servers / toolbox-mcp
toolbox-mcp
communitystdiolocalwrite capablehealthy
MCP server with 35 local tools for AI agents: read PDFs, exact math, image convert & resize, QR codes, crypto, timezone, regex, JSON/CSV. Works in Claude, Cursor, VS Code and Antigravity. No network, fully private.
01Tools · 45
How to read this: tool names here are observed from a live tools/list handshake. The Risk label is a heuristic inferred from the tool name (write/destructive verbs), not from executing the tool — a conservative guess, not a verified capability. We never escalate risk from a description. Found one that's wrong? Tell us — we fix on report.
| Tool | Risk | Side effects | Approval |
|---|---|---|---|
| base64_decode Decode Base64 back to text. | unknown | unknown | unknown |
| url_encode Percent-encode text for safe use in a URL. | unknown | unknown | unknown |
| base64_encode Encode text to Base64. | unknown | unknown | unknown |
| generate_uuid Generate one or more random UUIDs (version 4). | unknown | unknown | unknown |
| hash_text Generate a cryptographic hash of text. Supports md5, sha1, sha256, sha384, sha512. | unknown | unknown | unknown |
| bcrypt_hash Hash a password with bcrypt, using a chosen cost factor. | unknown | unknown | unknown |
| password_generate Generate a strong random password using a cryptographically secure source. | unknown | unknown | unknown |
| url_decode Decode a percent-encoded URL string back to text. | unknown | unknown | unknown |
| pdf_info Report page count, PDF metadata (title, author) and file size. | read | false | unknown |
| jwt_decode Decode a JWT and show its header and payload as readable JSON. Does NOT verify the signature. | read | false | unknown |
| cron_describe Explain a cron expression in plain English and list the next few run times. Use this instead of interpreting cron yourself. | read | false | unknown |
| slugify Convert any text into a clean URL slug (lowercase, dashes, no accents or symbols). | unknown | unknown | unknown |
| convert_color Convert a hex color (#rrggbb) into RGB and HSL values. | unknown | unknown | unknown |
| pdf_extract_text Extract the readable text from a PDF so the agent can actually read the document. Use this to read a PDF's contents. | read | false | unknown |
| html_to_markdown Convert an HTML fragment or page into clean Markdown. Useful for turning scraped pages into readable text. | unknown | unknown | unknown |
| image_grayscale Convert an image to grayscale (black and white). | unknown | unknown | unknown |
| xlsx_to_json Read an Excel spreadsheet (.xlsx) and return the first sheet as a JSON array of objects. | read | false | unknown |
| images_to_pdf Combine one or more images (PNG or JPG) into a single PDF, one image per page. | unknown | unknown | unknown |
| hmac_sign Compute an HMAC signature of a message with a secret key. Supports sha256, sha1, sha512. | unknown | unknown | unknown |
| calculate Evaluate a math expression exactly. Supports arithmetic, powers, roots, trig, and unit conversions like '5 km to miles'. Use this instead of doing math yourself. | unknown | unknown | unknown |
| pdf_merge Merge several PDF files into one, in the order given. | write | true | unknown |
| diff_text Compare two blocks of text and show a precise line-by-line diff (added, removed, unchanged). | read | false | unknown |
| image_watermark Overlay a line of text as a watermark on an image (bottom corner). | unknown | unknown | unknown |
| format_json Validate and reformat JSON. Pretty-prints by default, or minifies. Reports errors clearly. | unknown | unknown | unknown |
| regex_extract Apply a regular expression to text and return every match exactly. Use this instead of scanning text yourself, which is error prone. | unknown | unknown | unknown |
| exif_read Read the EXIF metadata from a photo (camera, date taken, GPS if present). | read | false | unknown |
| pdf_watermark Stamp a diagonal text watermark across every page of a PDF. | unknown | unknown | unknown |
| image_convert Convert an image to another format: png, jpeg, webp, avif, gif or tiff. | unknown | unknown | unknown |
| csv_to_json Convert CSV text into a JSON array of objects using the header row as keys. | unknown | unknown | unknown |
| qr_decode Read the text or URL out of a QR code image. | read | false | unknown |
| bcrypt_verify Check whether a password matches a bcrypt hash. | unknown | unknown | unknown |
| image_resize Resize an image. Give width, height, or both. 'fit' controls how it fits the box. | unknown | unknown | unknown |
| qr_generate Generate a QR code image (PNG) from text or a URL and save it to a file. | unknown | unknown | unknown |
| zip_create Create a .zip archive from a list of files. | write | true | unknown |
| pdf_rotate Rotate every page of a PDF by 90, 180 or 270 degrees. | unknown | unknown | unknown |
| zip_extract Extract all entries from a .zip archive into a folder. | unknown | unknown | unknown |
| change_case Convert text between cases: upper, lower, title, sentence, camel, snake, kebab, constant. | unknown | unknown | unknown |
| image_rotate Rotate an image by any angle (degrees, clockwise). | unknown | unknown | unknown |
| json_to_xlsx Write a JSON array of objects to an Excel spreadsheet (.xlsx). | unknown | unknown | unknown |
| text_stats Count words, characters, sentences and lines in text, with an estimated reading time. | read | false | unknown |
| pdf_split Extract a range of pages from a PDF into a new PDF. Pages are 1-based and inclusive. | unknown | unknown | unknown |
| timezone_convert Convert a date and time from one timezone to another. Use IANA zone names like 'America/New_York' or 'Asia/Tokyo'. Use this instead of doing timezone math yourself. | unknown | unknown | unknown |
| image_crop Crop a rectangular region out of an image. | unknown | unknown | unknown |
| image_info Report an image's format, dimensions, color channels and file size. | read | false | unknown |
| image_compress Compress an image to reduce file size, keeping its format. Lower quality = smaller file. | unknown | unknown | unknown |
02Install & source
npx -y toolbox-mcp
npx- repohttps://github.com/medoxisto/toolbox-mcp
- homepagehttps://www.npmjs.com/package/toolbox-mcp
- licenseMIT
- adoption19 stars · 6 forks
05Provenance & freshness
sourcesGitHub repo search [p4]
last_checked2026-08-18 15:22Z
next_check2026-08-18 18:16Z
cadenceevery 3h
verifiedtools_list:passed handshake:passed metadata:passed handshake:failed metadata:passed handshake:failed metadata:passed handshake:failed metadata:passed handshake:failed
index_statusindex — 8 unique facts >= 5
06Badge
Add the “as seen on MCPExplorer” badge to your README. 
[](https://mcpexplorer.com/servers/toolbox-mcp)
Next step
This is one server. A loadout combines the right servers, governance, and proven plays for a whole job — assembled deliberately, not tool-dumped.
Explore loadouts →