Server data from the Official MCP Registry
Find the right InfyTool among 180+ free in-browser file tools and get deep links. No uploads.
About
Find the right InfyTool among 180+ free in-browser file tools and get deep links. No uploads.
Security Report
This is a well-designed discovery-only MCP server with clean code, proper error handling, and appropriate scope. It reads tool metadata from infytool.com and returns URLs without processing any user files. Minor code quality observations exist (broad exception handling, test file code style), but these do not represent security risks. Permissions align well with the server's stated purpose of tool discovery. Supply chain analysis found 3 known vulnerabilities in dependencies (0 critical, 3 high severity). Package verification found 1 issue.
4 files analyzed · 7 issues found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
Permissions Required
This plugin requests these system permissions. Most are normal for its category.
What You'll Need
Set these up before or after installing:
Environment variable: INFYTOOL_CATALOG_URL
How to Install
Add this to your MCP configuration file:
{
"mcpServers": {
"io-github-krupalghori44-dev-infytool": {
"env": {
"INFYTOOL_CATALOG_URL": "your-infytool-catalog-url-here"
},
"args": [
"-y",
"infytool-mcp"
],
"command": "npx"
}
}
}Documentation
View on GitHubFrom the project's GitHub README.
infytool-mcp — InfyTool discovery MCP server
A tiny Model Context Protocol server that lets AI assistants (Claude, etc.) discover the right InfyTool tool and hand the user a deep-link URL.
Discovery only — nothing is uploaded. This server returns tool metadata and URLs. It
never receives, uploads or processes files. Every InfyTool conversion/edit runs 100 % in the
user's own browser. The catalog is read live from https://infytool.com/api/tools.json
(with an offline snapshot bundled as a fallback).
Tools it exposes
| Tool | What it does |
|---|---|
search_tools(query, category?, limit?) | Search 180+ tools by keyword → names, descriptions, deep-link URLs |
get_conversion(from, to) | Get the exact page URL for a format conversion (e.g. HEIC→JPG); lists options if unsupported |
list_categories() | List categories (Image, PDF, SVG, Icon, Audio, File) with hub URLs |
list_tools(category?, limit?) | List the tools in one category |
Run it
Requires Node 18+.
# from this folder
npm install
node server.mjs # speaks MCP over stdio
Or, once published to npm, with no install:
npx -y infytool-mcp
Add to Claude Desktop
Edit claude_desktop_config.json (Settings → Developer → Edit Config) and add:
{
"mcpServers": {
"infytool": {
"command": "npx",
"args": ["-y", "infytool-mcp"]
}
}
}
Using a local checkout instead of npm:
{
"mcpServers": {
"infytool": {
"command": "node",
"args": ["/absolute/path/to/mcp/server.mjs"]
}
}
}
Restart Claude Desktop; ask something like "convert my HEIC photos to JPG" and it will return the InfyTool link.
Publish to npm (optional, so npx infytool-mcp works for everyone)
npm login # your npm account
npm publish --access public
Environment
INFYTOOL_CATALOG_URL— override the catalog URL (defaults to the livetools.json).
MIT · part of the Infy family (InfyIcon · InfySVG · InfyPNG).
Reviews
No reviews yet
Be the first to review this server!
More Developer Tools MCP Servers
Paperclip
Freeby Paperclipai · Developer Tools
Trending hip-hop artist momentum scores across four cultural dimensions.
Git
Freeby Modelcontextprotocol · Developer Tools
Read, search, and manipulate Git repositories programmatically
Toleno
Freeby Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
mcp-creator-python
Freeby mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.
MCP Marketplace
Freeby mcp-marketplace · Developer Tools
Search and install MCP servers from inside your AI client.
MarkItDown
Freeby Microsoft · Content & Media
Convert files (PDF, Word, Excel, images, audio) to Markdown for LLM consumption