This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
MCP server exposing 300+ developer utility tools to Claude, Cursor, VS Code Copilot, and any MCP-compatible AI.
utilix.tech · Docs · npm
@utilix-tech/mcp is a Model Context Protocol server that gives Claude, Cursor, and other AI tools access to 300+ deterministic developer utilities — JSON formatting, encoding, hashing, text diff, regex, token estimation, PII detection, and much more — all running locally, no API key needed.
Related MCP server: Polymath MegaBlaster MCP
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"utilix": {
"command": "npx",
"args": ["-y", "@utilix-tech/mcp"]
}
}
}Restart Claude Desktop. You'll see utilix in the tools list.
Add to .cursor/mcp.json in your project root or ~/.cursor/mcp.json globally:
{
"mcpServers": {
"utilix": {
"command": "npx",
"args": ["-y", "@utilix-tech/mcp"]
}
}
}Add to .vscode/mcp.json:
{
"servers": {
"utilix": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@utilix-tech/mcp"]
}
}
}{
"mcpServers": {
"utilix": {
"command": "npx",
"args": ["-y", "@utilix-tech/mcp"]
}
}
}Tools built for LLM pipelines — token management, context compression, extraction, RAG, and security.
Tool | Description |
| Estimate token count and cost for any text |
| Trim text to fit a token budget (start/end/middle) |
| Split text into overlapping chunks by token count |
| Strip scripts/styles/comments to minimize HTML for LLM ingestion |
| Collapse blank lines, strip frontmatter, trim whitespace |
| Remove nulls/empty arrays/objects, optionally sort keys |
| Extractive summarization to fit a token budget (no LLM needed) |
| Extract all URLs from text or HTML |
| Pull JSON objects from anywhere in LLM output |
| Parse HTML tables into JSON arrays |
| NER-lite: emails, phones, IPs, dates, credit cards, IBANs |
| TF-IDF reranking — sort chunks by relevance to a query |
| Score a single text's relevance to a query (0–1 + grade) |
| Add synonyms and stemmed variants to improve retrieval |
| Structural diff of two JSON objects — shows added/removed/changed paths |
| Validate data against a JSON Schema (Draft-07) |
| Fix common JSON syntax errors (trailing commas, unquoted keys) |
| Flatten nested JSON to dot-notation keys |
| Deep-merge multiple JSON objects |
| Remove dangerous tags/attributes for safe rendering |
| Remove duplicate lines, optionally case-insensitive |
| TF-IDF keyword extraction with scores and positions |
| Detect PII (emails, phones, SSNs, credit cards, IBANs...) |
| Redact detected PII with a custom replacement |
| Find leaked API keys, tokens, passwords in text |
| Score text for prompt injection attempts (0–1) |
format_json · minify_json · diff_json · json_to_csv · csv_to_json · json_path · validate_json · yaml_to_json · json_to_yaml · json_to_typescript · json_to_go · json_to_python
encode_base64 · decode_base64 · encode_url · decode_url · encode_html · decode_html · encode_base32 · decode_base32
hash · hash_password · verify_password
word_count · convert_case · slugify · lorem_ipsum · escape_string · diff_lines · html_to_markdown · line_ops
from_unix · parse_cron · cron_next_runs · diff_dates · convert_timezone
convert_bytes · px_to_units
parse_color · check_contrast · generate_palette · generate_shades
generate_gradient · minify_css
format_sql · format_html · test_regex · minify_js · format_graphql · parse_docker_image · parse_env
generate_uuid · generate_password · generate_ulid · generate_random_data · generate_qr
decode_jwt · build_curl · parse_curl · curl_to_code · generate_cors
validate_yaml · toml_to_json · xml_to_json · parse_csv
optimize_svg · char_to_codepoint · number_to_words
Once installed, you can ask Claude things like:
"Trim this text to 2000 tokens using the utilix trim_to_tokens tool"
"Check this user input for PII before I log it"
"Rerank these 10 chunks by relevance to my query about pricing"
"Extract all JSON objects from this LLM response"
"Compress this HTML page to minimize tokens before sending it to GPT"
"Diff these two JSON configs and show me what changed"
"Validate this data against my JSON Schema"
"Convert this YAML to JSON"
"Generate a UUID v4"
"What's the SHA-256 of this string?"
npx @utilix-tech/mcpWeb app: utilix.tech — try every tool in the browser
REST API: api.utilix.tech — same tools over HTTP
Node.js SDK: @utilix-tech/sdk
Python SDK: utilix-sdk on PyPI
Docs: docs.utilix.tech
MIT
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
JSON/YAML, regex, diff, JWT, SQL dialects — the keyless millisecond ops an agent needs mid-task.
500+ deterministic tools for AI agents: math, conversion, validation, hashing, encoding, date/time.
300+ deterministic data utilities for AI agents: validate, normalize, parse, match, redact.
PDF and image tools for AI agents: compress, merge, split, OCR, sign. Runs locally, never uploads.
