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.

Utilix

NPM · @UTILIX-TECH/MCP · 2 COMPONENTS

300+ offline developer utilities, plus 22 AI tools with a free API key. JSON, JWT, regex, cron, SQL.

0 this week 0 Trust /100

Last scanned (17 hours ago)

Scores higher than 0% of npm servers

Category Developer Tools

Recent critical change

CVE-2024-21534 affects this package (12 Nov 2026). See the changelog before you install this server.

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security73
Provenance & Transparency45
Schema Quality & AI Usability75
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 29537 tokens (~90/item across 327 items; 327 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management33
  • Stability observed for 10 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage96
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 87% of tool parameters carry a description.Partial
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 7 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "trim_to_tokens" implies "truncate" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 327 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
What we tested

Checks we ran (16)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

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.

  • 18 Nov 26 0
    • Package version: 0.110.0 → 0.111.0 functional
  • 17 Nov 26 0
    • Package version: 0.109.0 → 0.110.0 functional
  • 16 Nov 26 0
    • Tool safety: pass → unverified ▼ security
    • Stability: 0.13 → unverified ▼ security
    • Capabilities: pass → unverified ▼ functional
    • Tool coverage: 100 → unverified ▼ functional
    • First check of Schema quality: unverified functional
    • Package version: 0.108.0 → 0.109.0 functional
  • 15 Nov 26 0
    • Package version: 0.107.0 → 0.108.0 functional
  • 14 Nov 26 0
    • Package version: 0.106.0 → 0.107.0 functional
  • 13 Nov 26 0
    • Stability: 0.03 → unverified ▼ security
    • Tool safety: pass → unverified ▼ security
    • Capabilities: pass → unverified ▼ functional
    • Tool coverage: 100 → unverified ▼ functional
    • First check of Schema quality: unverified functional
    • Package version: 0.105.1 → 0.106.0 functional
  • 12 Nov 26 −43
    • CVE-2024-21534 affects this package: high ▼ critical
    • CVE-2025-1302 affects this package: high ▼ critical
    • Known CVEs: unverified → fail ▼ critical
    • Score status: scored → failed ▼ critical
    • Tool safety: pass → unverified ▼ security
    • Malware scan: unverified → pass ▲ security
    • Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet. security
    • Tool coverage: 100 → unverified ▼ functional
    • Capabilities: pass → unverified ▼ functional
    • Stability: unverified → 0.03 ▲ functional
    • Dependency health: unverified → 0.84 ▲ functional
    • Score status: failed → scored ▲ functional
    • First check of Schema quality: unverified functional
    • Package version: 0.103.0 → 0.105.1 functional
    • Package version: 0.103.0 → 0.105.0 functional
    • Package version: 0.103.0 → 0.104.2 functional
    • Package version: 0.103.0 → 0.104.1 functional
  • 11 Nov 26 43

    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 21 Nov 2026 · Analysed npm/@utilix-tech/mcp@0.111.0

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Vulnerabilities 3 findings
ID CVE Severity Vector Fix available
GHSA-hw8r-x6gr-5gjp CVE-2025-1302 critical CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H yes
GHSA-pppg-cpfq-h7wr CVE-2024-21534 critical CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H yes
GHSA-mrhx-c7xc-m3w5 CVE-2023-54404 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H yes

Background: What a vulnerability scan can and cannot prove →

Dependencies 141 packages
Packages resolved 141
Deprecated 1
Stale 46
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 327 exposed · ~29,537 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
ai_explain_css ~67

Explain a CSS snippet selector by selector and property by property in plain English. Runs on Utilix's hosted AI: needs a free Utilix API key (UTILIX_API_KEY) and counts toward that account's monthly AI limit.

NameTypeReqDescription
cssstringyesThe CSS to explain

No output schema declared.

No examples provided.

ai_explain_dockerfile ~71

Explain a Dockerfile instruction by instruction and flag size, cache and security issues. Runs on Utilix's hosted AI: needs a free Utilix API key (UTILIX_API_KEY) and counts toward that account's monthly AI limit.

NameTypeReqDescription
dockerfilestringyesThe Dockerfile contents

No output schema declared.

No examples provided.

ai_explain_error_message ~87

Explain an error message: what it means, the usual causes and how to fix it. Runs on Utilix's hosted AI: needs a free Utilix API key (UTILIX_API_KEY) and counts toward that account's monthly AI limit.

NameTypeReqDescription
contextstring–Optional context: language, tool, what you ran
messagestringyesThe error message

No output schema declared.

No examples provided.

ai_explain_iam_policy ~74

Explain an AWS IAM policy: who can do what on which resources, and over-broad permissions. Runs on Utilix's hosted AI: needs a free Utilix API key (UTILIX_API_KEY) and counts toward that account's monthly AI limit.

NameTypeReqDescription
policystringyesThe IAM policy JSON

No output schema declared.

No examples provided.

ai_explain_k8s_manifest ~68

Explain a Kubernetes manifest field by field and flag reliability or security issues. Runs on Utilix's hosted AI: needs a free Utilix API key (UTILIX_API_KEY) and counts toward that account's monthly AI limit.

NameTypeReqDescription
manifeststringyesThe YAML manifest

No output schema declared.

No examples provided.

ai_explain_nginx_config ~67

Explain an nginx config block by block and flag risky or missing settings. Runs on Utilix's hosted AI: needs a free Utilix API key (UTILIX_API_KEY) and counts toward that account's monthly AI limit.

NameTypeReqDescription
configstringyesThe nginx config

No output schema declared.

No examples provided.

ai_explain_regex ~80

Explain a regular expression token by token in plain English. Runs on Utilix's hosted AI: needs a free Utilix API key (UTILIX_API_KEY) and counts toward that account's monthly AI limit.

NameTypeReqDescription
flagsstring–Optional flags, e.g. gi
patternstringyesThe regex pattern, without delimiters

No output schema declared.

No examples provided.

ai_explain_shell_command ~68

Explain a shell command part by part, including every flag, pipe and redirect. Runs on Utilix's hosted AI: needs a free Utilix API key (UTILIX_API_KEY) and counts toward that account's monthly AI limit.

NameTypeReqDescription
commandstringyesThe shell command

No output schema declared.

No examples provided.

ai_explain_sql ~86

Explain what a SQL query does, step by step, and point out performance concerns. Runs on Utilix's hosted AI: needs a free Utilix API key (UTILIX_API_KEY) and counts toward that account's monthly AI limit.

NameTypeReqDescription
dialectstring–Optional dialect, e.g. postgres, mysql, sqlite
sqlstringyesThe SQL query

No output schema declared.

No examples provided.

ai_explain_stack_trace ~89

Summarise a stack trace: the likely root cause, where it originates and how to fix it. Runs on Utilix's hosted AI: needs a free Utilix API key (UTILIX_API_KEY) and counts toward that account's monthly AI limit.

NameTypeReqDescription
contextstring–Optional context: framework, what you were doing
tracestringyesThe stack trace

No output schema declared.

No examples provided.

ai_explain_terraform ~68

Explain Terraform configuration: what each resource creates and notable risks. Runs on Utilix's hosted AI: needs a free Utilix API key (UTILIX_API_KEY) and counts toward that account's monthly AI limit.

NameTypeReqDescription
configstringyesThe Terraform (HCL) configuration

No output schema declared.

No examples provided.

ai_generate_commit_message ~82

Write a Conventional Commits message for a git diff. Runs on Utilix's hosted AI: needs a free Utilix API key (UTILIX_API_KEY) and counts toward that account's monthly AI limit.

NameTypeReqDescription
contextstring–Optional context: ticket, intent, scope
diffstringyesOutput of git diff (staged changes)

No output schema declared.

No examples provided.

ai_generate_cron ~76

Turn a plain-English schedule into a cron expression with an explanation. Runs on Utilix's hosted AI: needs a free Utilix API key (UTILIX_API_KEY) and counts toward that account's monthly AI limit.

NameTypeReqDescription
descriptionstringyesThe schedule, e.g. "every weekday at 9:30am"

No output schema declared.

No examples provided.

ai_generate_dockerfile ~91

Generate a production-ready Dockerfile from a description of the app. Runs on Utilix's hosted AI: needs a free Utilix API key (UTILIX_API_KEY) and counts toward that account's monthly AI limit.

NameTypeReqDescription
contextstring–Optional constraints, e.g. base image or port
descriptionstringyesDescribe the app: language, framework, build and run steps

No output schema declared.

No examples provided.

ai_generate_docstring ~110

Write an idiomatic documentation comment (JSDoc, Google-style docstring, Javadoc, rustdoc...) for a function or class. Runs on Utilix's hosted AI: needs a free Utilix API key (UTILIX_API_KEY) and counts toward that account's monthly AI limit.

NameTypeReqDescription
codestringyesThe function or class source
languagestring–Optional language
stylestring–Optional doc style, e.g. jsdoc, google, numpy

No output schema declared.

No examples provided.

ai_generate_json_schema ~87

Generate a JSON Schema (Draft-07) from a plain-English description of the data, optionally guided by an example. Runs on Utilix's hosted AI: needs a free Utilix API key (UTILIX_API_KEY) and counts toward that account's monthly AI limit.

NameTypeReqDescription
descriptionstringyesDescribe the data shape
examplestring–Optional example JSON document

No output schema declared.

No examples provided.

ai_generate_pr_description ~75

Write a pull request title and description from a diff. Runs on Utilix's hosted AI: needs a free Utilix API key (UTILIX_API_KEY) and counts toward that account's monthly AI limit.

NameTypeReqDescription
contextstring–Optional context: issue, motivation
diffstringyesThe branch diff

No output schema declared.

No examples provided.

ai_generate_regex ~87

Generate a regular expression from a plain-English description, with flags, an explanation and matching / non-matching examples. Runs on Utilix's hosted AI: needs a free Utilix API key (UTILIX_API_KEY) and counts toward that account's monthly AI limit.

NameTypeReqDescription
descriptionstringyesWhat the regex should match, e.g. "US ZIP codes with optional +4"

No output schema declared.

No examples provided.

ai_generate_shell_command ~106

Turn a plain-English task into a shell command, with a breakdown of every flag. Runs on Utilix's hosted AI: needs a free Utilix API key (UTILIX_API_KEY) and counts toward that account's monthly AI limit.

NameTypeReqDescription
shellstring–Target shell, e.g. bash, zsh, fish, powershell
taskstringyesWhat you want to do, e.g. "find files over 100MB modified this week"

No output schema declared.

No examples provided.

ai_generate_sql ~142

Write a SQL query from a plain-English question, using only the tables and columns in the schema you pass. Returns the query, its assumptions, and warnings for any write or unscoped UPDATE/DELETE statement. Nothing is executed. Runs on Utilix's hosted AI: needs a free Utilix API key (UTILIX_API_KEY) and counts toward that account's monthly AI limit.

NameTypeReqDescription
dialectstring–Optional dialect, e.g. postgres, mysql, sqlite, sqlserver
questionstringyesWhat to query, in plain English
schemastring–Optional schema, e.g. CREATE TABLE statements. Strongly recommended

No output schema declared.

No examples provided.

ai_generate_svg ~111

Generate an SVG illustration or icon from a text description. Returns the SVG markup and a hosted URL. Runs on Utilix's hosted AI: needs a free Utilix API key (UTILIX_API_KEY) and counts toward that account's monthly AI limit.

NameTypeReqDescription
heightinteger–Optional height in px
promptstringyesWhat to draw
stylestring–Optional style, e.g. flat, outline, isometric
widthinteger–Optional width in px

No output schema declared.

No examples provided.

ai_generate_test_cases ~80

Generate unit test cases (happy path, edge cases, errors) for a function. Runs on Utilix's hosted AI: needs a free Utilix API key (UTILIX_API_KEY) and counts toward that account's monthly AI limit.

NameTypeReqDescription
codestringyesThe function source
languagestring–Optional language / test framework

No output schema declared.

No examples provided.

align_markdown_tables ~83

Reformat every GitHub-Flavored-Markdown pipe table in a document so each column's pipes line up visually, padding cells to the widest content in that column and rebuilding the delimiter row to match, while preserving each column's declared alignment. Tables inside fenced code blocks are left untouched.

NameTypeReqDescription
markdownstringyesThe Markdown document containing one or more pipe tables

No output schema declared.

No examples provided.

analyze_caption_speed ~134

Parse an SRT or WebVTT file and report the words-per-minute reading speed implied by each cue's word count and duration, flagging cues that exceed common broadcast accessibility guidelines (default: ~180 WPM, ~20 characters/second). HTML-style cue tags like <i> are stripped before counting words and characters.

NameTypeReqDescription
cpsThresholdnumber–Characters-per-second above which a cue is flagged (default 20)
inputstringyesThe SRT or WebVTT file contents
wpmThresholdnumber–Words-per-minute above which a cue is flagged (default 180)

No output schema declared.

No examples provided.

analyze_email_headers ~114

Parse a raw email header block (e.g. Gmail's "Show original", or the headers from a .eml file) into structured fields, the Received hop chain in the order they appear, and any SPF/DKIM/DMARC verdicts already present in an Authentication-Results header. Never performs a live DNS/SPF/DKIM check, it only reports what the pasted headers already claim.

NameTypeReqDescription
headersstringyesThe raw email header block (From/To/Received/Authentication-Results/...)

No output schema declared.

No examples provided.

analyze_keyword_density ~168

Count keyword or phrase frequency and density (occurrences per 100 words) across a block of text, the way an SEO keyword-density checker does. With the default ngramSize of 1, common English stopwords and words shorter than minWordLength are excluded; for ngramSize 2 or 3 (phrases), stopwords are kept since useful phrases often contain them.

NameTypeReqDescription
minWordLengthinteger–Minimum word length to include (default 3)
ngramSizeinteger–Phrase length in words: 1 for single words, 2 or 3 for phrases (default 1)
textstringyesThe text to analyze
topNinteger–Number of top keywords/phrases to return (default 10)

No output schema declared.

No examples provided.

analyze_regex_groups ~114

Parse a regex pattern's capture groups (numbered and named) and backreferences, and flag any backreference pointing at a group that doesn't exist or hasn't finished being defined yet at that point in the pattern (a forward reference or self-reference). Structural, non-AI check. Pass the pattern body only, no delimiters or flags.

NameTypeReqDescription
patternstringyesThe regex pattern body to analyze, e.g. (?<year>\d{4})-(?<month>\d{2})\k<year>

No output schema declared.

No examples provided.

analyze_sentence_lengths ~50

Split text into sentences and report a histogram of sentence lengths in words, plus mean, median, standard deviation, and a consistency label. Distinct from readability grade scores.

NameTypeReqDescription
textstringyes–

No output schema declared.

No examples provided.

apply_json_merge_patch ~110

Apply an RFC 7396 JSON Merge Patch document to a target JSON document and return the merged result. A null-valued key in the patch removes that key from the target; a patch that is not itself a JSON object replaces the target wholesale, which is how arrays are replaced rather than merged element by element.

NameTypeReqDescription
patchstringyesThe RFC 7396 JSON Merge Patch document, as a JSON string
targetstringyesThe target JSON document, as a JSON string

No output schema declared.

No examples provided.

apply_json_patch ~92

Apply a sequence of RFC 6902 JSON Patch operations (add, remove, replace, move, copy, test) to a target JSON document and return the result, or an error naming the first operation that failed and why.

NameTypeReqDescription
patchstringyesThe RFC 6902 JSON Patch operation array, as a JSON string
targetstringyesThe document to patch, as a JSON string

No output schema declared.

No examples provided.

audit_css_custom_properties ~67

Audit a CSS stylesheet's custom-property (`--name`) declarations against their `var(--name)` usages: which ones are declared but never referenced, referenced but never declared, and declared more than once within the same selector block.

NameTypeReqDescription
cssstringyesThe CSS stylesheet to audit

No output schema declared.

No examples provided.

audit_dependency_ranges ~83

Parse a package.json's dependencies, devDependencies, peerDependencies, and optionalDependencies fields, classify each version specifier's range type, and flag wildcard ranges, the non-reproducible "latest" tag, git/URL/file/link dependencies, and packages listed with conflicting or redundant ranges across sections.

NameTypeReqDescription
textstringyesThe full package.json file contents

No output schema declared.

No examples provided.

audit_markdown_image_alt_text ~107

Scan a Markdown document's inline images (`![alt](src)`) and flag alt text accessibility smells: missing/empty alt text, a generic placeholder word used alone ("image", "photo"), alt text that's just the image's own filename, and a redundant "image of"/"photo of" prefix. Only inline image syntax is scanned; reference-style images and raw HTML `<img>` tags are not detected.

NameTypeReqDescription
markdownstringyesThe Markdown document to scan

No output schema declared.

No examples provided.

base32_decode ~34

Decode a Base32 string.

NameTypeReqDescription
alphabetstring––
inputstringyesBase32 string to decode

No output schema declared.

No examples provided.

base32_encode ~33

Encode a string to Base32.

NameTypeReqDescription
alphabetstring––
inputstringyesString to encode

No output schema declared.

No examples provided.

base58_decode ~31

Decode a Base58 string back to text.

NameTypeReqDescription
inputstringyesThe Base58 string to decode

No output schema declared.

No examples provided.

base58_encode ~39

Encode text as Base58 (Bitcoin-address style, no ambiguous 0/O/I/l characters).

NameTypeReqDescription
inputstringyesThe text to encode

No output schema declared.

No examples provided.

base62_decode ~31

Decode a Base62 string back to text.

NameTypeReqDescription
inputstringyesThe Base62 string to decode

No output schema declared.

No examples provided.

base62_encode ~35

Encode text as Base62 (alphanumeric, URL-safe, no punctuation).

NameTypeReqDescription
inputstringyesThe text to encode

No output schema declared.

No examples provided.

base64_decode ~27

Decode a Base64 string.

NameTypeReqDescription
inputstringyesBase64 string to decode

No output schema declared.

No examples provided.

base64_encode ~26

Encode a string to Base64.

NameTypeReqDescription
inputstringyesString to encode

No output schema declared.

No examples provided.

bcrypt_hash ~41

Hash a password using bcrypt.

NameTypeReqDescription
passwordstringyesPassword to hash
roundsinteger–Salt rounds (8–14, default 10)

No output schema declared.

No examples provided.

bcrypt_verify ~38

Verify a password against a bcrypt hash.

NameTypeReqDescription
hashstringyesbcrypt hash to verify against
passwordstringyesPlain-text password

No output schema declared.

No examples provided.

build_accept_language ~79

Build an Accept-Language request-header value from a list of locale/quality pairs, sorting by descending quality (ties keep their original order) and omitting ";q=1" for the default weight, per RFC 9110 section 12.5.4.

NameTypeReqDescription
localesarrayyesLocale/quality pairs to build the header from

No output schema declared.

No examples provided.

build_alt_svc_header ~83

Build an Alt-Svc response-header value (RFC 7838) from one or more alternative services, each a protocol-id (e.g. "h3"), optional host, port, max-age in seconds, and an optional persist flag, attaching a plain-English note for each well-known protocol-id.

NameTypeReqDescription
alternativesarrayyesAlternative services to advertise

No output schema declared.

No examples provided.

build_basic_auth_header ~62

Build a `Basic` Authorization header value (RFC 7617, base64 of `username:password`) from a username and password.

NameTypeReqDescription
passwordstringyesThe password
usernamestringyesThe username (must not contain a colon)

No output schema declared.

No examples provided.

build_bearer_auth_header ~40

Build a `Bearer` Authorization header value (RFC 6750) from a token.

NameTypeReqDescription
tokenstringyesThe bearer token

No output schema declared.

No examples provided.

build_caa_record ~188

Build a CAA (Certification Authority Authorization) DNS record (RFC 8659) from a tag plus either a domain (the CA authorized to issue, or null for a disallow-all record) or a raw value, with optional "; key=value" params and a critical flag.

NameTypeReqDescription
criticalboolean–Sets flags to 128 (the critical bit) instead of 0
domainstring|null–Authorized CA domain for issue/issuewild/issuemail; pass null to disallow all issuance
paramsarray–Extra "; key=value" parameters appended after domain
tagstringyesCAA tag, e.g. "issue", "issuewild", "iodef", "issuemail"
valuestring–Raw value to use instead of domain/params, required for tags other than issue/issuewild/issuemail

No output schema declared.

No examples provided.

build_cache_control ~206

Build an HTTP Cache-Control response-header value from a set of directives (public/private, no-cache, no-store, max-age, s-maxage, must-revalidate, immutable, stale-while-revalidate, etc.), with a plain-English explanation of each directive and warnings for combinations that cancel each other out. Pure string assembly, not validated against a live origin.

NameTypeReqDescription
immutableboolean––
maxAgeinteger–Freshness lifetime in seconds
mustRevalidateboolean––
mustUnderstandboolean––
noCacheboolean––
noStoreboolean––
noTransformboolean––
proxyRevalidateboolean––
sMaxAgeinteger–Freshness lifetime for shared caches, in seconds
staleIfErrorinteger––
staleWhileRevalidateinteger––
visibilitystring–public (any cache) or private (browser only)

No output schema declared.

No examples provided.

build_character_class ~171

Assemble a [...] regex character class from named building blocks (lowercase, uppercase, digits, whitespace), custom character ranges, and literal custom characters, with optional negation. Pure string assembly, it never runs the resulting pattern against any input.

NameTypeReqDescription
customCharsstring–Literal characters to include as-is; duplicates are ignored
customRangesarray–Custom ranges like "f-k", each exactly two characters joined by a hyphen
digitsboolean–Include 0-9
lowercaseboolean–Include a-z
negateboolean–Wrap the class in [^...] to match any character NOT in the set
uppercaseboolean–Include A-Z
whitespaceboolean–Include \s (space, tab, newline, etc.)

No output schema declared.

No examples provided.

Install

How do I install the Utilix MCP server?

Utilix runs locally as an npm package, launched with npx -y @utilix-tech/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · @utilix-tech/mcp

# add to Claude Code
claude mcp add utilix-tech-utilix-mcp -- npx -y @utilix-tech/mcp
Common questions

What is the Utilix MCP server?

Utilix is an MCP server listed in the public MCP registry as io.github.utilix-tech/utilix-mcp. 300+ offline developer utilities, plus 22 AI tools with a free API key. JSON, JWT, regex, cron, SQL. This page covers its npm package (@utilix-tech/mcp).

What tools does the Utilix MCP server expose?

Utilix exposes 327 tools: format_json, minify_json, diff_json, json_to_csv, csv_to_json, and 322 more. Their descriptions and schemas cost roughly 29,537 tokens of context every time the server is loaded.

Is the Utilix MCP server still maintained?

Utilix is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the Utilix MCP server under?

Utilix declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.