired“IPv4 network in CIDR notation”
    • ipstring“Optional IPv4 address to test for membership”
  • ip_infoon 5 other servers

    “Classify an IPv4 or IPv6 address without any lookup: version, whether it is private, loopback, link-local, carrier-grade NAT or public, and its integer and reverse-DNS forms (IPv4).”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    1 input, 1 required
    • ipstringrequired“The IP address”
  • semveron 5 other serverscalculates or converts

    “Compare two semantic versions (1.2.3, pre-releases like 2.0.0-rc.1 handled by the SemVer rules) and get which is newer, plus the next major, minor and patch versions of the first.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    2 inputs, 2 required
    • astringrequired“First version”
    • bstringrequired“Second version”
  • jwt_decodeon 32 other serverscalculates or converts

    “Decode a JSON Web Token's header and payload without verifying the signature, and report issued-at, not-before and expiry as dates and whether it has expired.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    1 input, 1 required
    • tokenstringrequired“The JWT”
  • markdown_to_htmlon 14 other serverscalculates or converts

    “Convert Markdown (headings, paragraphs, bold, italic, strikethrough, links, images, inline and fenced code, lists, quotes, rules) to HTML.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    1 input, 1 required
    • markdownstringrequired“The Markdown”
  • html_to_texton 9 other serverscalculates or converts

    “Strip HTML to readable plain text: scripts and styles removed, block elements become line breaks, list items get bullets, entities decoded.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    1 input, 1 required
    • htmlstringrequired“The HTML”
  • http_statuson 6 other servers

    “Name and plain-language meaning of an HTTP status code (1xx-5xx, including 402 Payment Required and 429 Too Many Requests), and whether to retry.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    1 input, 1 required
    • codeintegerrequired“Status code”
  • mimeon 2 other servers

    “MIME (content) type for a file name or extension, e.g.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    1 input, 1 required
    • filestringrequired“File name or extension”
  • coinon 2 other serverscalculates or converts

    “Flip one or more fair coins using a cryptographic random source.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    1 input
    • countinteger“How many coins (1-100, default 1)”
  • diceon 3 other serverscalculates or converts

    “Roll dice in standard notation such as 2d6+3 or 1d20, up to 100 dice of up to 1000 sides, with a cryptographic random source.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    1 input
    • rollstring“Dice notation, e.g.”
  • random_numberon 5 other serverscalculates or converts

    “One or more random whole numbers in a range (inclusive), optionally all different, from a cryptographic random source.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    4 inputs
    • mininteger“Lowest value (default 1)”
    • maxinteger“Highest value (default 100)”
    • countinteger“How many (1-1000, default 1)”
    • uniquestring or number or boolean“true for no repeats”
  • random_pickon 3 other serverscalculates or converts

    “Pick one or more items at random (without repeats) from a comma- or line-separated list.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    2 inputs, 1 required
    • itemsstringrequired“Comma-separated items”
    • countinteger“How many to pick (default 1)”
  • random_shuffleon 3 other serverscalculates or converts

    “Shuffle a comma- or line-separated list into a random order (Fisher-Yates with a cryptographic random source).”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    1 input, 1 required
    • itemsstringrequired“Comma-separated items”
  • random_teamson 1 other servercalculates or converts

    “Split a list of names into a given number of random, evenly sized teams.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    2 inputs, 1 required
    • itemsstringrequired“Comma-separated names”
    • teamsinteger“Number of teams (default 2)”
  • magic_8_ballon 1 other servercalculates or converts

    “Ask a yes-or-no question and get one of the 20 classic Magic 8-Ball answers, chosen at random.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    1 input
    • questionstring“Your question (optional, not stored)”
  • random_passwordon 2 other serversgenerates content

    “Generate strong random passwords or passphrase-style strings: choose length and character sets, from a cryptographic random source.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    3 inputs
    • lengthinteger“8-128 characters (default 20)”
    • symbolsstring or number or boolean“false to leave out symbols”
    • countinteger“How many (1-20, default 1)”
  • random_coloron 2 other serverscalculates or converts

    “One or more random colours in hex, RGB and HSL, optionally limited to pastel or dark tones.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    2 inputs
    • countinteger“How many (1-50, default 1)”
    • tonestring“any (default), pastel or dark”
  • yes_noon 1 other servercalculates or converts

    “A fair random yes or no, with a cryptographic random source.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    1 input
    • 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 retu…”
  • echoon 13 other serverscalculates or converts

    “Returns the message you send, with its length and the server time.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    1 input, 1 required
    • messagestringrequired“Message, up to 2,000 characters”
  • pingon 102 other serverscalculates or converts

    “A paid round-trip check: returns pong and the server time.”

    Publisher declares: read-only yes · destructive no · idempotent no · open-world yes

    1 input
    • 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 retu…”

Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-10-23.

How well are its tools described?

Features #4 and #5

How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.

Descriptions

AI reading of each description

Says what the tool does
100% of 52 tools
Says what it returns
100% of 52 tools
States limits, defaults or errors
100% of 52 tools
Says when to use it
100% of 52 tools
Items covered per tool
4.0 of 4 on average

Counted from the listing

Parameters with a description
100% of 86
Tools with a description
100% of 52
Typical description length
400 characters

The tool set

Counted from the listing

Tools
52
Size of the list
about 11,628 tokens for an agent to load (characters ÷ 4)
Naming
39 of 52 names use snake_case

AI reading: easy to mix up

No pair found.

The AI items cover 52 of 52 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none, comparing tools within groups of 40. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.

How do I add it to my client?

Config from the registry entry

From the remote endpoint (Streamable HTTP)

We connected to this URL on 2026-10-23 (a read-only session: no tool was called).

Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.

Claude Desktop or claude.ai
Settings → Connectors → Add custom connector, then paste:
https://agent-data-tools.revmesh2074.workers.dev/mcp/utilities
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
  "mcpServers": {
    "agent-data-tools-utilities": {
      "url": "https://agent-data-tools.revmesh2074.workers.dev/mcp/utilities"
    }
  }
}
VS Code · .vscode/mcp.json
{
  "servers": {
    "agent-data-tools-utilities": {
      "type": "http",
      "url": "https://agent-data-tools.revmesh2074.workers.dev/mcp/utilities"
    }
  }
}
VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"agent-data-tools-utilities","type":"http","url":"https://agent-data-tools.revmesh2074.workers.dev/mcp/utilities"}'
Claude Code
claude mcp add --transport http agent-data-tools-utilities https://agent-data-tools.revmesh2074.workers.dev/mcp/utilities
Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 --server-url https://agent-data-tools.revmesh2074.workers.dev/mcp/utilities --transport http
  • Optional settings the entry also lists (left out above): Authorization.
  • The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
  • The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.

Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.

Does the registry listing match what we found?

Feature #6

The registry verifies a package once, when it is published, and does not re-check it. A difference below is about the listing, not a judgement of the publisher.

Registry saysWe foundResultSource · date
Remote endpoint agent-data-tools.revmesh2074.workers.dev/mcp/utilitiesSession openedmatchesour test · 2026-10-23
No credential declared as requiredOpened a session without any credentialmatchesour test · 2026-10-23
Repository github.com/Nutshell2000/agent-data-toolsOpens publiclymatchesapi.github.com · 2026-10-23

Who made it?

Feature #7 · lineage

Facts about the publisher. We do not turn them into a trust score.

Namespace
io.github.Nutshell2000 · 8 servers
GitHub owner
a personal account (Nutshell2000)
Repository
github.com/Nutshell2000/agent-data-tools
Stars
0
Repository age
0–30 days
Last push
0–30 days ago
Archived
no
Security policy
none found (we looked for SECURITY.md in the repository and in its owner’s .github repository)

Source: the registry entry and api.github.com · 2026-10-23; security policy read from GitHub · 2026-10-23.

Publish this server? Run these checks against it yourself before release, from your own machine: a server the command starts, or your own server at its URL after a one-time proof that you control it: npx protocolprobe-selftest.

Choosing

Record checks

Public records · not a safety rating

4 of 5 record checks met · 4 do not apply

  • Not ranked by downloads: a remote server publishes no download figure
  • Not ranked by stars: 0 stars (ranked from 10)
  • MetRegistry entry is active and says how to run itActive, with a package or a remote address.
  • MetSource repository link opensThe linked GitHub repository is public.
  • MetRepository is not archivedNot archived.
  • MetCode pushed to the repository in the 90 days before our checkLast push 0-30 days before our check.
  • Not metRepository publishes a security policy (SECURITY.md)No SECURITY.md in the places GitHub reads it from.
  • Does not applyPackage names its licence with a standard (SPDX) identifierRemote server: it ships no package.
  • Does not applyThe version the registry lists can be installed and is not withdrawnRemote server: it ships no package.
  • Does not applynpm package carries build provenance (attestation)Remote server: it ships no package.
  • Does not applyNo known critical or high advisory in the package or its dependenciesRemote server: it ships no package.

Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-10-23. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating. How each check works · Leaderboards

Common questions about io.github.Nutshell2000/agent-data-tools-utilities

Answered from the data above

Is io.github.Nutshell2000/agent-data-tools-utilities safe to install?

We do not rate servers as safe or unsafe. 4 of its 5 applicable record checks are met (facts from public records, each listed on this page). What the records show: Its source repository opens publicly. Its repository had a push in the last 90 days. These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.

Does io.github.Nutshell2000/agent-data-tools-utilities need an API key or sign-in?

It opened a session without any credential on 2026-10-23. The registry entry declares no required credential; no declaration is not a guarantee.

Has io.github.Nutshell2000/agent-data-tools-utilities been security tested?

Partly. 3 of the 15 checks that apply to it were exercised. We connected and read what the server declares, but did not call its tools: ProtocolProbe calls no server's tools for anything it publishes. This is our choice, not a block by the server. No security verdict is published before verification.

What can io.github.Nutshell2000/agent-data-tools-utilities do?

It lists 52 tools. In our AI model's reading of their descriptions (two runs had to agree, nobody checked it by hand), they include tools that generate content and calculate or convert. We did not call any tool, so this describes the text, not the behaviour.

Can io.github.Nutshell2000/agent-data-tools-utilities change or delete data?

None of its 52 tools is described as changing anything (our AI model's reading of the descriptions; nobody checked it by hand). We did not call any tool.

Does io.github.Nutshell2000/agent-data-tools-utilities publish a security policy?

We found no SECURITY.md in its repository (root, .github/ or docs/) or in its owner's .github repository.

Where is the source code of io.github.Nutshell2000/agent-data-tools-utilities?

In github.com/Nutshell2000/agent-data-tools, which opens publicly.

Found this page useful?

Anonymous · no sign-in

A quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.

Similar servers

Same topic · AI-read

Active servers whose topic is also “developer-tools” and that have at least one tool of the same kind; most kinds in common first, then most GitHub stars. The topic and the tool kinds are an AI model's reading of the publishers' descriptions, not checked by hand. Similar is not a recommendation.

Compare with another server

Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.

Security testing

What did we test, and what did we leave out?

18 checks · features #1, #2

Not probed (we call no server's tools)

We connected and read what the server declares, but did not call its tools: ProtocolProbe calls no server's tools for anything it publishes. This is our choice, not a block by the server. No security score is given; a check we did not run is never counted as passed.

The 18 checks at a glanceour test · 2026-10-23
  1. Inventory: exercised
  2. Hidden instructions: exercised
  3. Real execution: not run · our policy
  4. Secret leak: not run · nothing to check it against
  5. Internal addresses: not run · our policy
  6. Unconfirmed changes: not run · our policy
  7. Bad input: not run · our policy
  8. Model requests: not run · nothing to check it against
  9. Sensitive questions: not run · nothing to check it against
  10. Folder boundary: not run · our policy
  11. Log leaks: not run · nothing to check it against
  12. Hidden content: not run · nothing to check it against
  13. Fake assistant turns: not applicable
  14. Token passthrough: not applicable
  15. Token audience: not applicable
  16. Sign-in redirect: not run · our policy
  17. Consent handling: not testable from outside
  18. Sign-in metadata: exercised

3 exercised12 not run (reason given)3 not applicable

Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 3 of the 15 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.

Exercised · 3
  • 1Inventory
    tool-list    Reads the declared tools, resources and prompts.exercised
  • 2Hidden instructions
    description-poisoning    Looks for hidden instructions in tool descriptions.exercised
  • 18Sign-in metadata
    oauth-url-scheme    Checks the published sign-in metadata for unsafe URLs.exercised
Not run, with the reason · 12
  • 3Real execution
    real-execution    Calls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 4Secret leak
    canary-leak    Plants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 5Internal addresses
    ssrf    Checks whether a tool can be steered to internal addresses.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 6Unconfirmed changes
    write-without-confirmation    Checks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 7Bad input
    error-handling    Sends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 8Model requests
    sampling    Checks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 9Sensitive questions
    elicitation-sensitive-data    Checks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 10Folder boundary
    root-boundary    Checks whether the server reaches outside the folders it was given.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 11Log leaks
    logging-side-channel    Checks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 12Hidden content
    audience-hiding    Checks resources that hide content from the user.This check needs content the server returns, and nothing was read or called.not run · nothing to check it against
  • 16Sign-in redirect
    open-redirect    Checks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy
  • 17Consent handling
    confused-deputy    Checks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside
Does not apply to this server · 3
  • 13Fake assistant turns
    fake-assistant-turn    Checks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable
  • 14Token passthrough
    token-passthrough    Checks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable
  • 15Token audience
    token-audience-validation    Checks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable

Source: our own test, 2026-10-23, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.

What happened during the test?

Feature #8

The steps in order, as the test record holds them.

  1. 0 msStarted a read-only session with the server's remote endpoint
  2. 46 msConnected after 0 redirects. No credential was sent or needed.
  3. Read the inventory: 52 tools, 0 resources, 0 prompts.
  4. 727 msFinished: 3 checks exercised.

Reference

How is it classified?

18 fields

One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.

TopicAI-classified
developer-tools
AI-classified · 2026-10-23
Pricing modelAI-classified
no value
No value: the AI answer was held back because the quoted text did not clearly support it.
Programming language
JavaScript
api.github.com · 2026-10-23
Hosting type
remote (hosted by the publisher)
registry · 2026-10-23
MCP capability
tools
our test · 2026-10-23
Transport
streamable HTTP
registry · 2026-10-23
Required credentials
none declared
registry · no declaration is not a guarantee
Package registry
does not apply
remote-only server: no package is shipped, so there is no package registry
Freshness
0–30 days
registry updatedAt · 2026-10-23
Lifecycle status
active
registry · 2026-10-23
License class
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Integrity hash
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Signature / provenance
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Dependency advisories
does not apply
ships no package, so there are no dependencies to audit
Popularity
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Publisher signals
owner: a personal account · repository age: 0–30 days · stars: 0–9
api.github.com · 2026-10-23
Maintenance
active
api.github.com · 2026-10-23
Environment
the publisher's infrastructure
where it runs, from the hosting type

“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.

Cite or correct this page

Sources and corrections

Suggested citation

ProtocolProbe. “io.github.Nutshell2000/agent-data-tools-utilities: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/io.github.Nutshell2000/agent-data-tools-utilities

Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.

As JSON: this record in the API · API documentation.

Badge for your README

ProtocolProbe: 4 of 5 record checks met

[![ProtocolProbe](https://protocolprobe.com/api/v1/badge/io.github.Nutshell2000/agent-data-tools-utilities)](https://protocolprobe.com/mcp/servers/io.github.Nutshell2000/agent-data-tools-utilities)

It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.

Something wrong, or is this yours?

If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here.

Write to hello@protocolprobe.com · corrections log · methodology